Project Grant 2602175
- The National Science Foundation Division of Materials Research awarded the University of Utah $328,828 on August 15, 2026, for collaborative research developing a motif-based deep learning framework to predict and interpret structural disorder in crystalline solids. The award, supported under the Mathematical and Physical Sciences program (CFDA 47.049), funds research using Zintl phases as a model system to link quantum mechanical simulations, materials databases, and deep learning to uncover...
- The National Science Foundation awarded a $310,000 Project Grant to Arizona State University (ASU) under the Mathematical and Physical Sciences Federal Grant Program (CFDA 47.049). The grant, which runs from May 1, 2025 to April 30, 2028, supports research to develop explainable machine learning models for predicting material properties based on their microstructure. By systematically learning the key n-point correlation functions that drive material behavior, the project aims to provide both...
- The National Science Foundation Division of Materials Research awarded Boise State University $100,000 on October 1, 2026, under the Mathematical and Physical Sciences program (CFDA 47.049) to investigate electrochemically driven phase transformations in nanostructured metal oxides for advanced battery materials. The research will establish a scientific framework for understanding how electrochemical reactions can create metastable crystalline materials with enhanced electrochemical properties...
- The National Science Foundation awarded a $445,000 project grant to Boise State University under the Mathematical and Physical Sciences program (CFDA 47.049) to support research and education activities from December 2022 through May 2025. Dr. Oliviero Andreussi of Boise State University and collaborators will develop new computational tools combining hierarchical models and machine learning techniques to characterize chemical processes at solid-liquid interfaces, with a focus on two-dimensional...
- The National Science Foundation Division of Materials Research awarded Cornell University a $4 million cooperative agreement on October 1, 2025, under the Mathematical and Physical Sciences program (CFDA 47.049) to advance artificial intelligence-driven materials discovery through the AI Materials Institute (AI-MI). The award funds development of the AI Materials Science Ecosystem (AIMS-EC), an open, cloud-based platform coupling a science-ready large-language model with multimodal data...
- The National Science Foundation Division of Materials Research awarded Rensselaer Polytechnic Institute $300,880 on August 15, 2026, to develop a motif-based deep learning framework for predicting and interpreting structural disorder in crystalline solids, with Zintl phases as the model system. The project runs through July 31, 2029, and is performed in Troy, New York. The research links quantum mechanical simulations, materials databases, and deep learning to uncover chemical principles...
- Boise State University was awarded a $486,000 Project Grant from the National Science Foundation Division of Materials Research under the Mathematical and Physical Sciences program (CFDA 47.049). The grant will fund research from July 1, 2021 through December 31, 2024 to study lattice dynamics and phase transitions in multifunctional oxide nanomaterials using ultraviolet Raman spectroscopy. The Mathematical and Physical Sciences program aims to advance scientific knowledge and enhance...
- The National Science Foundation Division of Information and Intelligent Systems awarded Boise State University $499,837 on August 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop transformative AI hardware that integrates photonic and electronic computing chips near memory through vertical 3D assembly, reducing data transfer costs and energy consumption for artificial intelligence computing. The project, titled "3D-PFLOPS: 3D Integrated...
- The National Science Foundation Division of Materials Research awarded Colorado State University $360,004 on July 1, 2026, under the Mathematical and Physical Sciences program (CFDA 47.049) to develop machine learning protocols for designing protein-DNA co-crystal materials that function as three-dimensional scaffolds for capturing and determining the atomic-level structures of biological molecules via X-ray crystallography. The award supports research aimed at accelerating structure...
- The National Science Foundation Division of Materials Research awarded $560,967 to the University of North Carolina at Charlotte on August 1, 2026, to develop physics-informed artificial intelligence generative models for crystal structure prediction and materials discovery. The project will design AI models that incorporate fundamental physics laws, local chemical bonding patterns, and crystallographic symmetries to predict how atoms pack into solid materials. The resulting framework will...
The National Science Foundation Division of Materials Research awarded Boise State University $344,276 on September 1, 2026, under the Mathematical and Physical Sciences program (CFDA 47.049) to develop a deep learning framework that estimates material parameters in multi-principal element alloys directly from microstructure images. The award is a Project Grant with period of performance through August 31, 2029, and place of performance in Boise, Idaho. The research addresses a critical bottleneck in computational materials modeling: the difficulty of determining numerous material parameters experimentally, particularly for complex alloys with multiple principal elements. The Principal Investigator will build an artificial intelligence framework that learns these parameters from microstructure imagery by combining machine learning with fundamental physics governing microstructure evolution. The resulting tools aim to accelerate materials discovery by strengthening the connection between experiments, simulations, and data while improving computational model accuracy and trustworthiness for new materials systems. Educational activities integrate AI-assisted computational problem-solving modules into engineering courses and provide faculty workshops to support AI integration in STEM education, preparing students for an AI-ready engineering workforce. Codes, datasets, and educational resources developed through the project will be made publicly available to benefit the broader research and education communities.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $344.3k | 7/17/26 |