Estimation of Maize Foliar Temperature and Stomatal Conductance as Indicators of Water Stress Based on Optical and Thermal Imagery Acquired Using an Unmanned Aerial Vehicle (UAV) Platform

Climatic variability and extreme weather events impact agricultural production, especially in sub-Saharan smallholder cropping systems, which are commonly rainfed. Hence, the development of early warning systems regarding moisture availability can facilitate planning, mitigate losses optimise yields through augmentation. Precision practices, facilitated by unmanned aerial vehicles (UAVs) with very high-resolution cameras, useful for monitoring farm-scale dynamics at near-real-time have become an important management tool. Considering these developments, we evaluated utility optical thermal infrared UAV imagery, combination a random forest machine-learning algorithm, to estimate maize foliar temperature stomatal conductance as indicators potential crop water stress content over entire phenological cycle. The results illustrated that waveband was most influential variable during vegetative growth stages, whereas red-edge near-infrared derived vegetation indices were fundamental reproductive stages both conductance. also suggested mild after hailstorm mid-reproductive stage. Furthermore, model optimally estimated various stages. Specifically, best predicted mid-vegetative stage Resultant maps modelled captured spatial heterogeneity within field. Overall, findings study demonstrated use concert prediction-based machine learning, is tool, available farmers help them make informed decisions include optimal implementation irrigation schedules.