Technological solutions to the challenges of scaling up aquaponic systems: a comprehensive approach

1 Introduction

Primary food production faces threats from water scarcity, resource depletion, soil degradation, declining yields, and environmental damage. Climate change worsens these problems by altering rainfall patterns, causing extreme weather, and increasing pest and disease outbreaks, all of which lead to reduced biodiversity (Sarkar et al., 2020). These issues occur alongside a growing global population, which is expected to reach approximately 10 billion by 2050 (United Nations (UN), 2019). To meet this increasing demand, food production must be sustainable, ensuring food security for everyone while adapting to climate change (Charles et al., 2014).

Fish-derived animal protein has been essential for health and nutrition (Khalili Tilami and Sampels, 2018). The overuse of fishery resources has increased dependence on aquaculture to ensure sustainable fish production (Costello et al., 2020). A key benefit of aquaculture is the diversification of production methods, such as recirculating aquaculture systems (RAS), which provide an alternative approach when biophysical and environmental conditions are unfavorable, helping to avoid disease and contamination, competition for land and water, and poor-quality products. These systems can also produce fish in high-quality production environments (Ahmed and Turchini, 2021). Despite their effectiveness, these systems are primarily used for monoculture production. To improve on this, integrated systems such as aquaponics should be developed to combine aquaculture and horticultural production (Boyd et al., 2020). Integration offers various benefits, including increased productivity, diversification, and sustainability (Ignowski et al., 2023). It can also optimize resource efficiency, sustain ecosystem balance, and enhance food security (Aznar-Sánchez et al., 2020). Aquaponics can operate as a semi-closed system, eliminating reliance on soil—which reduces soil erosion—and preventing nutrient loss through recycling. It is suitable for arid regions or areas with poor soil quality and can be implemented in urban settings to lower emissions from long supply chains (Okomoda et al., 2023).

Additionally, aquaponics has the potential to address sustainability challenges by reducing pesticide use, easing pressure on fish populations, and minimizing environmental pollution, while achieving productivity comparable to that of hydroponic systems (Graber and Junge, 2009). The fish produced have a low carbon footprint, offering a sustainable source of animal protein. Beyond sustainability, aquaponics offers ethical advantages by providing locally produced, nutritious food and creating employment opportunities in urban areas (Proksch et al., 2019). Prior reviews (Palm et al., 2018; Wirza and Nazir, 2021) indicate that successful aquaponics depends on careful management of several key factors, including system design, water and pH regulation, aeration and filtration techniques (Danaher et al., 2013), maintenance of optimal nutrient levels (Delaide et al., 2016, 2017), synergy between plant and fish species, microbial community dynamics, nitrogen levels, feed quantity and composition (Endut et al., 2016), pest control strategies, and effective marketing practices (Okomoda et al., 2023).

While knowledge of aquaponics components is continuously growing, much of it comes from small prototype systems tested under laboratory conditions (Colt et al., 2022). Several authors have pointed out the challenges of scaling up these systems (Goddek et al., 2015; Thorarinsdottir et al., 2015a; Kledal and Thorarinsdottir, 2018; Palm et al., 2018; Turnsek et al., 2020; Araújo et al., 2021), stressing that commercial-scale implementation will require increased efficiency, reduced resource use, and robust operations, management, and practices (Danish et al., 2021). Achieving sustainability across the technical, economic, institutional, social, environmental, and ecological pillars of aquaponics will require further research on system design and deployment (Schoor et al., 2023). Currently, commercial aquaponics is attracting considerable interest from both the scientific community and governments (Miličić et al., 2017; König et al., 2018; Greenfeld et al., 2019). The primary focus has been on commercial aquaponics, likely due to pressing challenges in food production, especially in urban regions and developing countries (Wu et al., 2019; Turnsek et al., 2020).

The recent integration of artificial intelligence (AI) and machine learning (ML) has transformed food production and the entire supply chain. It enables advanced monitoring, simulation, and automation by leveraging data from sensors, weather stations, and other technologies to support better decision-making regarding food yield, quality, spoilage, and safety. This approach encourages sustainable farming and resource conservation (Coronado-Apodaca et al., 2023; Karanth et al., 2023) and improves food security by forecasting risks associated with pathogens and environmental events. These technologies are expected to underpin future food systems, fostering innovative agricultural models such as vertical farming, digital farming, the bioeconomy, circular farming, and aquaponics (De Clerq et al., 2018). Recent developments—such as Agriculture 5.0, mission-oriented systems, the multi-level perspective, and citizen-consumer strategies (Klerkx and Rose, 2020)—mark a step forward from Agriculture 4.0. These advancements reflect a shift toward advanced, high-tech agriculture. For ‘Aquaponics 5.0’ or ‘Smart Aquaponics,’ expanding production will be essential.

Aquaponics relies on three interdependent components: aquatic organisms, bacteria, and plants. Achieving operational functionality and efficiency requires balancing and integrating multiple disciplines, including agriculture, aquaculture, microbiology, horticulture, chemistry, mechanics, and mechatronics (Ahmed and Turchini, 2021; Gillani et al., 2022). Industry 5.0 technologies offer opportunities to improve aquaponic systems through continuous monitoring of water quality, pH, air humidity, water and atmospheric temperatures, dissolved oxygen levels, and luminance (Reyes-Yanes et al., 2020a, b). Although limited in number, commercial-scale facilities incorporating modern technologies, including automatic control, improved system balance, and health and safety measures, can now be found worldwide (Thorarinsdottir et al., 2015b).

The literature contains numerous reviews describing the implementation of technology in aquaponics. Reyes-Yanes et al. (2020b) detailed the use of smart systems and the Internet of Things (IoT) in aquaponics, emphasizing automation and the shift from traditional to precision farming. The review covers key parameters monitored in aquaponics and discusses the IoT technologies and smart systems used to monitor and control these automated processes. While Chandramenon et al. (2024b) focused specifically on smart technologies for water quality analysis, monitoring, and maintenance, Channa et al. (2024) and Zamnuri et al. (2024) analyzed the integration of IoT in small-scale aquaponics, focusing on how this technology can improve efficiency and profitability, along with the challenges and opportunities. Flores-Iwasaki et al. (2025) provided an overview of aquaculture and analyzed the use of IoT sensors in RAS, biofloc technology (BFT), and aquaponics, with a focus on water quality monitoring. In contrast, Dennison et al. (2025) described the implementation of robotics and other technologies in hydroponics and aquaponics, highlighting how these technologies can boost productivity, optimize resource use, and reduce labor dependence.

Previous reviews provide an overview of technology implementation and the opportunities that new technologies offer to improve the efficiency of aquaponics. However, several challenges remain unaddressed, especially in scaling up aquaponics. To address these challenges, the present review divides the analysis into two parts. The first identifies the challenges facing aquaponics and categorizes them into five areas: 1) infrastructure and mechanics, 2) system knowledge, 3) market dynamics and consumer preferences, 4) culture and norms, and 5) legal frameworks and policies. The second explores the technologies developed and applied to address these challenges, with the goal of developing a more sophisticated theoretical framework for expanding aquaponics. It presents data on existing technological applications and highlights areas that require further enhancement. This framework facilitates discussion of how technology and its implementation can help scale aquaponic systems and summarizes possible improvements to their use.

2 Review methodology

2.1 Dataset extraction and preparation

The data analysis process was divided into two distinct phases, each guided by a review protocol that adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. In the first phase, the main objective was to identify and compile a comprehensive list of keywords to address the first research question, thereby establishing a foundational framework for the research. This framework was used to categorize the challenges identified during Phase 1.

The dataset was obtained from three databases, namely, Scopus, ScienceDirect, and Google Scholar, using a sequential search methodology. The methodology comprised four stages: identification, screening, selection, and inclusion. The identification stage included a rigorous search strategy implemented using specific keywords and combinations, such as: TITLE (“aquaponics”), TITLE-ABS-KEY AND “Upscaling” OR “challenges” OR “barriers” OR “limitations” OR “problems” OR “improvement”. The combinations were included to broaden the coverage of existing research on this topic. Papers were included based on their alignment with the themes of our research. The eligibility criteria for inclusion were: 1) fully published articles, 2) English-language publications, 3) quality of the complete text, and 4) relevance to the research topic. Redundant or unrelated articles, articles of insufficient quality, and articles not relevant to the topic were excluded from the review process. The systematic search was exhaustive and covered articles available up to July 2025. Figure 1 presents an overview of the search results. Of the 122 documents initially identified, 36 were ultimately included after manual selection based on quality and relevance.

