Multi-Task Spatiotemporal Prediction of Gas Extraction-Induced Seismicity Using a Hybrid GAT-LSTM Neural Network
Open Access
- 2 June 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (11) , 5568
Abstract
Spatiotemporal prediction of gas extraction-induced seismicity is a key challenge in regional seismic risk management, hindered by heterogeneous spatial coupling among reservoir blocks and extreme class imbalance in seismicity records. This study proposes a multi-task spatiotemporal forecasting framework based on a dual-encoder architecture combining a Graph Attention Network (GAT) with a Long Short-Term Memory (LSTM) network. The monitoring network is represented as a graph with node-level features including monthly production, reservoir pressure, compaction, and historical seismicity. A Voronoi tessellation strategy maps continuous epicentral coordinates to discrete graph nodes. The GAT encodes heterogeneous spatial interactions via adaptive attention, while a two-layer LSTM extracts multiscale temporal dependencies. Event detection and magnitude classification are treated as parallel tasks, jointly optimized using focal loss and focal-adjusted weighted cross-entropy to mitigate class imbalance. A Seismic Risk Index (SRI) integrates event occurrence and magnitude class probabilities into a continuous risk estimate. Validated on the KNMI seismic catalog and Groningen production data, the model achieves an event Probability of Detection (POD) of 0.677 and a magnitude classification macro average recall (MAvA) of 0.548 under an event rate of 0.07%. Compared with a pure LSTM baseline, the GAT improves POD by 2.1% and MAvA by 7.9%. The time-averaged risk field exhibits spatial heterogeneity broadly consistent with observed seismicity patterns, indicating the potential of this framework for fine-grained spatiotemporal risk assessment of extraction-induced seismicity.Keywords
Funding Information
- National Natural Science Foundation of China (42577162)
- Zhejiang Provincial Science and Technology Plan (2025E10118)
- Open Foundation of Shaanxi Key Laboratory of Lacustrine Shale Gas Accumulation and Exploitation
This publication has 47 references indexed in Scilit:
- Exploring Seismic Hazard in the Groningen Gas Field Using Adaptive Kernel SmoothingMathematical Geosciences, 2023
- Graph neural networks for multivariate time series regression with application to seismic dataInternational Journal of Data Science and Analytics, 2022
- Using machine learning for model benchmarking and forecasting of depletion-induced seismicity in the Groningen gas fieldComputational Geosciences, 2021
- Stress-based, statistical modeling of the induced seismicity at the Groningen gas field, The NetherlandsEnvironmental Earth Sciences, 2020
- Physics‐based forecasting of induced seismicity at Groningen gas field, the NetherlandsGeophysical Research Letters, 2017
- Data‐driven spatialbvalue estimation with applications to California seismicity: Tobor not tobJournal of Geophysical Research: Solid Earth, 2015
- A seismological model for earthquakes induced by fluid extraction from a subsurface reservoirJournal of Geophysical Research: Solid Earth, 2014
- Analysis of induced seismicity in geothermal reservoirs – An overviewGeothermics, 2014
- Mohr–Coulomb Failure CriterionRock Mechanics and Rock Engineering, 2012
- Spatial Tessellations2000