Predictions of biogeochemical cycles are essential for accurate biological-Earth-energy system modeling, and they are influenced by ecosystem structure and function, hydrological cycles, extreme events, and other interactions in the Earth system. Relevant ecological processes, including microbial and vegetation dynamics, operate at different spatial and temporal scales and vary across terrestrial, riverine, and coastal ecosystems. Biogeochemical cycles have two-way interactions with land cover/land use change and disturbances, such as floods, droughts, permafrost thaw-induced ground subsidence, extreme winds, and wildland fires, that impact energy exploration, production, and distribution systems and other built infrastructure. This session focuses on integrated understanding of mechanisms that are or should be represented in process-based, statistical, and artificial intelligence (AI)-enabled biological-Earth-energy system models; methods for evaluating and benchmarking models; approaches for building data-driven parameterizations and constraining models with data; and novel applications of AI and machine learning to improve predictive understanding of biological-Earth-energy system interactions.

• H - Hydrology
• IN - Informatics
• NH - Natural Hazards
• OS - Ocean Sciences