Hengguang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hengguang Liu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Changrong Zhang
Key Laboratory of Tropical Oceanography, South China Sea Institute of Oceanology, Chinese Academy of Sciences, Guangzhou 510301, China
1 shared publication - Chaoyan Fan
Key Laboratory of Tropical Oceanography, South China Sea Institute of Oceanology, Chinese Academy of Sciences, Guangzhou 510301, China
1 shared publication Fan Xiao
School of Earth Sciences and Engineering Sun Yat‐Sen University Guangzhou China
1 shared publicationHui Chang
School of Earth Sciences and Engineering Sun Yat‐Sen University Guangzhou China
1 shared publication- Shaohong Xia
Key Laboratory of Tropical Oceanography, South China Sea Institute of Oceanology, Chinese Academy of Sciences, Guangzhou 510301, China
1 shared publication Tiancheng Zheng
School of Earth Sciences and Engineering Sun Yat‐Sen University Guangzhou China
1 shared publication
Latest Publications
- Open Access
- 25 October 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (11) , 1907
Integrating Multimodal Deep Learning with Multipoint Statistics for 3D Crustal Modeling: A Case Study of the South China Sea
Constructing an accurate three-dimensional (3D) geological model is crucial for advancing our understanding of subsurface structures and their evolution, particularly in complex regions such as the South China Sea (SCS). This study introduces a novel approach that integrates multimodal deep learning with multipoint statistics (MPS) to develop a high-resolution 3D crustal P-wave velocity structure model of the SCS. Our method addresses the limitations of traditional algorithms in capturing non-stationary geological features and effectively incorporates heterogeneous data from multiple geophysical sources, including 44 wide-angle seismic crustal structure profiles obtained by ocean bottom seismometers (OBSs), gravity anomalies, magnetic anomalies, and topographic data. The proposed model is rigorously validated against existing methods such as Kriging interpolation and MPS alone, demonstrating superior performance in reconstructing both global and local spatial features of the crustal structure. The integration of diverse datasets significantly enhances the model’s accuracy, reducing errors and improving the alignment with known geological information. The resulting 3D model provides a detailed and reliable representation of the SCS crust, offering critical insights for studies on tectonic evolution, resource exploration, and geodynamic processes. This work highlights the potential of combining deep learning with geostatistical methods for geological modeling, providing a robust framework for future applications in geosciences. The flexibility of our approach also suggests its applicability to other regions and geological attributes, paving the way for more comprehensive and data-driven investigations of Earth’s subsurface.
- 25 October 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (11) , 1907
Open AccessIntegrating Multimodal Deep Learning with Multipoint Statistics for 3D Crustal Modeling: A Case Study of the South China Sea
Constructing an accurate three-dimensional (3D) geological model is crucial for advancing our understanding of subsurface structures and their evolution, particularly in complex regions such as the South China Sea (SCS). This study introduces a novel approach that integrates multimodal deep learning with multipoint statistics (MPS) to develop a high-resolution 3D crustal P-wave velocity structure model of the SCS. Our method addresses the limitations of traditional algorithms in capturing non-stationary geological features and effectively incorporates heterogeneous data from multiple geophysical sources, including 44 wide-angle seismic crustal structure profiles obtained by ocean bottom seismometers (OBSs), gravity anomalies, magnetic anomalies, and topographic data. The proposed model is rigorously validated against existing methods such as Kriging interpolation and MPS alone, demonstrating superior performance in reconstructing both global and local spatial features of the crustal structure. The integration of diverse datasets significantly enhances the model’s accuracy, reducing errors and improving the alignment with known geological information. The resulting 3D model provides a detailed and reliable representation of the SCS crust, offering critical insights for studies on tectonic evolution, resource exploration, and geodynamic processes. This work highlights the potential of combining deep learning with geostatistical methods for geological modeling, providing a robust framework for future applications in geosciences. The flexibility of our approach also suggests its applicability to other regions and geological attributes, paving the way for more comprehensive and data-driven investigations of Earth’s subsurface.
- Open Access
- 6 June 2022
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 9 (6)
Extended GOSIM: MPS‐Driven Simulation of 3D Geological Structure Using 2D Cross‐Sections
In the past two decades, algorithms for multiple‐point statistics (MPS) have been applied in many fields. However, 3D training datum or data (TD) is difficult to be obtained. Two‐dimensional geological cross‐sections from boreholes or geophysical data with high reliability are usually used to explain geological phenomena and are relatively easier to be acquired. In this study, a step‐wise algorithm that combines sequential process and global optimization is presented. Constructing 3D TD set and corresponding pattern databases that extended from 2D cross‐sections at each scale is one of the key steps after presetting the simulation parameters. The following step is constructing an initial model at the coarsest scale with the pattern databases. The iterative Expectation Maximum‐like (EM‐like) optimization process is implemented to obtain the final realization. Each iteration is conducted with a multiscale strategy. Simulation examples of the regional geological structures show that the stratigraphic sequence can be reasonably kept and reproduced. Also, the randomness and effectiveness of the microstructure model are verified by calculating the proportion of grains, fractal dimension and the curve of two‐point connectivity probability function.
- 6 June 2022
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 9 (6)
Open AccessExtended GOSIM: MPS‐Driven Simulation of 3D Geological Structure Using 2D Cross‐Sections
In the past two decades, algorithms for multiple‐point statistics (MPS) have been applied in many fields. However, 3D training datum or data (TD) is difficult to be obtained. Two‐dimensional geological cross‐sections from boreholes or geophysical data with high reliability are usually used to explain geological phenomena and are relatively easier to be acquired. In this study, a step‐wise algorithm that combines sequential process and global optimization is presented. Constructing 3D TD set and corresponding pattern databases that extended from 2D cross‐sections at each scale is one of the key steps after presetting the simulation parameters. The following step is constructing an initial model at the coarsest scale with the pattern databases. The iterative Expectation Maximum‐like (EM‐like) optimization process is implemented to obtain the final realization. Each iteration is conducted with a multiscale strategy. Simulation examples of the regional geological structures show that the stratigraphic sequence can be reasonably kept and reproduced. Also, the randomness and effectiveness of the microstructure model are verified by calculating the proportion of grains, fractal dimension and the curve of two‐point connectivity probability function.