Phase 2 focused on analyzing information regarding technology and its application in aquaponic systems. We used the same strategy and standards as in Phase 1, replacing the search terms with TITLE (“aquaponics”) AND “Technology” OR “Artificial intelligence” OR “Smart.” The extensive search covered articles available up to December 2025. Of the 389 documents initially identified, 135 were ultimately selected based on their quality and relevance to the review. Figure 2 summarizes the processes of identification, screening, selection, and inclusion.

3 Results and discussion

3.1 Infrastructure and mechanical challenges

The infrastructure for aquaponics includes all the materials required for the system to achieve its objectives. Our analysis identified 11 relevant topics, including system structure and design, capital and operating costs, energy source and consumption, seasonal weather variations, artificial lighting, maintenance costs, aeration costs, heating costs, filtration technology, noise issues, and security systems and alarms (Figure 3a; Table 1).

Table 1. Infrastructure and mechanical challenges to upscaling aquaponics: 11 key topics.

Infrastructure is the foundation of any aquaponic system and must be aligned with its production goals. Aquaponic systems face inherent challenges related to the weather and natural conditions of their location. For example, in tropical and warm regions, shading and cooling systems may be required to protect fish and plants from the sun and heat. Conversely, in colder climates, greenhouses with heating and lighting systems are needed, particularly during winter (Araújo et al., 2021). This underscores the significance of an aquaponic system’s location, making it challenging to generalize findings across different systems.

Several studies have shown that infrastructure represents the highest monetary cost and the greatest environmental impact of an aquaponic system. Forchino et al. (2018); Chen et al. (2020); Ghamkhar et al. (2020), and Baganz et al. (2022) found that constructing facilities for vegetable production accounts for 80% of the initial cost of establishing an aquaponic system, with facility construction being the highest cost at 49% of the total investment cost. Developing smart greenhouses and establishing the requirements for automated services require multidisciplinary collaboration involving experts such as technicians, city planners, biologists, economists, engineers, environmental scientists, and information and communications technology (ICT) technicians (Li et al., 2018a; Ferrández-Pastor et al., 2019). Increased plant growth, productivity, and quality drive the popularity of intelligent greenhouses in urban areas (Gupta and Kumar, 2021). The success of aquaponics depends on collaboration among key stakeholders, extending beyond natural scientists and engineers to include designers and architects, social scientists, and health and nutrition experts, who can help explore how aquaponic products could be incorporated into healthy and sustainable diets (Junge et al., 2017). The sustainability of commercial systems relies heavily on local adaptations and preconditions (Palm et al., 2018).

3.1.1 Technology for infrastructure and mechanics

The structure and design of aquaponic systems have evolved from simple covered greenhouse structures to high-tech controlled-environment agriculture (CEA) facilities that optimize the productivity of both plants and human labor (Shamshiri et al., 2018). CEA offers significant benefits, including reduced water use (90%–95%) and land use (1 indoor acre per 5–7 outdoor acres), continuous year-round growing capability, location flexibility (e.g., including urban centers), and reduced reliance on heavy machinery, pesticides, herbicides, and fertilizers (Cuce et al., 2016; Benke and Tomkins, 2017). Internet technologies have enabled smart greenhouses, where automated environmental control supports data processing and task execution through AI-based algorithms that predict and classify system processes (Ferrández-Pastor et al., 2019). Similarly, González et al. (2022) developed a monitoring digital twin (mDT) for CEA facilities to track subsystems such as crops, soil, climate, microclimate, water, energy, irrigation, and maintenance using the 4C model (connect, collect, control, change) proposed by Orange NXT. The system integrates services, data collection, storage, interaction, and scalability. Digital twin (DT) technology can enhance CEA productivity and sustainability by creating a virtual replica of real-world systems throughout their life cycle, enabling monitoring, analysis, and simulation of current and future states through data integration, AI, and ML.

In an aquaponic system, five primary factors contribute to electrical energy consumption: water heaters, air blowers, box fans, pumps, and lights, with usage varying by component. Channa et al. (2025) employed a dynamic control algorithm to adjust water temperature based on a solar forecast. This method reduces reliance on grid power during periods of solar intermittency and advances the integration of renewable energy. Simulations indicate that this approach can achieve a 26.9% annual reduction in energy consumption in an aquaponic system compared with conventional methods, thereby addressing their limitations. Sadek et al. (2024) developed an IoT-based smart greenhouse for hydroponics and aeroponics that automates climate control according to plant type and season. It uses sensors to monitor temperature, humidity, light intensity, and total dissolved solids, with automated data handling and remote access through a graphical interface. The system maintains optimal growing conditions with minimal user input.

Several studies provide evidence for the practical application of innovative solar-powered IoT architectures. Paul et al. (2022) proposed a sustainable system powered by solar energy with IoT and data analytics capabilities. Similarly, Naser et al. (2019) demonstrated the practical application of IoT in aquaponics through a solar-powered system that monitors parameters and ammonia levels. Khaoula et al. (2021) demonstrated the practical application of innovative IoT architectures powered by solar energy. This architecture highlights the significant contributions of IoT and AI to automation, monitoring, and control in aquaponic systems, emphasizing interoperability, security, scalability, and self-powering. Solar-powered IoT architectures offer solutions for modern aquaponics. By maximizing the use of sensors for water level, temperature, electrical conductivity, CO₂, and total ammonia nitrogen (TAN), together with actuators (water pumps), these systems enhance the efficiency and effectiveness of aquaponics operations, opening new possibilities for overcoming the challenges associated with commercial aquaponics. Baiyin et al. (2020) reported that a photovoltaic system could meet the power demand of aquaponics at a low net present cost (the total cost the system incurs over its lifetime). Sadek et al. (2024) developed an IoT-based system for indoor hydroponics and aeroponics, achieving more than 80% reductions in energy and water use, doubling production per area, and reducing time to yield. An analysis of solar energy and IoT use in aquaponics suggests that flexible, adaptable, and system-specific solutions are becoming increasingly feasible. Ondruška et al. (2022) improved resource use through monitoring and using a graph-theoretical approach that integrated an electrical heat pump, a biogas system, and a black soldier fly facility for fish feed. They also reported that reflective foils increased light efficiency in growth beds by 16.88%.

Lighting plays a vital role in aquaponic systems by providing plants with the light required for photosynthesis. In large-scale setups, artificial lighting becomes essential to provide the required photosynthetically active radiation (PAR) (Vitoshkin and Haslavsky, 2020). Plant photoreceptors capture this radiation and influence growth, morphology, and photosynthetic performance (Chen et al., 2020). Artificial lighting accounts for an estimated 65% of the energy used in indoor aquaponics. Several artificial lighting sources have been deployed, including high-intensity discharge (HID), induction (IND), fluorescent (FLO), and light-emitting diode (LED) lighting. Light-emitting diodes (LEDs) have gained popularity in horticultural applications because of their cost-effectiveness, durability, and low thermal energy output (Gillani et al., 2022). Oliver et al. (2018) found that LED lighting produced significantly higher plant weights and production per unit area for Swiss chard and kale, with an energy efficiency of up to 32.3 g/m2/kWh. Gillani et al. (2022) further noted that LED light treatments could offer approximately 75% energy savings compared with traditional lighting. Other advantages include improved plant growth, higher net photosynthetic rates, higher vitamin C content, lower nitrate content, and reduced oxalate accumulation (Gao et al., 2020), which may be attributed to the diverse spectrum of colors emitted by LEDs (Memiş et al., 2023).

In colder climates, the primary driver of electricity consumption is in-tank water heaters (Love et al., 2015). Environmental conditions can be regulated by implementing a controlled environment to monitor key variables, including critical temperature, humidity, solar radiation, rainfall, wind speed, and wind direction (Debroy et al., 2024). Another high cost is maintenance, as failures in any component can disrupt production and pose risks (Petrea et al., 2016). Issues can arise at any time, and using sensors to detect faults or anomalies can mitigate associated disruptions and risks, enhancing system efficiency (Taha et al., 2024). An emergency call system that monitors power outages and indoor temperatures can also be effective. Alarm and security systems are fundamental components of an aquaponic system (Araújo et al., 2021). Some growers stock spare consumables, such as fan belts, motors, and heaters, to address potential equipment malfunctions. It is therefore crucial to incorporate security into system design, especially as higher-value equipment is acquired and other costs increase. Security cameras with direct mobile phone connections provide enhanced surveillance capabilities. Anand and Sharma (2022) described the security services required, including sensors, smart devices, and embedded devices, and the need to protect them from IoT-related security risks, including data theft and unauthorized access. Noise-related issues arise in aquaponic systems, particularly where high-horsepower machinery is used. These issues have been reported primarily in urban and residential environments (Zhang et al., 2022). As the preceding discussion shows, integrating technology into infrastructure offers numerous benefits across various domains.

