Genesis Mission Awards Advance E3SM Prediction

The U.S. Department of Energy announced 278 Phase I projects under the Genesis Mission, selected from over 5,000 submissions. Phase I grants provide 9-month funding between $500,000 and $750,000 to integrate artificial intelligence with scientific research.

Fourteen awards connected to E3SM will advance prediction of clouds, precipitation, water resources, and coupled Earth system processes. Together, the projects apply physics-informed machine learning (ML), generative AI, foundation models, and agentic AI to challenges central to E3SM.

Five awards focus on cloud, aerosol, and precipitation physics. Yan Feng (ANL) leads work using observationally constrained, physics-informed ML to improve cloud microphysics. Gabriel Isaacman-VanWertz (Virginia Polytechnic Institute and State University) is developing multimodal AI to uncover connections between cloud microphysics and precipitation. Lekha Patel (SNL) leads generative modeling to upscale particle-resolved aerosol-cloud microphysics. Kyle Pressel (PNNL) leads development on physics-constrained artificial intelligence closures for cloud microphysics and turbulence. Yunyan Zhang (LLNL) leads work on scalable artificial intelligence methods for turbulence and cloud parameterizations. These projects address persistent sources of uncertainty in E3SM while helping translate detailed process understanding into computationally efficient model components.

Four awards strengthen E3SM’s representation and prediction of water. Hong-Yi Li (Lehigh University) leads work examining connections between groundwater, reservoirs, river flow, and energy systems. Eugene Yan (ANL) leads a multi-fidelity artificial intelligence foundation model for coupled surface-groundwater predictions, water availability, and flood hazards. Dali Wang (ORNL) leads integrated weeks-to-years water prediction for the Tennessee Valley Authority region. Qing Zhu (LBNL) is applying AI to water systems that support energy infrastructure.

Five projects target subseasonal-to-seasonal (S2S) and longer-range prediction. Hansi Singh (Planette Analytics Inc. ) leads development of deep learning methods to enhance subseasonal MCS predictions, including from E3SM. Luke Van Roekel (LANL) leads a generative AI project created specifically to address E3SM’s seasonal-to-decadal (S2D) needs through improved coupled ocean-ice states. Da Yang (Board of Trustees of the Leland Stanford Junior University) leads work on improving S2S prediction of atmospheric rivers. Jinwoong Yoo (University of Maryland) leads an agentic AI framework coupling large AI models with E3SM for seasonal-to-interannual U.S. water prediction. Shixuan Zhang (PNNL) leads drift-aware initialization of coupled Earth system models for scalable subseasonal-to-seasonal prediction.

E3SM staff, advisors, and collaborators participate across all 14 awards. Collectively, these projects can make E3SM more accurate, scalable, adaptive, and useful for energy and water decision-making.

Reference

List of Awardees: GM RFA Awards List

Abstracts can be found through PAMS Public Abstract Search site (Advance Search Parameters: Solicitation Number: DE-FOA-0003612 for Genesis, or search by PI’s name)

Lab specific announcements:

• ANL: Genesis Mission Research Projects
• BNL: Complete List of Brookhaven Lab Genesis Mission Phase I Projects
• LANL: Genesis Mission funding awarded to seven Los Alamos projects | LANL
• LBL: Genesis Mission Projects – Lawrence Berkeley National Laboratory
• LLNL: LLNL selected to lead 10 projects under DOE’s Genesis Mission
• ORNL: Department of Energy selects ORNL to lead nine Genesis Mission projects
• PNNL: https://www.pnnl.gov/projects/genesis-mission/awards
• SNL: Sandia selected to lead six Genesis Mission projects, partner on 17 others

Contact

• Renata McCoy, Lawrence Livermore National Laboratory