Loading…

Rockburst Intensity Grade Prediction Based on Data Preprocessing Techniques and Multi-model Ensemble Learning Algorithms

Rockburst is a mine dynamic disaster caused by the rapid release of elastic strain energy of surrounding rock. As the depth of engineering project operations increases, accurate classification of rockburst intensity cannot be achieved based on conventional criteria due to high uncertainty and unpred...

Full description

Saved in:
Bibliographic Details
Published in:Rock mechanics and rock engineering 2024-07, Vol.57 (7), p.5207-5227
Main Authors: Jia, Zhi-Chao, Wang, Yi, Wang, Jun-Hui, Pei, Qiu-Yan, Zhang, Yan-Qi
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c319t-877f0d675507d218f7807827a504dcdc59cbe8afd16541e4fa3ae9c2451ed89b3
cites cdi_FETCH-LOGICAL-c319t-877f0d675507d218f7807827a504dcdc59cbe8afd16541e4fa3ae9c2451ed89b3
container_end_page 5227
container_issue 7
container_start_page 5207
container_title Rock mechanics and rock engineering
container_volume 57
creator Jia, Zhi-Chao
Wang, Yi
Wang, Jun-Hui
Pei, Qiu-Yan
Zhang, Yan-Qi
description Rockburst is a mine dynamic disaster caused by the rapid release of elastic strain energy of surrounding rock. As the depth of engineering project operations increases, accurate classification of rockburst intensity cannot be achieved based on conventional criteria due to high uncertainty and unpredictability of rockburst. In this regard, an AOA-Voting-Soft ensemble machine learning was proposed in this study by combining seven individual classifiers, i.e., eXtreme gradient boosting, support vector machines, multilayer perceptron, k -nearest neighbor, random forest, naive Bayesian, and gradient boosting decision Tree. In addition, outliers were eliminated by means of density-based spatial clustering of applications with noise, and CURE-MeanradiusSMOTE was adopted to obtain a balanced data structure. Furthermore, the optimal combination of classifiers in Voting was determined by the game theory and the exhaustive search method. Weights of individual learners in Voting were determined through the arithmetic optimization algorithm and fivefold cross-validation. The results show that the prediction accuracy of the ensemble algorithm proposed in this study is 4.4% higher than that of the individual classifier with optimal performance. The importance analysis indicates that the elastic energy index is the most important variable that affects rockburst intensity grades. Moreover, this rockburst ensemble method can be applied further to solve other classification problems in underground engineering projects. Highlights This study improves the data preprocessing method, outliers were eliminated by means of density-based spatial clustering of applications with noise, and CURE-MeanradiusSMOTE was proposed to obtain a balanced data structure. This study presents a hybrid ensemble model for Rockburst intensity grade prediction, combining a new metaheuristic method with the Voting-Soft model. This study combines game theory and method of exhaustion to determine the best classifier combination in voting. The weights of individual learners in Voting were determined through arithmetic optimization algorithm and fivefold cross-validation. Sensitivity study was conducted on input variables with RBD-FAST, and the results suggest that W et is the most important input variable.
doi_str_mv 10.1007/s00603-024-03811-y
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3078183929</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3078183929</sourcerecordid><originalsourceid>FETCH-LOGICAL-c319t-877f0d675507d218f7807827a504dcdc59cbe8afd16541e4fa3ae9c2451ed89b3</originalsourceid><addsrcrecordid>eNp9kE9LAzEQxYMoWKtfwFPAczR_dpvssVathYoiFbyFNJltt26zNUnBfntTK3jzNAPz3pvHD6FLRq8ZpfImUjqgglBeECoUY2R3hHqsEAUpSvF-jHpUckH4QPBTdBbjitJ8lKqHvl47-zHfhpjwxCfwsUk7PA7GAX4J4Bqbms7jWxPB4bzcmWT2h03oLMTY-AWegV365nMLERvv8NO2TQ1Zdw5afO8jrOct4CmY4PfiYbvoQpOW63iOTmrTRrj4nX309nA_Gz2S6fN4MhpOiRWsSkRJWVM3kGVJpeNM1VJRqbg0JS2cdbas7ByUqR0blAWDojbCQGV5UTJwqpqLPro65ObK-5JJr7pt8PmlFjmJKVHxKqv4QWVDF2OAWm9CszZhpxnVe8L6QFhnwvqHsN5lkziYYhb7BYS_6H9c3-7MgLk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3078183929</pqid></control><display><type>article</type><title>Rockburst Intensity Grade Prediction Based on Data Preprocessing Techniques and Multi-model Ensemble Learning Algorithms</title><source>Springer Nature</source><creator>Jia, Zhi-Chao ; Wang, Yi ; Wang, Jun-Hui ; Pei, Qiu-Yan ; Zhang, Yan-Qi</creator><creatorcontrib>Jia, Zhi-Chao ; Wang, Yi ; Wang, Jun-Hui ; Pei, Qiu-Yan ; Zhang, Yan-Qi</creatorcontrib><description>Rockburst is a mine dynamic disaster caused by the rapid release of elastic strain energy of surrounding rock. As the depth of engineering project operations increases, accurate classification of