Project Grant 2616117
- The National Science Foundation Office of Integrative Activities awarded Northeastern University $350,000 on August 15, 2026, under the Geosciences program (CFDA 47.050) to develop machine learning models that accelerate hydrothermal flow simulations while preserving underlying physics. The project, titled HYDROTML, will generate thousands of physics-based simulations covering realistic ranges of rock properties, heat sources, and fluid conditions across meter-to-kilometer scales, then train...
- The National Science Foundation Office of Integrative Activities awarded the University of Texas at Austin $364,836 on September 1, 2026, under the Geosciences program (CFDA 47.050) to develop graph neural network-based digital twins for subsurface multiphase flow modeling. The project will create artificial intelligence methods that integrate observations and models to improve understanding of fluid movement through geological formations, particularly where complex geology and limited...
- The National Science Foundation Office of Integrative Activities awarded the University of Houston System $662,871 on October 1, 2026, under the Geosciences program (CFDA 47.050) to test geological hypotheses of the Yellowstone Caldera using deep generative models. The research will create high-resolution, three-dimensional electrical conductivity models of Yellowstone's hydrothermal plumbing system by applying unsupervised, probabilistic deep-learning inversion to airborne electromagnetic and...
- The National Science Foundation Office of Integrative Activities awarded the University of Montana $276,152 on August 15, 2026, under the Geosciences program (CFDA 47.050) to develop physics-informed machine-learning emulators of lake thermal process models for global temperature reconstruction from sediment cores. The project replaces computationally intensive first-principles physical lake models with machine-learning surrogates trained to emulate those models, enabling dramatic speedup of...
- This $399,162 Project Grant award from the National Science Foundation's Geosciences Program (CFDA 47.050) aims to develop interpretable, stable, and mass-conserving artificial intelligence (AI) models to improve the computational speed and efficiency of geoscientific models, such as those used for air pollution and climate research. The project will create simpler "surrogate" machine learning models for key components like atmospheric chemistry and wildfire plume rise, allowing for...
- The National Science Foundation Office of Integrative Activities awarded the University of Kansas Center For Research Inc. $453,579 on October 1, 2026, under the Geosciences program (CFDA 47.050) to develop artificial intelligence frameworks for mapping and characterizing active fault systems globally. The project will create AI tools that integrate geophysical and geological constraints within physically informed learning models to infer fault properties and map active fault networks across...
- The National Science Foundation Office of Integrative Activities awarded the University of Texas at Austin $450,000 on September 1, 2026, under the Geosciences program (CFDA 47.050) to develop computational tools for understanding coastal groundwater and ocean exchange using machine learning. The project will create a next-generation computational framework that combines neural operators with an open-source coupling framework to build hybrid physics-aware surrogate models emulating...
- The National Science Foundation Office of Integrative Activities awarded The Research Foundation For The State University Of New York $525,530 on August 15, 2026, under the Geosciences program (CFDA 47.050) for collaborative research advancing long-term temperature reconstruction using physics-informed neural networks through lake model emulation. The project develops a machine-learning framework to replace traditional physics-based lake models with AI-derived surrogates that dramatically...
- The National Science Foundation Office of Integrative Activities awarded the University of Miami $277,083 on August 15, 2026, under the Geosciences program (CFDA 47.050) to develop artificial intelligence tools for analyzing dense seismic array data from temporary field deployments in Oklahoma, Texas, and Hawai'i. The project will create a geometry-aware self-supervised learning framework that processes paired time-domain and frequency-domain seismic recordings while accounting for variations in...
- The National Science Foundation Office of Integrative Activities awarded Massachusetts Institute of Technology $898,723 on September 1, 2026, under the Geosciences program (CFDA 47.050) to develop artificial intelligence tools that combine physics-based models with high-resolution topographic data to forecast landscape evolution and erosion. The project will construct a hybrid simulation-to-real framework in which physics-informed generative AI models trained on landscape evolution simulations...
The National Science Foundation Office of Integrative Activities awarded The University of Kentucky Research Foundation $350,624 on August 15, 2026, under the Geosciences program (CFDA 47.050) to develop machine learning–accelerated surrogate models for hydrothermal flow simulation. The project, titled "Machine Learning Accelerated Hydrothermal Modeling for Earth Science," combines physics-based simulations of hydrothermal systems with machine learning models designed to respect the symmetries and physical laws of the governing equations. Hydrothermal systems—where hot water moves through rock in faults, volcanoes, and geothermal fields—are difficult to predict because they span multiple scales and involve complex interactions between liquid water and steam. Current computational models are accurate but too slow to test multiple scenarios. This research will generate thousands of simulations covering realistic ranges of rock properties, heat sources, and fluid conditions from the meter to kilometer scale, then train surrogate models to reproduce full simulations at a fraction of the computer time. The goal is to accelerate these models by factors of thousands while preserving underlying physics, enabling researchers to assess eruption likelihood, guide critical mineral exploration, and estimate geothermal field energy capacity. The project includes student training in earth science and AI, public release of software, and K-12 geohazard education. Performance runs through July 31, 2029, at Lexington, Kentucky.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $350.6k | 8/11/26 |