SBIR Phase I: AI Systems and Methods for Critical Natural Resource Development

The broader impact of this Small Business Innovation Research (SBIR) Phase I project will be to accelerate the development of mineral and energy resources critical to the US economy and electrification of global energy. Improved mineral targeting and screening will increase the effectiveness of each dollar spent on exploration for copper, nickel, cobalt, and critical rare-earth minerals. More effective drill-targeting can shorten the time required to measure a deposit by several years, helping to get critical supply into the market sooner. Applying AI to the design of carbon storage and geothermal reservoirs will help generate more energy and store more CO2 while ensuring critical safety requirements can be met with confidence. This Small Business Innovation Research (SBIR) Phase I project will advance the capabilities of several key AI methods to address challenges for the geosciences and natural resources. Generative and autonomous decision-making AI have radically changed several important industries from vehicles to biotechnology. They have the potential to do the same for the geosciences and industries like materials and energy by making it easier to interpret large, high dimensional data and design complex systems for underground resources. These methods, however, cannot be directly applied without modifications to address the size of geological problems and the significant diversity of data and relatively small amount available. The company’s approach focuses on improving neural network architecture to improve sample efficiency and to utilize foundation model approaches to reduce training data volume requirements. The company anticipates that this research will result in a class of state-of-the-art AI methods for geological resources and scientific applications. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.