rockburst intensity cannot be achieved based on conventional criteria due to high uncertainty and unpredictability of rockburst. In this regard, an AOA-Voting-Soft ensemble machine learning was proposed in this study by combining seven individual classifiers, i.e., eXtreme gradient boosting, support vector machines, multilayer perceptron, k -nearest neighbor, random forest, naive Bayesian, and gradient boosting decision Tree. In addition, outliers were eliminated by means of density-based spatial clustering of applications with noise, and CURE-MeanradiusSMOTE was adopted to obtain a balanced data structure. Furthermore, the optimal combination of classifiers in Voting was determined by the game theory and the exhaustive search method. Weights of individual learners in Voting were determined through the arithmetic optimization algorithm and fivefold cross-validation. The results show that the prediction accuracy of the ensemble algorithm proposed in this study is 4.4% higher than that of the individual classifier with optimal performance. The importance analysis indicates that the elastic energy index is the most important variable that affects rockburst intensity grades. Moreover, this rockburst ensemble method can be applied further to solve other classification problems in underground engineering projects. Highlights This study improves the data preprocessing method, outliers were eliminated by means of density-based spatial clustering of applications with noise, and CURE-MeanradiusSMOTE was proposed to obtain a balanced data structure. This study presents a hybrid ensemble model for Rockburst intensity grade prediction, combining a new metaheuristic method with the Voting-Soft model. This study combines game theory and method of exhaustion to determine the best classifier combination in voting. The weights of individual learners in Voting were determined through arithmetic optimization algorithm and fivefold cross-validation. Sensitivity study was conducted on input variables with RBD-FAST, and the results suggest that W et is the most important input variable.</description><identifier>ISSN: 0723-2632</identifier><identifier>EISSN: 1434-453X</identifier><identifier>DOI: 10.1007/s00603-024-03811-y</identifier><language>eng</language><publisher>Vienna: Springer Vienna</publisher><subject>Algorithms ; Arithmetic ; Bayesian analysis ; Civil Engineering ; Classification ; Clustering ; Data analysis ; Data structures ; Decision trees ; Density ; Earth and Environmental Science ; Earth Sciences ; Elastic analysis ; Ensemble learning ; Game theory ; Geophysics/Geodesy ; Heuristic methods ; Machine learning ; Mathematical analysis ; Multilayer perceptrons ; Noise prediction ; Optimization ; Optimization algorithms ; Original Paper ; Outliers (landforms) ; Outliers (statistics) ; Predictions ; Preprocessing ; Probability theory ; Quality ; Rockbursts ; Spatial data ; Strain energy ; Underground structures</subject><ispartof>Rock mechanics and rock engineering, 2024-07, Vol.57 (7), p.5207-5227</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c319t-877f0d675507d218f7807827a504dcdc59cbe8afd16541e4fa3ae9c2451ed89b3</citedby><cites>FETCH-LOGICAL-c319t-877f0d675507d218f7807827a504dcdc59cbe8afd16541e4fa3ae9c2451ed89b3</cites><orcidid>0009-0004-9212-0700</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Jia, Zhi-Chao</creatorcontrib><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Wang, Jun-Hui</creatorcontrib><creatorcontrib>Pei, Qiu-Yan</creatorcontrib><creatorcontrib>Zhang, Yan-Qi</creatorcontrib><title>Rockburst Intensity Grade Prediction Based on Data Preprocessing Techniques and Multi-model Ensemble Learning Algorithms</title><title>Rock mechanics and rock engineering</title><addtitle>Rock Mech Rock Eng</addtitle><description>Rockburst is a mine dynamic disaster caused by the rapid release of elastic strain energy of surrounding rock. As the depth of engineering project operations increases, accurate classification of rockburst intensity cannot be achieved based on conventional criteria due to high uncertainty and unpredictability of rockburst. In this regard, an AOA-Voting-Soft ensemble machine learning was proposed in this study by combining seven individual classifiers, i.e., eXtreme gradient boosting, support vector machines, multilayer perceptron, k -nearest neighbor, random forest, naive Bayesian, and gradient boosting decision Tree. In addition, outliers were eliminated by means of density-based spatial clustering of applications with noise, and CURE-MeanradiusSMOTE was adopted to obtain a balanced data structure. Furthermore, the optimal combination of classifiers in Voting was determined by the game theory and the exhaustive search method. Weights of individual learners in Voting were determined through the arithmetic