Wildfire

Forest health monitoring often depends on measurements that reveal treatment effects only after several years, such as radial growth, while many important physiological and canopy-level responses occur much sooner. This talk introduces the Physio-Spatial Monitoring Program (PSMP), a developing framework for repeatable tree-level monitoring that integrates standardized drone imagery, individual tree crown mapping, vegetation index trends, and site and treatment context. Field validation would pair same window drone flights with upper canopy physiology measurements including stomatal conductance, chlorophyll fluorescence, and midday water potential to test whether remotely sensed canopy signals correspond to measurable tree stress and treatment response. Rather than presenting artificial intelligence as a finished product, this talk frames PSMP as the data architecture needed to make future supervised learning possible: a system for turning repeated forest observations into model-ready records that can eventually support early warning alerts, treatment response prediction, and more adaptive forest management.