Simultaneous estimation of basement depth and density contrast by gravity anomaly via multi-task deep learning
文献类型：期刊论文
| 作者 | Wang, Lin3; Florio, Giovanni5; Fedi, Maurizio5; Xiong, Shengqing2; Wang, Wanyin1,3,4 |
| 刊名 | JOURNAL OF APPLIED GEOPHYSICS
 |
| 出版日期 | 2025-09-01 |
| 卷号 | 240页码:13 |
| 关键词 | Basement modeling Machine learning Inversion Gravity anomaly |
| ISSN号 | 0926-9851 |
| DOI | 10.1016/j.jappgeo.2025.105781 |
| 通讯作者 | Xiong, Shengqing(xsqagrs@126.com) |
| 英文摘要 | We propose a multi-task deep learning (DL) method to simultaneously estimate the basement depth and the density contrast from gravity field anomalies. The method is based on a specially designed hybrid architecture, which comprises a convolutional neural network branch and a Multilayer Perceptron branch. This hybrid architecture fully leverages the benefits of multi-task DL, enabling simultaneous estimation of basement depth and density contrast, where the input is a gravity map. In the training phase, useful statistical prior information is incorporated from a global basin dataset. Our idea is that the learning based on such dataset helps to restrict the solution to a limited domain, so leading to a reasonable estimation of the basement depth and the density contrast. We utilize a Deep Convolutional Generative Adversarial Network (DCGAN) to generate high-quality maps of basement depths based on a global catalog of basins. The preliminary real basement maps originate from the reinterpolations and nonstandard coordinate transformations of the sediment data inside the global basins, and more additional basement samples are generated by the trained DCGAN architecture, thereby forming our dataset. We apply the method to synthetic dataset and to two real cases, thus demonstrating the feasibility and effectiveness of our DL method. The results show good performance of our DL architecture not only for the estimated basement models, but also for the density contrast. The method candidates as a valid tool for practical applications, especially when there is a lack of constraint information in complex real cases. |
| WOS关键词 | TO-BASEMENT ; INVERSION ; RELIEF ; RIFT |
| 资助项目 | Scientific and Technological Project of China National Offshore Oil Corporation (CNOOC) Research Institute Co., Ltd.[CCL2021RCPS0167KQN] ; China Scholarship Council |
| WOS研究方向 | Geology ; Mining & Mineral Processing |
| 语种 | 英语 |
| WOS记录号 | WOS:001500340700001 |
| 出版者 | ELSEVIER |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/202154]  |
| 专题 | 海洋研究所_海洋地质与环境重点实验室 |
| 通讯作者 | Xiong, Shengqing |
| 作者单位 | 1.Chinese Acad Sci, Inst Oceanol, Key Lab Marine Geol & Environm, Qingdao 266071, Peoples R China 2.China AeroGeophys Survey & Remote Sensing Ctr Nat, Beijing 100083, Peoples R China 3.Changan Univ, Sch Geol Engn & Geomat, Xian 710054, Peoples R China 4.Natl Engn Res Ctr Offshore Oil & Gas Explorat, Beijing 100028, Peoples R China 5.Univ Napoli Federico II, Dipartimento Sci Terra Ambiente & Risorse, I-80126 Naples, Italy |
| 推荐引用方式 GB/T 7714 | Wang, Lin,Florio, Giovanni,Fedi, Maurizio,et al. Simultaneous estimation of basement depth and density contrast by gravity anomaly via multi-task deep learning[J]. JOURNAL OF APPLIED GEOPHYSICS,2025,240:13. |
| APA | Wang, Lin,Florio, Giovanni,Fedi, Maurizio,Xiong, Shengqing,&Wang, Wanyin.(2025).Simultaneous estimation of basement depth and density contrast by gravity anomaly via multi-task deep learning.JOURNAL OF APPLIED GEOPHYSICS,240,13. |
| MLA | Wang, Lin,et al."Simultaneous estimation of basement depth and density contrast by gravity anomaly via multi-task deep learning".JOURNAL OF APPLIED GEOPHYSICS 240(2025):13. |
入库方式： OAI收割
来源：海洋研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。