The integration of satellite remote sensing and ground-based in-situ observations provides a powerful foundation for understanding environmental variability and change. When coupled with hybrid modeling approaches combining Artificial Intelligence/Machine Learning (AI/ML) with physics-based models, these multi-source datasets enable deeper process-level understanding, improved prediction, and actionable insights. This session emphasizes advances at the intersection of observations and hybrid modeling, focusing on how they improve our ability to analyze, attribute, and predict variability and extremes in environmental time series ranging from precipitation and aerosols to carbon fluxes and land–atmosphere feedbacks.
Recent progress in various satellite-derived products (e.g., precipitation from GPM/IMERG, aerosol optical depth/AOD, black carbon concentrations, vegetation and carbon flux indicators) and ever-expanding ground-based networks has greatly enhanced our capability to detect and monitor environmental parameters and their variability. At the same time, hybrid approaches such as physics-informed ML, data assimilation with AI, explainable AI, and transfer learning are emerging as transformative tools to improve predictive skill for extremes, attribute their sources, and assess long-term trends. Together, these innovations are reshaping how we study historical variability and future projections, and how results are translated into actionable information for climate adaptation and resilience.