Among the 11 challenges identified in this area, technology has been applied primarily in high-tech greenhouses. Core applications include IoT for sensing and actuation, AI for prediction, ML for anomaly detection, and DT for simulating and optimizing farm performance. Other important applications include managing energy consumption, lighting, and alarm and security systems. Ezzahoui et al. (2021) compared technologies in hydroponics and aquaponics and concluded that, in aquaponics, technology should prioritize safety, reduce energy consumption, and provide comprehensive information on plant and animal health. However, further development is still needed to address ventilation, aeration, heating, filtration, and noise-mitigation costs. Smart infrastructure offers considerable potential for aquaponics, but its implementation will require cross-disciplinary collaboration and expertise. Key barriers include high initial costs, limited technical expertise, specialized infrastructure, maintenance requirements, and unreliable power and internet access in rural or developing areas. Nevertheless, important technologies, including IoT, CEA, mDT, and AI (Table 1), are already being implemented to address these challenges. Advances in infrastructure can enhance system resilience, manageability, scalability, efficiency, and long-term adaptability.

3.2 System knowledge challenges

Aquaponics is a complex system, and scaling it successfully requires a strong understanding of its components and how they interact. The analysis identified 16 key system knowledge areas: system design, system knowledge, water quality and control, fish culture, feeds, hydroponic systems, plant culture, microorganisms, nitrifying bacteria, nitrogen utilization, nutrient management, organic residuals, pests and diseases, data evaluation, training, and environmental impacts (Figure 3b; Table 2). When analyzing these challenges, it is essential to utilize advanced technologies and a variety of strategies to enhance system integration and knowledge sharing.

Table 2. Sixteen key areas related to system knowledge challenges, covering their general descriptions, the technologies used, and barriers to adoption.

The complexity of aquaponics presents significant knowledge challenges because, unlike traditional crop specialization, it demands a comprehensive understanding of the interactions among animals, plants, and microorganisms, together with their sensitivities (Estim et al., 2019; Greenfeld et al., 2020a). Incorporating technology into aquaponic systems can address many of these challenges by enabling the collection, transmission, and processing of data to support control systems.

3.2.1 Technology to support aquaponic system knowledge

Recent projects focus on enhancing component integration in aquaponics by utilizing system-wide synergies. For example, Suciu et al. (2022) introduced the Aquaculture Digitalization Project (ADO), a low-cost IoT solution for small- and medium-sized aquaculture producers with limited technical expertise and funding. Using open-source frameworks and standardized technologies, ADO reduces hardware and software costs while improving interconnectivity and system availability. At a cost of less than €600 per device, it provides data acquisition, storage, and visualization tools that support system management. Fasciolo et al. (2023) developed an aeroponic system using IoT and AI in three phases: 1) analyzing how inputs and system structure affect plant growth; 2) testing these relationships to develop growth- and health-monitoring models; and 3) applying demand-driven planning for just-in-time resource use. A key aim of integrating technology into aquaponics is to reduce malfunctions, improve functionality and productivity, and decrease the time and labor required for system management. Consistent with this objective, Goda et al. (2025) found that smart, sustainable, integrated multitrophic aquaponic systems (IMTA-FRS), particularly AI-enabled and solar-powered models, outperformed conventional systems economically, achieving higher cash inflows, net income, and return on revenue. They also remained resilient under rising-cost scenarios, underscoring their sustainability.

Innovative aquaponics management methods now use real-time computer vision to monitor fish behavior, plant growth, and water quality. Malik et al. (2025) combined multispectral imaging with deep learning to detect early signs of fish stress with 98.3% accuracy and nutrient deficiencies with 95.1% accuracy, representing a 22% improvement over sensor-only systems. Chandramenon et al. (2024b) used IoT and ML to determine the optimal freshwater replenishment rate in a 100 L aquaponic system, finding that replacing 19% of the water maintained optimal conditions. Their related work also demonstrated that combining vermiponics with IoT-based replenishment monitoring can enhance productivity, highlighting the value of integrating sustainable approaches with technology (Chandramenon et al., 2024b). Xue and Noor (2025) further improved system functionality using fuzzy logic and a convolutional neural network (CNN). Together, these studies demonstrate that technology can help scale aquaponic systems by improving sustainability, efficiency, and control, particularly in urban settings where effective wastewater management and waste reduction are essential.

Optimizing resources and tailoring management protocols to specific crops are essential for improving plant yield and quality. For example, Kyaw and Ng (2017) developed a smart aquaponics prototype for spinach and tilapia comprising seven modules: data acquisition, alerts, system correction, central processing, web and mobile applications, and cloud storage. The system autonomously manages water quality, light intensity, and fish feeding, providing early warnings and correcting abnormalities without human intervention. Similarly, Abbasi et al. (2022) introduced AquaONT, which gathers and shares information across multiple system domains, including disease management. Despite these advances, aquaponics still faces practical challenges, including inefficient nitrogen utilization, high aeration costs, noise issues, and unpredictable water quality.

3.2.1.1 Water quality, fish culture, and parameter control

Maintaining fish health and water quality in aquaponics requires continuous monitoring of several parameters (Mandal and Ghosh, 2024). Predicting complex conditions remains difficult because it depends on integrating multidimensional data. Automation can improve operational efficiency, reduce human intervention, and help maintain stable ecosystem conditions (Dennison et al., 2025). Because aquaponic systems vary widely, researchers have developed a range of models to improve prediction and control. For example, Ren et al. (2018); Haryanto et al. (2019); Naser et al. (2019), and Ezzahoui et al. (2021) developed smart aquaponic systems that use IoT to monitor and control pH, water level, temperature, and oxygen, enabling remote water-quality management and reducing labor demands. Taufiqurrahman et al. (2020) further reduced risk by developing an IoT-based water temperature control system that combines adaptive boosting (AdaBoost) with decision tree regression (DTR), improving responses to extreme temperature fluctuations and supporting fish health.

Numerous researchers are actively developing and implementing technologies to address challenges in aquaponics, particularly those related to water quality, one of the principal barriers to scaling up aquaponics. Kok et al. (2024) conducted a series of experiments to improve water-quality management using proportional-integral-derivative (PID) control, finding that it increased performance and reduced errors in SIMULINK. Similarly, Shaji et al. (2024) implemented automation and real-time water quality monitoring in a small-scale prototype, whereas Nor and Puteh (2024) and Hidayat and Rochman (2024) integrated IoT to enhance system functionality. Furthermore, Sundararajan et al. (2025) demonstrated the implementation of an IoT-based water-quality prediction model in an aquaponic system, enhancing control through multiscale feature fusion using a convolutional autoencoder and gated recurrent unit (GRU) networks. This approach provides greater precision and effectiveness than other models. Another advance is the development of an Android application for monitoring aquaponic systems (Frendiana and Pangesti, 2025). Mahmoud et al. (2024) implemented IoT to monitor and control an aquaponic system and deployed a DT to model the physical system. This combination improved data collection, supporting plant growth, fish health monitoring, crop production, and nutrient management. The authors also reported that simplifying system operation and monitoring improved economic returns and reduced labor costs by approximately 70%.

Another key challenge in aquaponics is understanding animal behavior, and researchers are developing technologies to address this issue. Vargas Vaca et al. (2022) created a dynamic RAS simulator that performs flexible, automated simulations based on tank volume. Chiu et al. (2022) designed an IoT-based intelligent system for California Bass that uses sensors and AI-driven deep learning to optimize fish growth, improve survival, and reduce feed waste. Debroy and Seban (2022) developed two models for estimating fish biomass in aquaponics—an artificial neural network (ANN) and a hybrid adaptive neuro-fuzzy inference system (ANFIS). The ANFIS model achieved higher prediction accuracy and provided a simple, cost-effective tool for forecasting tomato fruit growth, helping farmers manage fish growth and better align supply with demand. Islam et al. (2023) implemented a real-time IoT monitoring system across multiple ponds to assess the suitability of the ponds for 11 fish species, providing continuous insights into fish tank conditions.

