Local-scale observations are critical for understanding hydrologic, geomorphic, and biogeochemical processes, but field-based, in situ, drone, and airborne measurements are often constrained by limited spatial coverage, temporal resolution, labor intensity, and methodological inconsistency. Satellite observations provide important regional context, but often lack the spatial resolution needed to resolve the local processes that drive broader system behavior. Recent advances in artificial intelligence (AI), combined with the growing availability of dense imagery, video, and sensor-based time series, are creating new opportunities to generate high-resolution, high-throughput observations from low-cost, readily deployable platforms. This session invites contributions that use AI to observe, quantify, and interpret local-scale Earth surface processes and to connect those insights to watershed- and landscape-scale dynamics. Topics of interest include AI-enhanced hydrologic and ecohydrologic observations, geomorphic monitoring, biogeochemical measurements, AI-ready data workflows, and quantitative comparisons between AI-enabled and traditional observational approaches, including benchmarking, uncertainty analysis, and performance assessment.

• B - Biogeosciences
• EP - Earth and Planetary Surface Processes