Recent developments in Earth observation, data science, and computational modeling are revolutionizing our understanding of soil physics processes. The goal of this session is to bring together researchers who utilize a combination of remote sensing data, artificial intelligence (AI), and process-based models for better understanding soil properties and hydrological behavior, as well as for their interactions with the atmosphere. Contributions. We invite submissions on the following (but not restricted to) topics:
• Application of multi-scale remote sensing (satellite, aircraft, drones, proximal sensing) for soil physical properties estimation, process monitoring, and spatial variability of soil conditions (moisture, texture, compaction, salinity, erosion) mapping across scales.
• Uses of machine learning and AI methods to combine with mechanistic/process-based models.
• Data assimilation, (Bayesian) inverse modeling, data fusion techniques, and data-driven models for monitoring soil conditions (moisture, texture, compaction, salinity, erosion), soil hydraulic properties, and soil–plant–atmosphere interactions across scales.
• Quantifying uncertainties and error propagation in coupled soil physics models and remote sensing products.
• Case studies that illustrate the use of these methods for climate impact assessments, sustainable land management, and hydrological prediction.
This session will bridge the traditional concepts in soil physics and the advancing technologies (e.g., remote sensing, data analytics, and modeling) to bring soil scientists and remote sensing researchers into an interdisciplinary discussion. Young and early-career researchers, as well as interdisciplinary researchers, are especially invited to submit their contributions.