Project Grant 2608400
- Federal Grant Award Summary The National Science Foundation's Division of Polar Programs (CFDA 47.078) awarded $738,807 to The Leland Stanford Junior University effective September 1, 2025, through August 31, 2030, to develop physics-informed deep learning algorithms for modeling ice sheet and ice shelf dynamics. The primary deliverable is DIFFICE.JAX, an open-source deep learning tool designed to infer continent-wide ice shelf viscosity structures from satellite data. This technology...
- Federal Grant Award Summary The National Science Foundation's Office of Integrative Activities awarded $805,132 to the University of Colorado-Denver under the Geosciences program (CFDA 47.050) for a three-year collaborative research project spanning September 1, 2025 through August 31, 2028. The project delivers novel artificial intelligence (AI) and machine learning methodologies specifically designed to automate sea ice classification by addressing critical data quality irregularities in...
- Federal Grant Award Summary Award Details: This NSF Geosciences Program (CFDA 47.050) Project Grant of $505,036 was awarded to Trustees of Dartmouth College on January 1, 2026, with a completion date of December 31, 2028. The collaborative research project, titled "Physics-Informed Machine Learning of Ice Calving and Sliding," addresses sea level rise prediction by combining artificial intelligence with established glaciology principles. Primary Deliverables and Services: The project...
- This $411,096 federal Project Grant award was provided by the National Science Foundation's Polar Programs (CFDA 47.078) to The Leland Stanford Junior University (Stanford University). The project aims to utilize machine learning and physics-based models to map and understand how surface meltwater on the Greenland ice sheet reaches the bedrock, which can impact ice sheet dynamics and response to climate change. Key products and services to be delivered include: Development of open-source deep...
- Federal Project Grant Award Summary The Leland Stanford Junior University received a $266,000 Project Grant from the National Science Foundation's Division of Information and Intelligent Systems (CISA program, CFDA 47.070) effective October 1, 2025, through September 30, 2029. This collaborative research initiative advances Large Language Model (LLM) unlearning—a technology enabling the targeted removal of harmful data influences, memorized sensitive content, copyrighted material, and unsafe...
- Federal Grant Award Summary The University of Colorado received a $317,922 Project Grant from the National Science Foundation's Office of Integrative Activities under the Geosciences Program (CFDA 47.050), effective September 1, 2025, through August 31, 2028. This collaborative research initiative develops novel artificial intelligence (AI) and machine learning methodologies to automate sea-ice classification and mapping by addressing critical data quality irregularities in existing label...
- Federal Grant Award Summary The National Science Foundation's Division of Polar Programs (CFDA 47.078) awarded $782,557 to The Research Foundation for the State University of New York on August 1, 2025, for a CAREER project addressing dimensionality reduction of glacier and ice-sheet processes using deep learning. The primary deliverable is the development and evaluation of three high-efficiency artificial intelligence (AI)-based modules that represent complex glacier processes for integration...
- Federal Grant Award Summary The National Science Foundation (NSF) awarded The Leland Stanford Junior University a $677,600 Project Grant under the Mathematical and Physical Sciences program (CFDA 47.049) effective September 15, 2025, with a completion date of August 31, 2028. The project, titled "AIMING: AI Theorem Proving Beyond Limited Data: Efficient Learning of Mathematicians' Ecosystem," develops artificial intelligence (AI) systems designed to accelerate mathematical research and...
- Federal Grant Award Summary The National Science Foundation (NSF) awarded The Leland Stanford Junior University a $103,017 Project Grant under the Mathematical and Physical Sciences program (CFDA 47.049) effective November 1, 2025, with completion scheduled for August 31, 2026. This collaborative research initiative, titled "ELEMENTS: Enabling Particle and Nuclear Physics Discoveries with Neural Deconvolution," develops open-source cyberinfrastructure to publish and reuse...
- Federal Project Grant Award Summary Funding Agency: National Science Foundation, Office of Integrative Activities Program: Geosciences (CFDA 47.050) Award Amount: $325,000 Award Date: October 1, 2025 Performance Period: October 1, 2025 – September 30, 2028 Awardee: Massachusetts Institute of Technology (Cambridge, MA) This collaborative research project develops advanced artificial intelligence (AI) tools and improved Earth System Model (ESM) parameterizations to address critical limitations...
The National Science Foundation's Office of Integrative Activities awarded The Leland Stanford Junior University a $300,000 Project Grant under the Geosciences program (CFDA 47.050) beginning September 1, 2026, and concluding August 31, 2029. This award supports the development of DiffIce-JAX 2.0, an openly available, physics-informed machine learning software platform designed to infer hidden physical properties of Antarctic ice sheets—specifically ground slipperiness and ice stiffness—by coupling artificial intelligence algorithms with high-fidelity physics models. The software processes satellite and airborne measurement data to enhance predictive capabilities regarding ice-sheet dynamics and sea-level rise, thereby addressing a critical scientific uncertainty in understanding accelerating ice-sheet melting and its contribution to global coastal flooding risks. The project delivers community cyberinfrastructure that democratizes access to specialized ice-sheet modeling techniques by lowering technical barriers for broader participation in geoscience research. Key technical advances include implementation of a multistage neural network training strategy to handle multiscale features and extension of regional ice-shelf inversion capabilities to full Antarctic ice-sheet scales using the JAX Python library. The award further supports workforce development through annual summer schools and conference workshops that train emerging scientists at the intersection of geoscience and artificial intelligence, facilitating the adoption of these tools across the research community.Federal Grant Award Summary
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $300.0k | 6/30/26 |