Oklahoma Labeled AI Dataset for Seismology

Read full text
Authors: Hongyu Xiao, Jacob I. Walter, Paul O. Ogwari, Andrew D. Thiel, Isaac Woelfel, Nicholas Gregg, Brandon Mace
Cited by: 1

Abstract

Oklahoma Labeled AI Dataset (OKLAD), a manually curated dataset compiled by the Oklahoma Geological Survey (OGS). Covering a region strongly impacted by anthropogenic activity, OKLAD provides a rare resource for studying induced seismicity and serves as a benchmark for evaluating deep-learning detection models and transfer learning approaches in local and regional seismic monitoring. This is associated with Xiao et al.,2026 paper in JGR machine learning about induced seismicity and transfer learning.

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
13 March 2026
Document type
Dataset