Accurately scaling flux tower observations to landscape levels requires integrating ground-truth data, remote sensing (RS) observations, and theoretical understanding. As environmental monitoring goals grow more complex, the synergy between process-based models and Artificial Intelligence (AI) has become essential for scale-aware data integration.

Building on the AmeriFlux–NEON–CarbonDew workshop series, this session focuses on advancing the methods that link eddy covariance fluxes with RS observations across spatial and temporal scales, emphasizing AI’s role in bridging these gaps.

We welcome contributions including, but not limited to: (i) AI-enabled flux attribution and upscaling using RS; (ii) Ground-truthing and cross-validation across multi-scale RS and flux towers; (iii) Advances in physics-informed machine learning (PIML); (iv) Integration of novel RS sensors (hyperspectral, lidar) into AI-enhanced flux frameworks; (v) Real-world applications in land management, forestry, and urban systems; and (vi) Collaborative tools and open-science platforms for sharing AI models and benchmark datasets.

• A - Atmospheric Sciences
• GC - Global Environmental Change
• H - Hydrology
• SY - Science and Society