Agricultural production is increasingly vulnerable to climate variability, extreme weather, and growing resource limitations. To better understand these challenges and support adaptation, regional crop modeling, whether process-based, data-driven, or hybrid, has become an essential tool for assessing agricultural productivity, food and water security, and the impacts of climate variability and change. At the same time, the growing availability of satellite observations provides unprecedented opportunities to better constrain, calibrate, and validate crop model simulations, from field to continental scale. This session focuses on recent methodological and applied advances in linking regional crop models with Earth observation datasets to improve predictive accuracy and robustness.

We invite contributions that address:
• Advances in regional crop modeling frameworks, including process-based, data-driven (machine learning/AI, statistical), and hybrid approaches
• Data assimilation techniques and model parameterization methodologies
• Integration of remote sensing data into regional crop modeling systems
• Pre- and in-season yield forecasting
• Applications to water use, irrigation, and agro-hydrological monitoring
• Applications to assess and optimize climate change adaptation strategies
• Benchmarking and intercomparison of crop models with remote sensing data

This session brings together researchers in crop modeling, remote sensing, climate science, and data assimilation, spanning both process-based and data-driven approaches, to advance integration across disciplines and tackle global challenges in agriculture, water, and food security. We particularly welcome contributions on coupling satellite-derived soil moisture, evapotranspiration, and vegetation data with crop and land surface models for forecasting and irrigation applications at regional to continental scale.