Combining multiple technologies can address several aquaponics challenges. For example, Ubina et al. (2023) developed an artificial intelligence of things (AIoT) infrastructure that integrates IoT, cloud technology, and AI to optimize fish feeding, culture, and welfare. The system uses smart sensors and actuators in feeders and sorters to enable real-time, remote monitoring through the cloud. It includes four DT services: automated feeding; metric estimation of fish count, size, and weight; environmental monitoring of water conditions, net integrity, and algae growth; and health monitoring of vitality, mortality, and disease. These AI-enabled services support optimization, prediction, and analysis to improve profitability and production efficiency. Accessible through web and mobile devices, the system supports intelligent aquaculture management. Although still in its early stages, the authors propose adding drones and additional sensors to improve data collection and reduce errors. Similarly, Liu et al. (2023) advanced the traditional time-series model for RAS by developing a multi-graph fusion network (GraphTS) that integrates multi-sensor spatiotemporal data to improve monitoring and trend prediction in aquaculture production. Integration of such technology helps improve system management. For example, Lee and Wang (2020) developed a cloud-based (IoT) system for monitoring aquaponic systems, focusing on fish metabolism and activity. Their method measures critical parameters, such as water temperature, depth, dissolved oxygen, and fish activity. Infrared sensors track fish movement, helping calculate metabolic rates and detect abnormalities. The data are transmitted to a cloud platform to support real-time monitoring and analysis, improving fish health management and overall system performance. Khandakar et al. (2024) implemented an ML model to predict the length and weight of fish species by analyzing environmental parameters, including pH, ammonia, and nitrate levels, and integrating local interpretable model-agnostic explanations (LIME) to enhance model transparency. Other approaches have also been developed for fish monitoring. For example, the hardware application for real-time aquaponic monitoring (N-AquaRAM) trains a deep neural network to estimate fish size in real time and incorporates a deep-learning accelerator capable of classifying 40 million fish samples per second (Siddique et al., 2025). This development illustrates the rapid pace of technological innovation and its potential for addressing the different challenges associated with controlling and monitoring aquaponic systems. To monitor fish welfare, Fandiño Pelayo et al. (2025) integrated low-cost digital sensors to measure physicochemical variables—pH, dissolved oxygen, and temperature—and used these as inputs for real-time classification of fish health status, including supervising the ML models. Among these models, the random forest (RF) model yielded the highest classification accuracy (99%).

Aquaponics can benefit greatly from technological advances in aquaculture. AI tools, including IoT, ML, cameras, and algorithms, are being used to reduce human intervention, increase productivity, and improve the monitoring of fish health, feed optimization, and water resources (Ashraf Rather et al., 2024; Føre et al., 2024). Wan et al. (2022) described an IoT-based aquaponics monitoring system designed to optimize the fish-to-plant ratio through a miniaturized, modular, low-cost design. It includes a 32-bit microcontroller with 16 data-acquisition modules, a Raspberry Pi for image processing and edge computing, and Ali Cloud storage, with data displayed and controlled through a WeChat Mini Program. The system showed no packet loss within 90 m and maintained a 5% error rate for environmental parameters, making it suitable for small-scale aquaponics. These advances enable more precise environmental control, improved resource use, and more efficient fish and plant growth while reducing labor requirements. Although automated management is increasingly feasible (Debroy et al., 2025), challenges remain in data collection, standardization, model accuracy, interpretability, and integration with existing systems. Nevertheless, emerging technologies continue to improve the management, monitoring, productivity, and sustainability of aquaponic systems.

3.2.1.2 Hydroponic system and plant culture

The nutrient film technique (NFT) system is highly efficient in large-scale commercial operations, particularly for leafy vegetables, due to its ease of use and low water requirements (Thorarinsdottir et al., 2015b). However, plant production in aquaponic systems can still be improved. Various technological innovations have been introduced to enhance these systems. For example, Concepcion et al. (2022) utilized spectro-morphological data and ML to accurately predict moisture content in aquaponic plants, revealing how environmental factors influence plant growth. Similarly, Strand et al. (2023) developed a cost-effective sensor strip capable of measuring critical parameters, including electrical conductivity, temperature, and pH. In addition to this proposal, Idoje et al. (2023) used ML algorithms to evaluate the efficiency of various hydroponic systems. To determine the most effective algorithm for predicting optimal plant growth, they used independent variables, including days after transplanting, temperature, water consumption, number of leaves, and nutrient concentrations of N, P, K, Ca, Mg, Mn, S, and Na. The results of this study can help guide the selection of appropriate hydroponic systems for food production based on location-specific climatic parameters. Concepcion et al. (2020) developed an efficient vision-based approach using ML, particularly Quadratic support vector machine (QSVM), to monitor and classify lettuce growth stages (e.g., vegetative and head development) and detect harvest time, with an accuracy of up to 88.33%. The model uses color-based superpixels combined with a multifold watershed transformation for segmentation. This method provides an effective tool for plant phenotyping and the optimization of management practices in aquaponic systems. Similarly, Tobias et al. (2020) proposed a hybrid tree-fuzzy logic model for accurately predicting lettuce growth stages, with the most reliable predictions observed during the head development stage. The system effectively identifies optimal maturity and harvest times, demonstrating high accuracy and low error rates. Abbasi et al. (2023a, b) described an automated system for monitoring plant morphology and improving crop spacing using a cloud-based application. The system extracts relevant information on crop attributes and optimal plant spacing from the ontology and compares these data with the results generated by the final model to recommend further actions. Further development of these technologies may help address additional challenges. For example, Concepcion et al. (2023) developed a novel vegetation index (vODGIabc) to correct lighting issues and improve crop growth estimation. Linear solid relationships were found using vODGIabc to estimate fresh weight, height, number of spanning leaves, leaf area index, and growth stage of lettuce crops. This low-cost approach to developing a greenness index for estimating biophysical signatures proved more accurate than the previously established triangular greenness index, which used a red-green-blue smartphone camera.

Lauguico et al. (2020a, b) used ML and machine vision to classify lettuce growth stages and improve the performance of smart aquaponics, underscoring the need for intensive monitoring, control, and automation. Similarly, Reyes-Yanes et al. (2020b, 2022) demonstrated that image processing and deep learning can support plant quality control, crop size estimation, and DT integration. Yang et al. (2023) found that support vector machines (SVMs) can accurately detect yellow and rotten leaves in hydroponic lettuce, achieving accuracies of 98.33% and 97.91%, respectively, and offering strong potential for robotic sorting and automated quality control. Concepcion et al. (2022) predicted primary macronutrient concentrations (NPK) using aquaphotomics, computational intelligence, and sensors measuring temperature, pH, and electrical conductivity, thereby reducing sensor deployment and energy consumption by 50%. The approach could also be extended to secondary macronutrients and micronutrients. Finally, Ondruška et al. (2022) used non-destructive image processing to efficiently evaluate crop growth rates. Monitoring plant nutritional status through indicators such as color, shape, and overall appearance is essential. Collectively, these technological advances improve the precision, efficiency, and sustainability of aquaponic systems, making commercial-scale operations more viable and economically successful.

3.2.1.3 Nutrient management and organic residual solids

Nutrient management and solid waste handling are major sources of labor and time requirements in aquaponics, particularly in semi-commercial and commercial systems. Although nutrient regulation has been widely studied, the majority of research has focused on small-scale systems, with comparatively little attention given to commercial applications (Goddek et al., 2015; Dhal et al., 2022b). Key challenges in intelligent nutrient regulation include limited data and difficulty selecting relevant features from small datasets (Dhal et al., 2022a). To address this, Dhal et al. (2022c) used 211 observations and 12 nutrient predictors from three aquaponic farms in southeast Texas. After generating synthetic data and applying dimensionality reduction, they identified calcium and ammonium as the key variables and regulated them using a closed-loop IoT sensing-and-actuation system. Their approach provides a flexible model that could be adapted to other aquaponics settings with suitable modifications. Taha et al. (2022b) also developed ML models to estimate NPK content in aquaponically grown lettuce. Using a FieldSpec4 Pro FR portable spectroradiometer to measure leaf reflectance spectra, the study included 128 lettuce seedlings subjected to various NPK treatments. Real-time sensing of nitrogenous compounds (NH₃, NO₂^-, and NO₃^-) enables immediate intervention when biological filters underperform (Channa et al., 2024). Predictive ML models can forecast these levels in advance, ensuring that toxic byproducts do not escape into the environment. This approach enables automatic nutrient estimation, advancing aquaponics toward precision agriculture. Various models are involved in optimizing, regulating, and managing nutrient levels in aquaponic systems. However, further research on nutrient management is needed, particularly at a commercial scale, where nutrient flux is critical to production success.

