209 Deep-Time Earth and the AI Revolution

We invite overviews related to compiling and deciphering large regional to global-scale datasets on the fascinating history of our Earth and Solar System, and to unraveling the interplay of processes that shaped the past.

Tuesday, 21 October 2025
1:30 PM - 5:30 PM
HBGCC, 301C

Deep-Time Data-Driven Discovery in Mineralogy: Visualizing Earth's >4.6-Billion Year Mineral Evolution

Paper number: 209-2
Program: Technical Sessions
Time: 2:05 PM – 2:25 PM

Authors

  • Robert Hazen Presenting Author
    Carnegie Institution for Science, Earth and Planets Laboratory, Washington, DC

Abstract

Minerals and rocks are information-rich, multi-dimensional, and multi-scale natural systems that preserve hundreds of compositional, structural, morphological, and other environmental signatures of planetary history. Every mineral specimen is a time capsules, waiting to be opened. The convergence of mineralogy with data science and informatics is revolutionizing our ability to decode these persistent and vivid records of planetary evolution. Progress in mineral informatics rests on four pillars: (1) the development of large and rapidly expanding open-access data resources, including data on physical and chemical properties as well as locations, ages, and asociated mineral species; (2) the application of powerful data analytical and visualization methods, including network analysis, cluster analysis, association analysis, and more; (3) the development of artificial intelligent algorithm for complex data distribution, with powerful applications in the search for new critical mineral resources; and (4) interdisciplinary interpretation and quantitative rules extraction of results after applying these data and methods, for example to understand global trends in mineralogy through deep time.

Among recent contributions are development and expansion of open and reliable data resources that conform to FAIR practices (Findable, Accessible, Interoperable, and Reusable); elucidation of co-evolutionary trends in planetary mineralogy, petrology, geochemistry, tectonics, and their links to biosphere; applications of artificial intelligence and machine learning in mineral resource exploration, including predictive modeling for discovering new economic deposits; and community detection, unsupervised learning, network analysis, and clustering algorithms applied to mineral/rock identification, classification, and planetary evolution staging.

Geological Society of America Abstracts with Programs. Vol. 57, No. 6

doi: 10.1130/abs/2025AM-412556

© Copyright 2025 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.