Reliable and Intelligent Systems for Plant Monitoring

Plant science is undergoing rapid transformation through advances in next-generation sensing technologies and artificial intelligence, enabling continuous, multimodal, and high-resolution monitoring across controlled, greenhouse, and open-field conditions. Emerging technologies, including field-deployable sensors, biosensors, proximal and remote sensing, spectral and imaging systems, robotics, and high-throughput phenotyping platforms, are generating increasingly complex and heterogeneous data streams. In parallel, advances in artificial intelligence and smart sensing architectures are transforming these data into biologically meaningful information and predictive outputs. Together, these developments are driving a transition from standalone sensing devices toward integrated sensing ecosystems that combine multimodal acquisition, data processing, and intelligent modelling. As such systems move from proof-of-concept demonstrations toward continuous, operational plant monitoring, performance within a single dataset or experimental setting is no longer a sufficient benchmark. Reliable deployment instead requires consideration of the entire sensing-to-prediction pipeline, encompassing sensor stability and calibration, environmental variability, data integrity and uncertainty, and the robustness and transferability of AI-derived predictions.Despite the rapid evolution of sensing technologies, important challenges remain in integrating heterogeneous data sources, validating emerging sensing systems, and translating complex sensor outputs into reliable, interpretable, and actionable information. The current research topic aims to bring together innovative studies that design, validate, and advance reliable sensing–AI systems for plant monitoring and prediction, with a particular focus on sources of variability and uncertainty across the sensing-to-prediction continuum. Emphasis is placed on the interactions between sensor performance, data quality, environmental and operational variability, and the robustness of downstream AI models. Relevant challenges include sensor calibration and stability, measurement uncertainty, environmental interference, missing or noisy observations, and model generalization and transferability across sensing platforms, cultivars, seasons, and growing environments. Particular attention is given on longitudinal and predictive monitoring, where the reliability of sensing and AI systems must be maintained as plant and environmental conditions evolve. By combining methodological advances in sensing, data processing, and artificial intelligence with rigorous validation under variable conditions, the current research topic seeks to support the transition from static or context-specific assessments toward robust, transferable, and predictive plant-monitoring systems.The current research topic welcomes original research, methods, reviews, mini-reviews, perspectives, and data reports addressing reliable sensing and AI-enabled plant monitoring. Contributions may focus on, but are not limited to:• Performance, calibration, validation, and stability of advanced sensing systems, including proximal and remote sensing, spectroscopy, imaging, biosensors, and IoT-enabled devices.• Measurement and data reliability, including sensor drift, environmental interference, uncertainty, missing or noisy observations, and data-quality assessment.• Robust and uncertainty-aware AI methodologies, including model calibration, generalization, and robustness under biological and environmental variability.• Transferability and domain adaptation across sensors, cultivars, seasons, sites, and growing environments.• Reliable multimodal sensing and data integration under heterogeneous or incomplete observations.• Longitudinal and predictive monitoring of evolving plant states, including early warning and time-series modelling.• Cross-platform, cross-season, and cross-environment validation of sensing–AI systems. Topic editors: Xanthoula Eirini Pantazi Source: https://www.frontiersin.org/research-topics/86320/reliable-and-intelligent-systems-for-plant-monitoring