Effective solids removal is essential for maintaining water quality, fish welfare, and nutrient availability in coupled and decoupled aquaponic systems (Goddek et al., 2019). Innovative technologies can improve waste reuse, but the most appropriate solids-removal method depends on system complexity. Small systems with limited water volumes can use passive, low-maintenance, cost-effective solutions, whereas larger, more intensive systems often require advanced or combined techniques to maintain water quality (Thorarinsdottir et al., 2015a). In aquaponics, fish waste is converted into plant nutrients through microbial processes (Bhattacharjee, 2025); however, only approximately 30% of aquaculture nutrients are converted into final products, leaving the rest as both a challenge and an opportunity (Chiquito-Contreras et al., 2022). Bhoir et al. (2020) developed an IoT-enabled compost monitoring system that uses humidity sensors and an integrated organic waste container to regulate compost moisture, reducing landfill waste and methane emissions. Efficient waste management, transformation, and reuse are critical for scaling up aquaponics and adapting it to urban environments. Urban formats, including home-, factory-, and building-based systems, demonstrate the versatility of aquaponics (Nair et al., 2025), while smart technologies, IoT, and AI are increasingly improving nutrient cycling and waste management, supporting successful urban implementation (Nair et al., 2025). This highlights the strong potential of technology to monitor and control waste production and transformation, improving system performance, water quality, species health, and overall production efficiency.

3.2.1.4 Infestations of pests, parasites, or diseases

As in traditional agriculture, crops grown in aquaponic systems are vulnerable to various diseases and biotic stresses throughout their growth cycles. Common concerns include plant pests, such as aphids and spider mites; microorganisms, including bacteria and fungi; fish parasites, including Monogenea and Cestoda; and various viruses (Goddek et al., 2015). Despite the importance of managing these issues, there is limited research on the prevalence and potential spread of pests and pathogens in aquaponic environments. Managing diseases, infestations, and parasites is particularly challenging in aquaponics, as solutions used in conventional agriculture cannot be applied to these integrated systems. Proactive monitoring and predictive technologies are therefore essential in aquaponics farming. Several specialized technological applications have been developed to address these challenges. For example, Wongchai et al. (2022) employed data categorization and deep-learning techniques to accurately predict plant diseases. Their model achieved 96% accuracy, 89% precision and specificity, a 75% F1 score, and an area under the curve (AUC) of 66%. Such predictive capability offers significant potential to enhance the sustainability and efficiency of both hydroponic and aquaponic systems. Similarly, Abbasi et al. (2023b) developed an automated diagnostic system for leafy greens in aquaponics, including lettuce, basil, spinach, and parsley. Using 2,640 images and transfer learning on a crop-specific dataset, the system employed a three-stage process: crop classification, health status assessment, and disease detection. This approach improves early diagnosis and treatment decisions, benefiting plant management in aquaponic systems. Barosa et al. (2019) developed a decision-tree-based framework for disease detection in aquaponic systems using image processing and IoT technology. Their system can detect diseases in various species, including eggplant, chili, citrus, and mandarin, and provides real-time feedback through a mobile application. The system features camera surveillance for live streaming and processes images to recognize leaves and detect disease. If a disease is detected, a report is automatically sent to the owner via the mobile application, enhancing plant health monitoring and control. This tool illustrates a practical approach to real-time disease management and decision support and demonstrates that technologies for detecting pests and diseases in aquaponic systems continue to evolve, with potential for further improvement and refinement. In the future, users will be trained in using such technology, enabling them to manage aquaponic systems more effectively and scale up their operations. Canning et al. (2022) introduced the bionic Internet of Things (b-IoT), which uses Aucuba japonica as a plant sensor to monitor environmental conditions through changes in surface liquid affinity. By combining organic sensing with conventional IoT and using contact-angle mapping to measure leaf properties, this hybrid approach shows promise for environmental monitoring, including applications related to climate change. Significant progress has been made in monitoring pests and parasites; however, further research is needed to improve precision and support implementation at a commercial scale.

3.2.1.5 Human factors—training

Tokunaga et al. (2015) found that labor costs represent 46% of total operating costs and 40% of total annual costs in aquaponic systems. This is higher than in other forms of aquaculture, highlighting the need for adequate labor resources in aquaponic management. To address these challenges, Wang et al. (2020) designed an aquaponic system with a computational intelligence system that not only helps students understand the technology but also develop proficiency in its application.

Slob et al. (2023) explored the use of a virtual reality-based DT for greenhouses, emphasizing human interaction within an immersive greenhouse DT environment. This approach facilitates understanding of technology adoption and its potential applications, reducing errors through realistic training experiences. It improves the proficiency of both new and experienced system operators, fostering a successful training model. In another study, Abbasi et al. (2021) introduced a knowledge-modeling approach that uses an ontology to automatically determine system characteristics based on crop selection. This approach helps practitioners visualize how the crop affects system design and aids decision-making regarding the layout of the production facility. Small IoT-based aquaponic prototypes are emerging as tools to promote students’ interest in aquaponics and its benefits, offering an innovative learning approach that combines practical, hands-on experiences with advanced digital educational tools to enhance the learning environment (Mohamad et al., 2025).

Training in technology management and implementation remains essential for aquaponics practitioners. Because systems require constant attention to prevent disease, manage water levels, and control pests, AI-driven IoT solutions can reduce routine labor and support more scalable production environments (Metin et al., 2023). Computational intelligence also offers practical value for managing complex systems, recognizing patterns, and modeling systems, helping engineers and designers better understand the requirements of aquaponic systems. Although technology has advanced resource-efficient and resilient aquaponic systems, challenges remain in fully understanding and managing their interacting components.

3.3 Challenges in market dynamics and consumer preferences

Within the context of market dynamics and consumer preferences, 20 critical topics related to aquaponics products were identified, including business management, investment costs, human resources and labor, logistics and distribution, marketing and sales services, risk mitigation, storage, market demand, price differentiation, clients and services, optimal product quality, novel product varieties, consumer decision-making, supply chain, labor requirements, packaging, public acceptance, market competition, interactions and intermediaries, and product placement (Figure 4a; Table 3). Xie and Rosentrater (2015) showed that economies of scale in aquaponic systems can reduce both production costs and environmental impacts as output increases. Developing market strategies and evaluating product demand, therefore, require careful consideration of the specific requirements of buyers, such as chefs, selected supermarkets, and niche consumer groups. As shown in Table 3, the challenges are varied, and addressing these obstacles is crucial for implementing technology that can reduce issues in this field. Ensuring consistent product quality is vital and relies on careful planning of staffing, cost management, distribution logistics, and timing (Engle, 2016). Additionally, the profitability of commercial aquaponics depends heavily on expertise in business, finance, and marketing.

Table 3. Twenty challenges related to market dynamics and consumer preferences were identified as barriers to upscaling aquaponics.

Selling to premium markets requires greater marketing investment. Raulier et al. (2023) found that commercial considerations are increasingly important across aquaponics projects. Palm et al. (2018) noted that semi-commercial aquaponics occupies a position between small- and large-scale operations and may serve both retail and wholesale markets. Scaling production, therefore, depends on a strong sales and marketing strategy and cultivating demand among consumers willing to pay a premium. Success also requires understanding the competitive landscape. For example, producers of aquaponically grown lettuce compete with major retailers, grocery stores, and local farmers’ markets, so they must clearly justify higher prices to consumers (Engle, 2016). Under Dutch market conditions, urban aquaponics can command premium prices (Stadler et al., 2017). Willingness to pay is strongly shaped by environmental awareness and perceptions of sustainability.

