A prototype-based rockburst types and risk prediction algorithm considering intra-class variance and inter-class distance of microseismic data

The prediction and classification of rockburst risk based on microseismic data is the premise of preventing rockbursts during deep mine excavation. By reviewing previous studies, this paper finds two problems that hinder the rockburst prediction: 1) there is a lack of research on the distribution fe...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiufeng Zhang, Guoying Li, Yang Chen, Hao Wang, Haikuan Zhang, Haitao Li, Weisheng Du, Xiao Li, Xuewei Xu, Yuze He
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Earth Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/feart.2025.1601090/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849689224495759360
author Xiufeng Zhang
Guoying Li
Yang Chen
Hao Wang
Haikuan Zhang
Haitao Li
Weisheng Du
Xiao Li
Xuewei Xu
Yuze He
author_facet Xiufeng Zhang
Guoying Li
Yang Chen
Hao Wang
Haikuan Zhang
Haitao Li
Weisheng Du
Xiao Li
Xuewei Xu
Yuze He
author_sort Xiufeng Zhang
collection DOAJ
description The prediction and classification of rockburst risk based on microseismic data is the premise of preventing rockbursts during deep mine excavation. By reviewing previous studies, this paper finds two problems that hinder the rockburst prediction: 1) there is a lack of research on the distribution features of monitoring data on the main controlling factors of rockbursts; 2) there is no research on the intra-class variance and inter-class gap of microseismic data. Based on the typical rockburst risk events, a quantitative information model of geology and mining is constructed. The relationship between the spatial–temporal distribution characteristics of microseismic data before a rockburst and the main controlling factors of a rockburst is studied. The results show that the distribution features may be different for the same type of microseismic (MS) and rockburst events, and different types of events may show similar distribution features. Therefore, based on the quantitative study of the relationship between the performance of a deep learning prediction algorithm and a rockburst prediction vector, a rockburst risk and type prediction algorithm based on a convolutional neural network (CNN)-gated recurrent unit (GRU) model with prototype-based prediction is proposed. The CNN-GRU model can produce prediction vectors by fusing implicit and explicit information extracted from the original MS data and early warning indicators. Cross-entropy loss, vector-prototype contrastive loss, and vector-prototype contrastive loss are proposed to automatically control the intra-class variance and inter-class gap of prediction vectors belonging to different rockburst risks and types. Many experiments show that the performance of the proposed CNN-GRU model with prototype-based prediction is superior to other algorithms in the prediction of rockburst risks and types based on MS data.
format Article
id doaj-art-8907151db42244d084ee00c8f343f829
institution DOAJ
issn 2296-6463
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Earth Science
spelling doaj-art-8907151db42244d084ee00c8f343f8292025-08-20T03:21:42ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632025-05-011310.3389/feart.2025.16010901601090A prototype-based rockburst types and risk prediction algorithm considering intra-class variance and inter-class distance of microseismic dataXiufeng Zhang0Guoying Li1Yang Chen2Hao Wang3Haikuan Zhang4Haitao Li5Weisheng Du6Xiao Li7Xuewei Xu8Yuze He9Coal Industry Management Department, Shandong Energy Group Co., Ltd., Jinan, Shandong, ChinaCoal Industry Management Department, Shandong Energy Group Co., Ltd., Jinan, Shandong, ChinaCoal Industry Management Department, Shandong Energy Group Co., Ltd., Jinan, Shandong, ChinaCoal Industry Management Department, Shandong Energy Group Co., Ltd., Jinan, Shandong, ChinaDeep Mining and Rock Burst Research Branch, Chinese Institute of Coal Science, Beijing, ChinaDeep Mining and Rock Burst Research Branch, Chinese Institute of Coal Science, Beijing, ChinaDeep Mining and Rock Burst Research Branch, Chinese Institute of Coal Science, Beijing, ChinaDeep Mining and Rock Burst Research Branch, Chinese Institute of Coal Science, Beijing, ChinaDeep Mining and Rock Burst Research Branch, Chinese Institute of Coal Science, Beijing, ChinaDeep Mining and Rock Burst Research Branch, Chinese Institute of Coal Science, Beijing, ChinaThe prediction and classification of rockburst risk based on microseismic data is the premise of preventing rockbursts during deep mine excavation. By reviewing previous studies, this paper finds two problems that hinder the rockburst prediction: 1) there is a lack of research on the distribution features of monitoring data on the main controlling factors of rockbursts; 2) there is no research on the intra-class variance and inter-class gap of microseismic data. Based on the typical rockburst risk events, a quantitative information model of geology and mining is constructed. The relationship between the spatial–temporal distribution characteristics of microseismic data before a rockburst and the main controlling factors of a rockburst is studied. The results show that the distribution features may be different for the same type of microseismic (MS) and rockburst events, and different types of events may show similar distribution features. Therefore, based on the quantitative study of the relationship between the performance of a deep learning prediction algorithm and a rockburst prediction vector, a rockburst risk and type prediction algorithm based on a convolutional neural network (CNN)-gated recurrent unit (GRU) model with prototype-based prediction is proposed. The CNN-GRU model can produce prediction vectors by fusing implicit and explicit information extracted from the original MS data and early warning indicators. Cross-entropy loss, vector-prototype contrastive loss, and vector-prototype contrastive loss are proposed to automatically control the intra-class variance and inter-class gap of prediction vectors belonging to different rockburst risks and types. Many experiments show that the performance of the proposed CNN-GRU model with prototype-based prediction is superior to other algorithms in the prediction of rockburst risks and types based on MS data.https://www.frontiersin.org/articles/10.3389/feart.2025.1601090/fullrockburst predictionrockburst typesdeep learningmicroseismic dataprototype learning
spellingShingle Xiufeng Zhang
Guoying Li
Yang Chen
Hao Wang
Haikuan Zhang
Haitao Li
Weisheng Du
Xiao Li
Xuewei Xu
Yuze He
A prototype-based rockburst types and risk prediction algorithm considering intra-class variance and inter-class distance of microseismic data
Frontiers in Earth Science
rockburst prediction
rockburst types
deep learning
microseismic data
prototype learning
title A prototype-based rockburst types and risk prediction algorithm considering intra-class variance and inter-class distance of microseismic data
title_full A prototype-based rockburst types and risk prediction algorithm considering intra-class variance and inter-class distance of microseismic data
title_fullStr A prototype-based rockburst types and risk prediction algorithm considering intra-class variance and inter-class distance of microseismic data
title_full_unstemmed A prototype-based rockburst types and risk prediction algorithm considering intra-class variance and inter-class distance of microseismic data
title_short A prototype-based rockburst types and risk prediction algorithm considering intra-class variance and inter-class distance of microseismic data
title_sort prototype based rockburst types and risk prediction algorithm considering intra class variance and inter class distance of microseismic data
topic rockburst prediction
rockburst types
deep learning
microseismic data
prototype learning
url https://www.frontiersin.org/articles/10.3389/feart.2025.1601090/full
work_keys_str_mv AT xiufengzhang aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT guoyingli aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT yangchen aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT haowang aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT haikuanzhang aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT haitaoli aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT weishengdu aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT xiaoli aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT xueweixu aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT yuzehe aprototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT xiufengzhang prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT guoyingli prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT yangchen prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT haowang prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT haikuanzhang prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT haitaoli prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT weishengdu prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT xiaoli prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT xueweixu prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata
AT yuzehe prototypebasedrockbursttypesandriskpredictionalgorithmconsideringintraclassvarianceandinterclassdistanceofmicroseismicdata