Hanfeng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hanfeng Zhang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Fenggang Wen
Shaanxi Key Laboratory of Lacustrine Shale Gas Accumulation and Exploitation, Xi’an 710065, China
1 shared publication - Fushen Liu
Research Center of Coastal and Urban Geotechnical Engineering, Zhejiang University, Hangzhou, China
1 shared publication - Hongfei Duan
School of Civil Engineering, Sun Yat-sen University, Zhuhai 519000, China
1 shared publication - Rui Xu
Research Center of Coastal and Urban Geotechnical Engineering, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China
1 shared publication - Shouguang Wang
State Key Laboratory of Intelligent Coal Mining and Strata Control, Beijing 100013, China
1 shared publication - Shuai Chen
Institute of Mathematics, Henan Academy of Sciences, Zhengzhou 450046, China
1 shared publication
Latest Publications
- Open Access
- 2 June 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (11) , 5568
Multi-Task Spatiotemporal Prediction of Gas Extraction-Induced Seismicity Using a Hybrid GAT-LSTM Neural Network
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.
- 2 June 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (11) , 5568
Open AccessMulti-Task Spatiotemporal Prediction of Gas Extraction-Induced Seismicity Using a Hybrid GAT-LSTM Neural Network
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.