3.3.1 Technology for market dynamics and consumer preferences

A fair and inclusive supply chain design is essential for promoting equitable growth and market expansion in aquaponics. However, intermediaries often complicate operations, particularly at semi-commercial and commercial levels. Studies indicate that relatively few aquaponic ventures reach financial sustainability (Colt et al., 2022), with scaling challenges and limited legislative recognition creating additional obstacles. To address these issues, the development of aquaponics should involve all stakeholders—from researchers and policymakers to consumers—to ensure long-term viability and sectoral growth (Dos Santos, 2018). According to the latest information, blockchain is one proposed solution for improving product tracking, decision-making, and transparency in aquaponics. In the agri-food sector, it strengthens traceability, verifies quality and sustainability, and supports corporate responsibility goals (Corsini et al., 2023; Gupta and Shankar, 2024). It also enhances supply chain management by improving security, quality assurance, transparency, and scalability (Dal Mas et al., 2023). More broadly, blockchain can improve food safety, accountability, fraud prevention, and digitalization in agri-food operations (Feng et al., 2020). Its decentralized structure also supports smallholder farmers by enabling direct transactions, reducing intermediaries, and securing data through cryptography (Secinaro et al., 2022).

3.3.1.1 Human resource management and human capital

Narwane et al. (2022) analyzed IoT adoption in the Indian agricultural and food supply chain and identified 24 critical factors across technological, social, economic, and organizational domains. The study highlighted five key barriers to adoption: lack of interoperability, concerns about environmental sustainability, limited trust, security issues, and network challenges. These findings help identify priority areas for improving technology adoption, particularly among aquaponics farmers. Similarly, Greenfeld et al. (2019) hypothesized that larger system sizes, higher retail prices, and refined business strategies improve profitability in commercial aquaponics. These factors significantly influence the economic viability of commercial aquaponics globally. The recommended strategies include securing initial capital, providing business guidance, and establishing a supportive regulatory framework to facilitate the development of larger, more efficient systems that can command premium prices through organic certification. However, overcoming other commercial obstacles, such as education and marketing, is crucial. Improving education is essential for optimizing system operations, developing business plans, and providing skilled labor for the growing aquaponics industry (Cammies et al., 2021). Risk mitigation must be implemented systematically across all stages of aquaponic operations. Standardizing risk-reduction practices is essential for ensuring the safety and efficiency of production processes and personnel. A comprehensive approach should encompass identifying, assessing, and managing potential risks, thereby minimizing the likelihood of production losses and safeguarding those involved in the system. Integrating risk mitigation into operating procedures is essential for aquaponic systems to operate sustainably and safely.

Integrating various technologies significantly benefits the workforce and human capital. Although smart systems require a higher initial investment, they deliver better long-term economic outcomes through precise management. A major benefit is the automated monitoring and control of parameters such as pH, temperature, and feeding, which can reduce manual labor costs by approximately 70%, allowing workers to focus on higher-level management (Mahmoud et al., 2024; Dennison et al., 2025). For instance, P-graph optimization helps identify the most cost-effective process pathways, such as combining heat pumps and biogas systems, increasing annual net income by as much as ninefold. Additionally, developing ML models that detect patterns of mechanical wear in sensor data supports predictive maintenance of pumps and aerators, preventing costly failures and downtime. Another key contribution aligned with sustainability is AI-driven adaptive fertigation, which employs image processing to accurately assess plant nutrient requirements, reducing supplement costs by approximately 75% (Abbasi et al., 2021, 2023b; Ondruška et al., 2022; Chandramenon et al., 2024c). This eco-friendly technology helps address challenges faced by aquaponics, fosters new expertise and innovation, and enhances efficient and sustainable production.

3.3.1.2 Marketing, market demands, channels, and clients

Recent advances in ML, IoT, big data analytics, and cloud computing have transformed the agri-food sector by improving connectivity, reducing reliance on manual intervention, and supporting more efficient energy use. More broadly, information and communication technologies (ICT) help farmers increase productivity by providing data and decision support (Mapiye et al., 2023). However, in a rapidly changing environment, this alone is insufficient; greater system control and access to real-time data are also needed to enable better decision-making and optimize production. However, IoT faces challenges on multiple fronts, including technological issues such as decentralization, privacy, security, data governance, internet availability, interoperability, software and hardware complexity, and extensive data management (Reyes-Yanes et al., 2020b; Zamnuri et al., 2024). Social challenges include gaining societal and user acceptance, cultivating technical skills, and navigating relevant legislation. Organizational challenges include building trust, raising capital, achieving an adequate return on investment (ROI), and managing heterogeneity (Badia-Melis et al., 2018). To enhance the market reach and client engagement of aquaponics, technology must be leveraged across multiple areas, including market development, distribution channels, and customer relations.

Aquaponics is a sustainable production model that aligns with consumer demand for environmentally friendly food options (Kralik et al., 2022). However, its market potential depends on clearly communicating the benefits and distinctive features of aquaponic products (Short et al., 2017). Experimental studies indicate that both positive taste experiences and information about environmental benefits can increase consumers’ willingness to pay (Miličić et al., 2017; Macht et al., 2025). Consumer education is therefore essential for market growth, as effective communication about aquaponic production may help secure price premiums similar to those associated with organic foods (Macht et al., 2025).

3.3.1.3 Services

Raulier et al. (2023) examined the professional, technical, and business dimensions of aquaponics in Europe and found that 96% of entities sold products, 74% offered services, and 37% were involved in research and development. Their study also showed that market dynamics vary according to the type, size, and location of commercial aquaponic farms, while commercial strategies remain largely unstandardized. This points to clear opportunities for technological innovation, especially for improving user interfaces and producer–consumer interactions. Although technologies that connect producers and consumers are already available, their uptake remains limited. Social media can support product promotion, system visibility, and customer engagement; however, business management tools for monitoring inputs and outputs, managing risk, coordinating distribution, and controlling storage are still underused. Debroy et al. (2025) further noted that predictive analytics and evaluation methods remain underexplored, despite the potential of real-time monitoring to reduce resource use and improve sustainability. Overall, there is strong potential for technologies that inform, engage, and encourage consumers by highlighting the energy-, resource-, and space-efficiency benefits of aquaponics.

The aquaponics market is shaped by smart technologies and consumer education. Market dynamics and consumer preferences were among the key challenges identified, spanning 22 topics; however, relatively few studies address strategies or technologies to tackle them. Even so, existing digital tools could support these areas. Scaling aquaponics depends on sufficient demand for products and services, making distribution channels, customer service, and product availability critical. Digital marketing and consumer-engagement tools are especially important. Sharma et al. (2023) identified six influential technologies, ranging from the internet and mobile platforms to AI and mixed reality, all of which can shape consumer decision-making across age groups. Likewise, Greenfeld et al. (2020b) found that informing consumers about the benefits of aquaponic produce increased preference in Israel and Australia, underscoring the value of targeted education. Greenfeld et al. (2019) also highlighted the need to address growers’ concerns, consumer perceptions, and the economic value of environmental benefits, while Short et al. (2018) showed that willingness to pay for aquaponic and soil-grown lettuce was similar, although members of environmental groups bid slightly less for aquaponic lettuce. Together, these findings highlight the need for tailored communication strategies and technologies that respond to diverse consumer preferences and promote the sustainability benefits of aquaponics. Widespread internet access and social media offer strong marketing opportunities in both developed and developing countries, while eco-friendly packaging and improved logistics can strengthen supply chains and reduce labor costs.

3.4 Culture and norms challenges

Issues related to culture and norms in aquaponic systems center on two key topics: food traditions and insurance (Figure 4b; Table 4). In a recent survey, Raulier et al. (2023) identified 31 plant varieties and 3 fish species as the most widely cultivated worldwide. Aquaponic farm owners generally perceived that consumers prioritized products based on their being “local” and the ability to “know the origin of the product,” with 81.5% (n = 22) of respondents citing these factors as critical. The third most important factor, identified by 66.7% (n = 18) of respondents, was the availability of “fresh and seasonal products.”

Table 4. Description of the principal challenges in culture and norms.

Aquaponics offers clear advantages in areas affected by farmer–herder conflicts and in urban settings. Stuiver and O’hara (2021) outlined a 2050 urban food vision based on small-scale, hyperlocal initiatives that can reshape communities, cities, and regions. They emphasized a food economy rooted in natural resources, cultural diversity, and nature-based innovation, supported by community engagement, gradual transformation, and the scaling of existing initiatives. This vision aligns closely with urban aquaponics, which has strong growth potential. Urban aquaponics supports urban food production while balancing productivity and sustainability (Okomoda et al., 2023) and can be integrated into urban food hubs in response toamid urbanization and migration. Oladimeji et al. (2020) found that aquaponics outperformed conventional aquaculture in fish production, while pumpkin yields were 5- and 11-fold higher on irrigated and non-irrigated land, respectively. Braglia et al. (2022) also found that aquaponics increased beneficial compounds in crops such as parsley and basil, reinforcing its value as an innovative and sustainable food production method. Aquaponics can also diversify production, cultivating vegetables that are specific to different communities. For instance, Ho-Lastimosa et al. (2019) integrated Native Hawaiian traditions with aquaponic technology, while Beebe et al. (2020) found that backyard aquaponic systems increased access to fruits and vegetables, improved diets, and fostered family and community cohesion by reconnecting participants with Native Hawaiian values, suggesting that these systems can enhance food security.

