Microseismic moment tensor inversion based on ResNet model

This paper proposed a moment tensor regression prediction technology based on ResNet for microseismic events. Taking the great advantages of deep networks in classification and regression tasks, it can realize the great potential of fast and accurate inversion of microseismic moment tensors after th...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiaqi Yan, Li Ma, Tianqi Jiang, Jing Zheng, Dewei Li, Xingzhi Teng
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2025-06-01
Series:Artificial Intelligence in Geosciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666544125000036
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849430803574947840
author Jiaqi Yan
Li Ma
Tianqi Jiang
Jing Zheng
Dewei Li
Xingzhi Teng
author_facet Jiaqi Yan
Li Ma
Tianqi Jiang
Jing Zheng
Dewei Li
Xingzhi Teng
author_sort Jiaqi Yan
collection DOAJ
description This paper proposed a moment tensor regression prediction technology based on ResNet for microseismic events. Taking the great advantages of deep networks in classification and regression tasks, it can realize the great potential of fast and accurate inversion of microseismic moment tensors after the network trained. This ResNet-based moment tensor prediction technology, whose input is raw recordings, does not require the extraction of data features in advance. First, we tested the network using synthetic data and performed a quantitative assessment of the errors. The results demonstrate that the network exhibits high accuracy and efficiency during the prediction phase. Next, we tested the network using real microseismic data and compared the results with those from traditional inversion methods. The error in the results was relatively small compared to traditional methods. However, the network operates more efficiently without requiring manual intervention, making it highly valuable for near-real-time monitoring applications.
format Article
id doaj-art-54ec7979735a4989bc8afde4a6e5b9be
institution Kabale University
issn 2666-5441
language English
publishDate 2025-06-01
publisher KeAi Communications Co. Ltd.
record_format Article
series Artificial Intelligence in Geosciences
spelling doaj-art-54ec7979735a4989bc8afde4a6e5b9be2025-08-20T03:27:51ZengKeAi Communications Co. Ltd.Artificial Intelligence in Geosciences2666-54412025-06-016110010710.1016/j.aiig.2025.100107Microseismic moment tensor inversion based on ResNet modelJiaqi Yan0Li Ma1Tianqi Jiang2Jing Zheng3Dewei Li4Xingzhi Teng5Key Laboratory of Coal Resources Exploration and Comprehensive Utilization, Ministry of Natural Resources, Xi’an, Shaanxi, 710021, China; College of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing, 100083, ChinaKey Laboratory of Coal Resources Exploration and Comprehensive Utilization, Ministry of Natural Resources, Xi’an, Shaanxi, 710021, ChinaState Key Laboratory for Fine Exploration and Intelligent Development of Coal Resources, China University of Mining and Technology-Beijing, Beijing, 100083, China; China Coal Technology and Engineering Group Shenyang Research Institute, Fushun Liaoning, Liaoning, 113122, China; Corresponding author at: China Coal Technology and Engineering Group Shenyang Research Institute, Fushun Liaoning, Liaoning, 113122, China.College of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing, 100083, China; State Key Laboratory for Fine Exploration and Intelligent Development of Coal Resources, China University of Mining and Technology-Beijing, Beijing, 100083, ChinaSchool of Earth Sciences, Zhejiang University, Hangzhou, 310058, Zhejiang, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing, 100083, ChinaThis paper proposed a moment tensor regression prediction technology based on ResNet for microseismic events. Taking the great advantages of deep networks in classification and regression tasks, it can realize the great potential of fast and accurate inversion of microseismic moment tensors after the network trained. This ResNet-based moment tensor prediction technology, whose input is raw recordings, does not require the extraction of data features in advance. First, we tested the network using synthetic data and performed a quantitative assessment of the errors. The results demonstrate that the network exhibits high accuracy and efficiency during the prediction phase. Next, we tested the network using real microseismic data and compared the results with those from traditional inversion methods. The error in the results was relatively small compared to traditional methods. However, the network operates more efficiently without requiring manual intervention, making it highly valuable for near-real-time monitoring applications.http://www.sciencedirect.com/science/article/pii/S2666544125000036MicroseismicResNetMoment tensorRegression
spellingShingle Jiaqi Yan
Li Ma
Tianqi Jiang
Jing Zheng
Dewei Li
Xingzhi Teng
Microseismic moment tensor inversion based on ResNet model
Artificial Intelligence in Geosciences
Microseismic
ResNet
Moment tensor
Regression
title Microseismic moment tensor inversion based on ResNet model
title_full Microseismic moment tensor inversion based on ResNet model
title_fullStr Microseismic moment tensor inversion based on ResNet model
title_full_unstemmed Microseismic moment tensor inversion based on ResNet model
title_short Microseismic moment tensor inversion based on ResNet model
title_sort microseismic moment tensor inversion based on resnet model
topic Microseismic
ResNet
Moment tensor
Regression
url http://www.sciencedirect.com/science/article/pii/S2666544125000036
work_keys_str_mv AT jiaqiyan microseismicmomenttensorinversionbasedonresnetmodel
AT lima microseismicmomenttensorinversionbasedonresnetmodel
AT tianqijiang microseismicmomenttensorinversionbasedonresnetmodel
AT jingzheng microseismicmomenttensorinversionbasedonresnetmodel
AT deweili microseismicmomenttensorinversionbasedonresnetmodel
AT xingzhiteng microseismicmomenttensorinversionbasedonresnetmodel