Project Grant 2616413

The National Science Foundation Office of Integrative Activities awarded Texas A&M University $718,221 on August 15, 2026, under the Geosciences program (CFDA 47.050) to develop artificial intelligence tools for analyzing dense seismic array data.

The project will create a geometry-aware self-supervised learning framework to process temporary dense-array seismic recordings from Oklahoma, Texas, and Hawai'i. The framework will learn representations from paired time-domain and frequency-domain views of array data while accounting for station layout, noise conditions, and deployment geometry. These learned representations will be linked to interpretable source properties through sequential downstream tasks including source-physics mapping and rare or under-recognized event discovery. The work addresses the challenge that temporary dense seismic arrays, deployed for weeks to months, generate datasets too large and complex to analyze manually. New AI tools will identify meaningful signal patterns, connect short-term dense-array observations to long-term monitoring records, and help scientists distinguish natural from human-related seismic activity and recognize emerging event types. The project will also produce reusable workflows and curated training resources for the research community while training students and early-career researchers at the intersection of geoscience and machine learning.

Performance period runs through July 31, 2029, with work performed at Texas A&M University in College Station, Texas.