Shouguang Wang
Shouguang Wang has a total of 9 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
2 shared publications - Fushen Liu
Research Center of Coastal and Urban Geotechnical Engineering, Zhejiang University, Hangzhou, China
2 shared publications - Hanfeng Zhang
Research Center of Coastal and Urban Geotechnical Engineering, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, 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 - 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.
- Open Access
- 25 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (11) , 5298
Numerical Investigation of Hydraulic Fracturing Induced Seismicity in Fractured Shale Media Using a Fully Coupled HMD–DFN Model
Amid the global transition to low-carbon energy systems, unconventional oil and gas resources play a key role in ensuring energy security. Hydraulic fracturing is a central technology for unconventional resource development, but it may also induce seismicity. This study investigates energy release and induced seismicity during hydraulic fracturing in naturally fractured media. A fully coupled hydro-mechanical-damage (HMD) model combined with a discrete fracture network (DFN) is developed to represent natural fractures in shale reservoirs. By incorporating frictional contact and shear slip, the model simulates tensile propagation of hydraulic fractures and shear slip of natural fractures. Parameter sensitivity analyses are conducted for natural fracture characteristics, differential stress, elastic modulus, and injection rate. The energy release of shear slip and tensile propagation is compared based on total seismic moment. Results show that the seismic moment generated by natural fracture shear slip is several orders of magnitude higher than that from tensile propagation, indicating that shear slip is the dominant energy release mechanism. Increasing the number and length of natural fractures enhances fracture-network connectivity and pressure diffusion, making natural fractures more prone to shear instability. Higher differential stress, elastic modulus, and injection rate may further promote slip-induced energy release and elevate induced seismic risk. These findings provide a theoretical basis for seismic risk assessment and parameter optimization in hydraulic fracturing.
- 25 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (11) , 5298
Open AccessNumerical Investigation of Hydraulic Fracturing Induced Seismicity in Fractured Shale Media Using a Fully Coupled HMD–DFN Model
Amid the global transition to low-carbon energy systems, unconventional oil and gas resources play a key role in ensuring energy security. Hydraulic fracturing is a central technology for unconventional resource development, but it may also induce seismicity. This study investigates energy release and induced seismicity during hydraulic fracturing in naturally fractured media. A fully coupled hydro-mechanical-damage (HMD) model combined with a discrete fracture network (DFN) is developed to represent natural fractures in shale reservoirs. By incorporating frictional contact and shear slip, the model simulates tensile propagation of hydraulic fractures and shear slip of natural fractures. Parameter sensitivity analyses are conducted for natural fracture characteristics, differential stress, elastic modulus, and injection rate. The energy release of shear slip and tensile propagation is compared based on total seismic moment. Results show that the seismic moment generated by natural fracture shear slip is several orders of magnitude higher than that from tensile propagation, indicating that shear slip is the dominant energy release mechanism. Increasing the number and length of natural fractures enhances fracture-network connectivity and pressure diffusion, making natural fractures more prone to shear instability. Higher differential stress, elastic modulus, and injection rate may further promote slip-induced energy release and elevate induced seismic risk. These findings provide a theoretical basis for seismic risk assessment and parameter optimization in hydraulic fracturing.