Forecasting the spatiotemporal evolution of fluid-induced microearthquakes with deep learning

2025-06-17

AI Summary

To address the challenge of spatiotemporal forecasting of microseismicity (MEQs) in fluid-injection operations such as enhanced geothermal systems (EGS), this paper proposes the first Transformer-based model for joint multi-target prediction. Given historical hydraulic stimulation parameters and prior microseismic observations, the model performs end-to-end prediction of cumulative event count, logarithmic seismic moment, and 50%/95% spatial envelopes of the microseismic cloud. A novel learnable standard deviation module is embedded to enable probabilistic uncertainty quantification, facilitating real-time inference of fault growth and permeability evolution. Evaluated on the EGS Collab Experiment 1 dataset, the model achieves R² scores of 0.98 and 0.88 for 1-second and 15-second forecasts, respectively. It delivers high accuracy, real-time capability, and physical interpretability—establishing a new paradigm for risk预警 in geotechnical engineering.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Microearthquakes (MEQs) generated by subsurface fluid injection record the evolving stress state and permeability of reservoirs. Forecasting their full spatiotemporal evolution is therefore critical for applications such as enhanced geothermal systems (EGS), CO$_2$ sequestration and other geo-engineering applications. We present a transformer-based deep learning model that ingests hydraulic stimulation history and prior MEQ observations to forecast four key quantities: cumulative MEQ count, cumulative logarithmic seismic moment, and the 50th- and 95th-percentile extents ($P_{50}, P_{95}$) of the MEQ cloud. Applied to the EGS Collab Experiment 1 dataset, the model achieves $R^2>0.98$ for the 1-second forecast horizon and $R^2>0.88$ for the 15-second forecast horizon across all targets, and supplies uncertainty estimates through a learned standard deviation term. These accurate, uncertainty-quantified forecasts enable real-time inference of fracture propagation and permeability evolution, demonstrating the strong potential of deep-learning approaches to improve seismic-risk assessment and guide mitigation strategies in future fluid-injection operations.

Problem

• Forecasting spatiotemporal evolution of fluid-induced microearthquakes
• Predicting reservoir stress and permeability changes
• Enhancing seismic-risk assessment in fluid-injection operations

Innovation

• Transformer-based deep learning model
• Forecasts cumulative MEQ count and seismic moment
• Provides uncertainty estimates via learned standard deviation