Forecasting induced seismicity in enhanced geothermal systems using machine learning: challenges and opportunities

Geophysical Journal International, vol. 242

Abstract

SUMMARY Induced seismicity poses a significant challenge to the safe and sustainable development of Enhanced Geothermal Systems (EGS). This study explores the application of machine learning (ML) for forecasting cumulative seismic moment (CSM) of induced seismic events to evaluate reservoir stability in response to fluid injections. Using data from the Cooper Basin (Australia), the St1 Helsinki geothermal project (Finland), and a controlled laboratory injection experiment, we evaluate ML models that integrate catalogue and operational features with various frameworks. Results indicate that feature-rich models outperform simpler ones in complex seismic environments like the Cooper Basin and laboratory cases, where seismicity is promoted by earthquake interaction and fault reactivation. However, in scenarios like St1 Helsinki, with minimal event clustering, additional features offer limited predictive benefits. While ML models are promising, several challenges impede reliable forecasting, including data scarcity from operational wells, the extrapolation demands of cumulative output (i.e. CSM) and the difficulty of predicting abrupt CSM increases for large seismic events. Enhancing model robustness requires synthetic data augmentation and improved feature selection capable of capturing diverse reservoir dynamics. These advancements may enable more accurate near real-time forecasts of problematic induced seismic events, informing operational decisions to mitigate seismic risks while maximizing energy extraction, and hence offering a pathway for broader adoption of ML in renewable energy development and management.

Authors 7

1. Sadegh Karimpouli corresponding

   GFZ Helmholtz Centre for Geosciences

   Affiliation as printed

   GFZ Helmholtz Centre for Geosciences , 14473 Potsdam ,

   GFZ Helmholtz Centre for Geosciences, 14473 Potsdam, Germany

2. Grzegorz Kwiatek

   GFZ Helmholtz Centre for Geosciences

   Affiliation as printed

   GFZ Helmholtz Centre for Geosciences , 14473 Potsdam , . E-mail: sadegh.karimpouli@gfz.de

   GMuG Gesellschaft für Materialprüfung und Geophysik mbH , Dieselstraße 9, D-61231 Bad Nauheim ,

3. Patricia Martínez‐Garzón Aachen

   GFZ Helmholtz Centre for Geosciences · RWTH Aachen University

   Affiliation as printed

   GFZ Helmholtz Centre for Geosciences , 14473 Potsdam ,

   RWTH University of Aachen , 52062 Achen ,

   GFZ Helmholtz Centre for Geosciences, 14473 Potsdam, Germany

   RWTH University of Aachen, 52062 Achen, Germany

4. Danu Caus

   German Climate Computing Centre · Helmholtz-Zentrum Hereon

   Affiliation as printed

   DKRZ German Climate Computing Centre , 20146 Hamburg ,

   Helmholtz AI , 85764 Neuherberg ,

   Helmholtz Centre Hereon , 21502 Geesthacht ,

   DKRZ German Climate Computing Centre, 20146 Hamburg, Germany

   Helmholtz AI, 85764 Neuherberg, Germany

   Helmholtz Centre Hereon, 21502 Geesthacht, Germany

5. Lei Wang

   GFZ Helmholtz Centre for Geosciences

   Affiliation as printed

   GFZ Helmholtz Centre for Geosciences , 14473 Potsdam ,

   GFZ Helmholtz Centre for Geosciences, 14473 Potsdam, Germany

6. Georg Dresen

   GFZ Helmholtz Centre for Geosciences

   Affiliation as printed

   GFZ Helmholtz Centre for Geosciences , 14473 Potsdam ,

   GFZ Helmholtz Centre for Geosciences, 14473 Potsdam, Germany

7. Marco Bohnhoff

   GFZ Helmholtz Centre for Geosciences · Freie Universität Berlin

   Affiliation as printed

   Free University Berlin Department of Earth Sciences, , 14195 Berlin ,

   GFZ Helmholtz Centre for Geosciences , 14473 Potsdam ,

   Department of Earth Sciences, Free University Berlin, 14195 Berlin, Germany

   GFZ Helmholtz Centre for Geosciences, 14473 Potsdam, Germany