Cultivating medicinal plants or vegetables specific to ethnic cuisines is a promising avenue for development, with specialized restaurants representing a potential market. Kralik et al. (2022) demonstrated that fish produced through aquaponics are nutritionally comparable to wild-caught fish and that consumer perceptions improve when consumers are informed about the environmental benefits of aquaponics. This suggests that, with effective communication strategies, aquaponic products can compete in the market. Consumer education and marketing play crucial roles in expanding the aquaponics market. A survey conducted in Melbourne, Australia, emphasized the importance of considering consumer perceptions and preferences (Awal and Bonnici, 2021).

Aquaponics can also strengthen social cohesion by rehabilitating abandoned urban spaces and addressing limited access to fresh food in cities (Tomlinson, 2015). For instance, the evolution of aquaponics could focus on producing essential vegetables or those integral to local dietary preferences. Technology could play a pivotal role in promoting, integrating, and understanding the needs of local communities during this process (Davies and Garrett, 2018). Food production increasingly interacts with many types of technology, including nature-based solutions, which offer significant potential to improve urban sustainability. Using such solutions, cities can alleviate resource and pollution pressures in peri-urban and rural areas while supporting increasingly dense populations (Li et al., 2014). Aquaponics is a model of closed-loop design and provides an opportunity to demonstrate a paradigm shift in technological innovation. These designs prioritize the reuse of water, nutrients, waste, and energy, establishing new standards for sustainable production. Within these frameworks, materials may be renewable, biodegradable, or even edible. Green infrastructure firms engaged in food production on structures such as green roofs, green walls, rain gardens, and green buildings exemplify the application of nature-based solutions (Štrbac et al., 2023).

Aquaponics offers numerous opportunities to integrate animal and plant production while meeting the respective input needs. However, securing insurance coverage for such multi-component systems is difficult. For instance, Bosma et al. (2017) noted that insurance costs are often excluded from operational calculations because of significant variability in insurance payments, and that not all farms opt for insurance. Furthermore, the insurance framework for aquaponic systems remains uncertain, primarily due to risks and concerns about their viability that vary by species and production level (Greenfeld et al., 2019). A key challenge is that insurance policies often require profit margins of over 12%, which exceeds the typical profit margin of aquaponic systems (7.36%) (Tokunaga et al., 2015). Improving access to insurance may involve standardizing processes and implementing risk management methods. Technology plays a vital role by enabling information sharing, demonstrating production capacity, and promoting systems via social media. Models that analyze metadata and optimal environmental conditions for different crops can provide reliable data to help insurers predict trends, evaluate risks, and develop insurance models tailored to aquaponic production system (Ghandar et al., 2021). Evidence shows that although interest in insurance for aquaponics is increasing, the current framework remains fragmented and cautious, reflecting the technology’s early stage of development, particularly in areas such as risk monitoring and control, which can help improve the situation (Blockchain, AI, ML, and DSS). Technology adoption faces several important barriers, including dietary habits, regional traditions, the high cost of certain food products such as premium products, limited access to insurance and initial capital, and the technical fragility of some aquaponic systems, especially in rural and peri-urban areas (Table 4).

3.5 Legal frameworks and policy challenges

Challenges related to legal frameworks and policies fall into four primary themes: legal conditions, regulations, certifications, and the political environment (Figure 4c; Table 5). Aquaponic systems face institutional unfamiliarity and legislative hurdles during establishment due to the integration of vegetable or herb farming with fish farming (Hoevenaars et al., 2018). This means that the institutional basis for aquaponics varies significantly worldwide.

Table 5. Challenges relating to legal frameworks and policies.

Cammies et al. (2021) examined the economic and legal challenges facing aquaponics in the EU, identifying three key areas for consideration: (1) making aquaponics eligible for the new system of Environmental Land Management grants, (2) enabling aquaponics to qualify for organic certification, and (3) clarifying and streamlining the aquaponics license application process. In line with the last paragraph, Fruscella et al. (2021) conducted a review of organic aquaponics and EU regulations, highlighting critical challenges, particularly in integrating aquaponics into the existing organic farming framework. According to Commission Regulation (EU) (2018/848), effective from January 2022, aquaponic produce is ineligible for organic certification because crops must be grown in soil. Aquaponics typically utilizes soilless, hydroponic systems. The dual nature of aquaponics, combining horticulture and aquaculture, further complicates its regulation, as these sectors are governed by different directorates within the European Commission. This division hinders the creation of a cohesive regulatory framework for aquaponics (Kledal et al., 2018; Cammies et al., 2021). Unlike the EU, countries such as the USA and Canada allow aquaponic products to be certified as organic, underscoring the need for clearer, science-based, and more integrated regulation. Technological innovation could help narrow this gap by supporting hybrid systems better suited to EU organic standards. Advances in aquaculture and integrated farm management may also ease compliance across regulatory bodies. In addition, blockchain can strengthen transparency and traceability, while big data can inform policy advocacy (van Hilten et al., 2020; Singh et al., 2024). Precision farming may further support organic standards, encourage innovation, and facilitate international certification, helping align aquaponics with global regulations (Reyes-Yanes et al., 2020b). Despite these regulatory barriers, the sector has grown steadily, as shown by the increasing number of farms, research studies, and commercial ventures worldwide (Basumatary et al., 2023; Verma et al., 2023). This trend suggests a promising future, particularly if regulatory reforms make scaling aquaponics more feasible worldwide.

4 Perspectives on the challenges to upscaling aquaponic systems

After analyzing the challenges and the technologies implemented to address them, it is essential to explore the perspectives and opportunities that aquaponics offers to maximize its benefits on a commercial scale. Concerning infrastructure, the combination of low-maintenance systems and high-durability materials, along with designs that enable high production and the creation of optimal conditions through components and sensors, will play a crucial role in reducing risks, enhancing safety and control, and adapting systems to diverse environmental contexts, both urban and rural. This is one of the most important trends. It can be expected that, in the near future, systems with more productive components will be systematized and synchronized. A vital element of these systems will be the capacity for users to access real-time information, a feature that will significantly enhance their efficiency and productivity. For example, infrastructure, noise generation, filtration, processes, and system security remain key areas of research, particularly in the current context of environmental change. This represents a significant field for exploration, innovation, and technology adaptation. Future infrastructure must be designed with vulnerabilities, environmental risks, and the adaptation and resilience of productive systems in mind. It is therefore important to analyze in detail the components required for infrastructure to overcome challenges in each region, including utilities and energy grids focused on renewable energy sources, systems to enhance automation and data management, long-term maintenance strategies, and infrastructure designed to withstand natural disasters. To achieve this, a significant range of technologies already exist: IoT, AI, ML, wireless sensor networks, big data, analytics, autonomous robot systems, ubiquitous cloud computing for sustainable intensification, drones, precision agriculture technologies coupled with robotics and sensors, blockchain, and nanotechnology (Davies and Garrett, 2018; De Clerq et al., 2018; Rose and Chilvers, 2018; Grieve et al., 2019; Klerkx et al., 2019; Rhayem et al., 2020; Vishnoi and Goel, 2024).

