|
|||||
|
|
| 瞬变电磁长短时记忆网络深度学习实时反演方法 | |
| 引用本文： | 范涛, 薛国强, 李萍, 燕斌, 鲍亮, 宋金秋, 任笑, 李泽林. 2022. 瞬变电磁长短时记忆网络深度学习实时反演方法. 地球物理学报, 65(9): 3650-3663, doi: 10.6038/cjg2022P0572 |
| 作者姓名： | 范涛 薛国强 李萍 燕斌 鲍亮 宋金秋 任笑 李泽林 |
| 作者单位： | 1. 中煤科工西安研究院(集团)有限公司, 西安 710077; 2. 中国科学院地质与地球物理研究所 中国科学院矿产资源研究重点实验室, 北京 100029; 3. 西安电子科技大学计算机科学与技术学院, 西安 710071 |
| 基金项目： | 陕西省自然科学基础研究计划重点项目（2022JZ-16），天地科技股份有限公司科技创新创业资金专项项目顶层设计重点项目（2020-TD-ZD003），天地科技股份有限公司科技创新创业资金专项面上项目（2022-2-TD-MS006），国家自然科学基金重点项目（42030106）资助 |
| 摘 要： |  瞬变电磁一维反演方法对初始模型依赖大，对异常体边界反映不清晰，计算速度也难以达到实时化水平.为此，本文开展基于深度学习的瞬变电磁实时反演方法研究，提出在非观测时间段进行反演训练，而在观测时间段进行实时精细成像的瞬变电磁长短时记忆网络反演策略.  |
| 关 键 词： | 瞬变电磁法 长短时记忆网络 精细反演 地电边界 实时成像 |
| 收稿时间： | 2021-08-09 |
| 修稿时间： | 2022-06-09 |
TEM real-time inversion based on long-short term memory network |
|
| FAN Tao, XUE GuoQiang, LI Ping, YAN Bin, BAO Liang, SONG JinQiu, REN Xiao, LI ZeLin. 2022. TEM real-time inversion based on long-short term memory network. Chinese Journal of Geophysics (in Chinese), 65(9): 3650-3663, doi: 10.6038/cjg2022P0572 | |
| Authors: | FAN Tao XUE GuoQiang LI Ping YAN Bin BAO Liang SONG JinQiu REN Xiao LI ZeLin |
| Affiliation: | 1. CCTEG XI'an Research Institute (Group) Co., Ltd, Xi'an 710077, China; 2. Key Laboratory of Mineral Resources, Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, China; 3. School of Computer Science and Technology, XiDian University, Xi'an 710071, China |
| Abstract: | 1D transient electromagnetic (TEM) inversion method relies heavily on initial model, which lead to unclear boundaries, of anomaly body, and the inversion speed is difficult to reach the real-time level. Hence, the long-short term network(LSTM) of TEM real-time inversion method based on deep learning has been proposed. The inversion can be carried out during non-observational time periods, while real-time fine imaging can be finished during the observation time period. Taking the massive sampling time-vs resistivity data as the input file, the Encoder-Decoder model in Seq2seq model is adopted, according to the characteristics of transient electromagnetic inversion, the structure of decoder is adaptively changed, and Bahdanau Attention mechanism is added to highlight the role of key information.  At last, the output data of depth vs resistivity is produced. We applied the inversion network to tens of thousands of three layers and five layers geoelectric model which generated randomly, the test group's three measure standard deviation are all less than 10%, the reliability of the algorithm in this paper was validated, on this basis, 2 groups of near-actual model containing local abnormal body were built, the inversion of network further used in 3D numerical simulation data. The imaging results reflecting the abnormal body boundary clearly, and the computational velocity is less than 1 s. |
| Keywords: | Transient electromagnetic method Long-short term memory network Inversion Boundary Real-time |
| 点击此处可从《地球物理学报》浏览原始摘要信息 | |
| 点击此处可从《地球物理学报》下载全文 | |