Renewable Energy and Artificial Intelligence in Urban Agriculture: Pathfinding Smart and Sustainable Food Systems

By 2050, urban centers will house nearly 70% of the global population. Transitioning to localized food production via Urban Agriculture (UA) including vertical farms, plant factories, and rooftop greenhouses is critical to achieving food security and minimizing supply-chain emissions. However, intensive UA frameworks, particularly Controlled Environment Agriculture (CEA), are highly energy-dependent. Relying on traditional electrical grids shifts the environmental burden rather than solving it. The integration of localized renewable energy sources (such as agrivoltaics, wind micro-turbines, and biomass) offers a clean alternative, but introduces high volatility and system complexity. Artificial Intelligence (AI) serves as the critical enabler to bridge this gap. Advanced machine learning, predictive analytics, and autonomous control loops are required to orchestrate fluctuating renewable energy inputs in coordination with the energy demands of the dynamic social-ecological timetables of indoor crop production. This Research Topic (RT) focuses on studies of the development of AI such as computational intelligence, deep learning, advanced automation to optimize the energy-food nexus in UA. We seek to capture research on cutting-edge engineering solutions that transform urban CEA into self-sustaining, high-efficiency cognitive assets. The critical challenge this collection addresses is the unsustainable energy bottleneck of intensive urban agriculture, where transition to indoor vertical farming and controlled environments inadvertently shifts the environmental burden onto fossil-fuel-powered grids. While localized renewable energy sources offer a clean alternative, their inherent weather-dependent volatility clashes directly with the continuous and complex social-ecological energy needs of indoor crop production. Current systems lack the intelligent architecture to dynamically synchronize these two volatile systems without relying on traditional grid backups or oversized, cost-prohibitive battery storage. This Research Topic will answer how advanced computational intelligence, deep reinforcement learning, and edge-AI architectures can act as real-time orchestrators to maximize crop yield per kilowatt-hour under highly fluctuating renewable supplies. It will explore how physics-informed digital twins can co-optimize the thermodynamic interplay between urban building envelopes, microgrids, and crop microclimates, and determine the optimal deployment strategies for autonomous, renewable-powered agricultural robotics. This is the precise moment to tackle this integration due to three recent technological convergences: the maturity of Edge-AI chips capable of running complex machine learning models directly on localized farm infrastructure with low latency, the widespread adoption of multi-spectral IoT sensor networks providing high-granularity biological data, and recent breakthroughs in vision transformers and deep reinforcement learning that allow systems to predict and adapt to complex, non-linear environmental changes. By focusing explicitly on research directly at these data-driven, autonomous engineering approaches, this RT fits perfectly within the scope of advanced automation and computer science applied to sustainable cyber-physical systems consisting of Urban Agriculture (UA). The boundaries of this RT are centered at the intersection of artificial intelligence, localized renewable energy engineering, and urban agricultural systems, specifically focusing on data-driven, automated optimization of the energy-food nexus within UA systems. The scope explicitly excludes studies on traditional open-field farming, manual urban gardening, or renewable energy grid integration that lacks a direct, functional connection to urban food production systems. To ensure technological and academic rigor, we invite authors to address the following specific themes:• Development of deep reinforcement learning and predictive machine learning models to synchronize fluctuating localized renewable energy generation with the dynamic load requirements of indoor vertical farming.• Edge-AI architectures and intelligent microgrid control systems engineered for autonomous load balancing and localized energy storage optimization in controlled environment agriculture.• Deep learning models, vision transformers, and multi-spectral image analysis for real-time crop health diagnostics and automated anomaly detection aimed at minimizing HVAC and lighting energy waste.• Physics-informed neural networks and digital twin frameworks designed to simulate, predict, and co-optimize the coupled thermodynamic behaviors of urban building envelopes, microgrid infrastructure, and indoor crop microclimates.• Genetic algorithms and advanced computational modeling to optimize circular urban bio-systems, specifically maximizing the conversion rates of urban organic waste into stable biogas, electricity, and heat for city greenhouses.• Swarm intelligence, pathfinding algorithms, and control systems for autonomous agricultural robotics and unmanned aerial vehicles operating via renewable-powered micro-charging infrastructure.We welcome a diverse range of manuscript types to capture a comprehensive overview of this rapidly advancing field, including Original Research articles presenting novel algorithmic models or empirical engineering data, comprehensive Review articles that synthesize current literature and map future research trajectories, Systematic Reviews following rigorous reporting protocols, and concise Mini-Reviews targeting focused technical advancements. Additionally, we encourage the submission of Perspective pieces offering visionary insights into policy and engineering integration, Brief Research Reports detailing preliminary or high-impact pilot studies, and Data Report manuscripts that provide open-access, high-granularity datasets critical for training future machine learning models in smart urban agriculture. Topic editors: Dr. Binay Kumar Pandey, Dr. Digvijay Pandey Source: https://www.frontiersin.org/research-topics/82781/renewable-energy-and-artificial-intelligence-in-urban-agriculture-pathfinding-smart-and-sustainable-food-systems