It is worth exploring in more detail how technology can improve system knowledge, for example, by automating and optimizing feeding schedules and monitoring protocols. ML algorithms can identify the most efficient feed formulation and feeding regimes, enhancing growth rates and reducing environmental impact (Mandal and Ghosh, 2024). For example, fish feed can account for up to 50% of operating costs. Computer vision systems, such as AquaVision and YOLO algorithms, track fish swimming patterns to detect hunger or leftover pellets (Reyes-Yanes et al., 2020a). This accurate detection prevents the accumulation of undegraded feed, which can cause toxic ammonia spikes and environmental pollution, thereby maintaining water quality and influencing fish behavior. Technology can even predict growth and help with stock management and harvest planning. A key challenge in aquaponics is maintaining nutrient balance. Technology is crucial for understanding, detecting, predicting, and controlling nutrients through real-time monitoring (nutrient levels, pH, dissolved oxygen, and temperature), enabling prompt decision-making and action to prevent future issues. The key technological components for nutrient management are sensors (IoT), which provide continuous, real-time data on critical parameters. Devices such as Raspberry Pi or Arduino process sensor data for remote monitoring. The implementation of AI also analyzes historical and real-time data to detect and predict nutrient deficiencies and identify early signs of fish and plant stress. Progress in nutrient management technology looks promising, as it reduces the time and effort required to manage raw materials while boosting the health, growth, and productivity of fish and plants (Yang and Kim, 2019). These technologies support the health of nitrifying bacteria, which are crucial for nutrient recycling. AI algorithms evaluate physicochemical parameters to recommend the appropriate microbial cultures, ensuring the continuous conversion of fish waste into nitrates that plants can absorb. Additionally, hybrid vision-based systems and ML can identify plants’ specific nutrient requirements based on their foliage shape. This enables precise supplementation with only the necessary nutrients (such as potassium or calcium), significantly reducing the cost of extra nutrients by roughly 75% (Concepcion et al., 2020; Dhal et al., 2022b). Additionally, they help reduce environmental impact by lowering the consumption of raw materials, water, and other resources. A further step toward this goal is the increasing significance of hybrid renewable energy systems that combine multiple sources to reduce intermittency. These systems, which incorporate solar, hydropower, biomass, and other energy sources, aim to deliver a stable and reliable power supply. Moreover, agrivoltaics—where photovoltaic panels are used alongside crop farming—is being adapted for aquaponics to improve land-use efficiency (Dewi et al., 2025). This important trend can be further advanced by integrating AI with biosensor innovations. Smart optical biosensors and devices are expected to play a vital role in predictive analytics for aquaponics, especially in areas where management relies heavily on human effort and resources. The goal is to facilitate predictive prevention by identifying stress signals and early pathogen indicators before problems, such as fish mortality or plant issues, arise. Moving forward, models trained on behavioral, physiological, and water chemistry data simultaneously are expected to become standard, aiding in enhancing productivity, efficiency, management, and innovation within scalable systems.

One area where technology can play a fundamental role in the further development, dissemination, and recognition of aquaponics relates to market and user preferences. A total of 20 challenges were identified under this heading, only some of which have been directly addressed through technology, such as monitoring preferences, decision support using DT, and digital tools for business management (Greenfeld et al., 2020b; Ghandar et al., 2021). There are many further areas relevant to aquaponics that have yet to be explored, such as risk mitigation through digital systems, analysis of distribution channels, and even detecting where aquaponic systems could be profitable. Transportation, storage, distribution, and delivery represent major costs in food production. AI is beginning to coordinate relevant activities and to support the introduction of new crops, considering the needs of both the producer and the product, while enabling the customer to be more involved in decision-making. Interaction and intermediaries influence the final price of a product, particularly in systems that are still becoming widely known, such as aquaponics. Competition and its management can benefit from AI. Technology can be used in the supply chain to manage labor requirements and even improve packaging. As mentioned earlier, AI can offer a range of advantages in forecasting and detection.

A database of problems to be solved would help establish the relevant algorithms and generate corrective actions. AI provides sophisticated tools that aquaponic system owners can use to analyze consumer trends, preferences, and options, thereby strengthening strategic decision-making processes, such as consumer trend analysis, predictive analytics for marketing to maximize profit, and data-driven system optimization, helping consumers obtain important information about products (Ogundipe et al., 2024). It even offers the opportunity to develop immersive systems for learning the functionality of aquaponic systems in 3D. Advanced digital tools provide the data-driven evidence needed to meet regulatory standards and fulfill consumer expectations for transparency. For instance, blockchain technology creates an immutable “farm-to-fork” record of a product’s entire lifecycle, which supports sustainability claims, prevents fraud, and boosts consumer confidence (Chun-Ting et al., 2020). Another way to improve aquaponics system management is through DT technology, which creates virtual models of physical farms to forecast environmental impacts and test interventions before implementation, thereby enhancing system resilience and ecological stability. Regarding sustainability metrics, IoT platforms facilitate continuous monitoring of vital indicators such as nutrient use efficiency (NUE) and water use efficiency (WUE), which are essential for standardizing sustainability reporting across the industry. AI-driven solutions have the power to transform customer service in the aquaponics industry. By leveraging natural language processing, computer vision, and recommendation systems, these solutions can personalize product interfaces and cater to diverse user preferences, enhancing user experience and usability. Furthermore, AI can be harnessed to optimize reliability, performance, and scalability, thereby reducing the risks associated with product failures and improving overall product quality. AI enables product managers to orchestrate data-driven marketing strategies and optimize distribution channels, maximizing market penetration and consumer engagement (Babatunde et al., 2024). Predictive analytics, targeted advertising, and dynamic pricing algorithms maximize product sales, ensuring a competitive edge in the market. AI can elevate aquaponics to another level, for example, by introducing e-commerce.

Understanding and adapting to evolving consumer behavior is critical to the long-term success of online businesses and will play a crucial role in the future development and scaling of aquaponics. This understanding and adaptation will also influence laws and policies: as the demand for and feasibility of aquaponics increase, they will promote the development of laws and regulations relevant to production processes in this field. AI is also important for improving the international landscape of certifications, policies, and rules in this context. Technology will be increasingly present across all production systems, and there are many areas yet to be explored in aquaponics. The complexity of these systems allows for different solutions and the development of new tools. The potential of smart aquaponics is only in its initial stages. When combined, these technologies offer not just solutions but adaptive, long-term solutions that can respond to diverse environmental contexts. Furthermore, generating innovation and investing in technological development create new possibilities for improving productive aquaponic systems. The use of technology in aquaponics is in its infancy, but as it continues to develop, it will become more widespread. The future of smart aquaponics is full of promise and excitement, and the field is ripe for innovation and growth.

5 Conclusion

Aquaponic systems span a broad spectrum of designs, sizes, and implementation methods. The use of technology in aquaponics will grow as it becomes cheaper and better understood. There are numerous areas for further research and development. The challenges to scaling aquaponics identified in this review have been categorized into five groups. The use of technology has been particularly successful in infrastructure, especially greenhouse automation, enabling control of environmental parameters such as light, humidity, and temperature. Automation has streamlined management using sensors to detect unfavorable conditions. However, research on residual filtration, aeration, and safety in aquaponic systems has been limited to date. It would therefore be worthwhile to explore the suitability of other existing technologies for these systems. Technology is already widely used to support scientific knowledge of fish and plant production management. However, there is a need for further development of microbiological analysis, particularly regarding nitrifying bacteria, human training, and environmental impacts.

The third theme focused on market dynamics and consumer preferences. While some issues under this heading may be less relevant to small, hobby, or experimental unitary systems, they are crucial for commercial aquaponics. Technology can enhance these processes by analyzing distribution areas, future markets, customer needs, delivery channels, risk, optimal production, and supply chains. Technology can also help to reduce production, sales, and distribution costs by connecting customers directly with companies, bypassing intermediaries.

This leads to the fourth theme, culture and norms. As cities become more cosmopolitan, specific needs arise, particularly in local food production. Aquaponics can significantly strengthen communities. However, aquaponics faces challenges in legal frameworks and policies: although widely regarded as an efficient and sustainable system, it is not officially recognized in most public policies, laws, or treaties. Ongoing efforts to promote aquaponics in urban settings and establish it as a viable commercial system could lead to its future inclusion in standards, laws, and regulations. Key steps involve developing specific certifications for aquaponic products to enhance consumer confidence and supporting environmental policies that acknowledge aquaponics as a sustainable practice.

Generative AI statement

The author(s) declared that generative AI was not used in the creation of this manuscript.

Any alternative text (alt text) provided alongside figures in this article has been generated by Frontiers with the support of artificial intelligence and reasonable efforts have been made to ensure accuracy, including review by the authors wherever possible. If you identify any issues, please contact us.

Publisher’s note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

Footnotes

Edited by: Aya S. Hussain, Purdue University, United States

Reviewed by: Kumaresan Marappan, Vels Institute of Science, Technology & Advanced Studies (VISTAS), India

Puteri Nurul Ma’rifah, Universitas Trunodjoyo Madura, Indonesia