optimization algorithm and fivefold cross-validation. The results show that the prediction accuracy of the ensemble algorithm proposed in this study is 4.4% higher than that of the individual classifier with optimal performance. The importance analysis indicates that the elastic energy index is the most important variable that affects rockburst intensity grades. Moreover, this rockburst ensemble method can be applied further to solve other classification problems in underground engineering projects. Highlights This study improves the data preprocessing method, outliers were eliminated by means of density-based spatial clustering of applications with noise, and CURE-MeanradiusSMOTE was proposed to obtain a balanced data structure. This study presents a hybrid ensemble model for Rockburst intensity grade prediction, combining a new metaheuristic method with the Voting-Soft model. This study combines game theory and method of exhaustion to determine the best classifier combination in voting. The weights of individual learners in Voting were determined through arithmetic optimization algorithm and fivefold cross-validation. Sensitivity study was conducted on input variables with RBD-FAST, and the results suggest that W et is the most important input variable.</description><subject>Algorithms</subject><subject>Arithmetic</subject><subject>Bayesian analysis</subject><subject>Civil Engineering</subject><subject>Classification</subject><subject>Clustering</subject><subject>Data analysis</subject><subject>Data structures</subject><subject>Decision trees</subject><subject>Density</subject><subject>Earth and Environmental Science</subject><subject>Earth Sciences</subject><subject>Elastic analysis</subject><subject>Ensemble learning</subject><subject>Game theory</subject><subject>Geophysics/Geodesy</subject><subject>Heuristic methods</subject><subject>Machine learning</subject><subject>Mathematical analysis</subject><subject>Multilayer perceptrons</subject><subject>Noise prediction</subject><subject>Optimization</subject><subject>Optimization algorithms</subject><subject>Original Paper</subject><subject>Outliers (landforms)</subject><subject>Outliers (statistics)</subject><subject>Predictions</subject><subject>Preprocessing</subject><subject>Probability theory</subject><subject>Quality</subject><subject>Rockbursts</subject><subject>Spatial data</subject><subject>Strain energy</subject><subject>Underground structures</subject><issn>0723-2632</issn><issn>1434-453X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kE9LAzEQxYMoWKtfwFPAczR_dpvssVathYoiFbyFNJltt26zNUnBfntTK3jzNAPz3pvHD6FLRq8ZpfImUjqgglBeECoUY2R3hHqsEAUpSvF-jHpUckH4QPBTdBbjitJ8lKqHvl47-zHfhpjwxCfwsUk7PA7GAX4J4Bqbms7jWxPB4bzcmWT2h03oLMTY-AWegV365nMLERvv8NO2TQ1Zdw5afO8jrOct4CmY4PfiYbvoQpOW63iOTmrTRrj4nX309nA_Gz2S6fN4MhpOiRWsSkRJWVM3kGVJpeNM1VJRqbg0JS2cdbas7ByUqR0blAWDojbCQGV5UTJwqpqLPro65ObK-5JJr7pt8PmlFjmJKVHxKqv4QWVDF2OAWm9CszZhpxnVe8L6QFhnwvqHsN5lkziYYhb7BYS_6H9c3-7MgLk</recordid><startdate>20240701</startdate><enddate>20240701</enddate><creator>Jia, Zhi-Chao</creator><creator>Wang, Yi</creator><creator>Wang, Jun-Hui</creator><creator>Pei, Qiu-Yan</creator><creator>Zhang, Yan-Qi</creator><general>Springer Vienna</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7TN</scope><scope>7UA</scope><scope>8FD</scope><scope>C1K</scope><scope>F1W</scope><scope>FR3</scope><scope>H96</scope><scope>KR7</scope><scope>L.G</scope><orcidid>https://orcid.org/0009-0004-9212-0700</orcidid></search><sort><creationdate>20240701</creationdate><title>Rockburst Intensity Grade Prediction Based on Data Preprocessing Techniques and Multi-model Ensemble Learning Algorithms</title><author>Jia, Zhi-Chao ; Wang, Yi ; Wang, Jun-Hui ; Pei, Qiu-Yan ; Zhang, Yan-Qi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c319t-877f0d675507d218f7807827a504dcdc59cbe8afd16541e4fa3ae9c2451ed89b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Arithmetic</topic><topic>Bayesian analysis</topic><topic>Civil Engineering</topic><topic>Classification</topic><topic>Clustering</topic><topic>Data analysis</topic><topic>Data structures</topic><topic>Decision trees</topic><topic>Density</topic><topic>Earth and Environmental Science</topic><topic>Earth Sciences</topic><topic>Elastic analysis</topic><topic>Ensemble learning</topic><topic>Game theory</topic><topic>Geophysics/Geodesy</topic><topic>Heuristic methods</topic><topic>Machine learning</topic><topic>Mathematical analysis</topic><topic>Multilayer perceptrons</topic><topic>Noise prediction</topic><topic>Optimization</topic><topic>Optimization algorithms</topic><topic>Original Paper</topic><topic>Outliers (landforms)</topic><topic>Outliers (statistics)</topic><topic>Predictions</topic><topic>Preprocessing</topic><topic>Probability theory</topic><topic>Quality</topic><topic>Rockbursts</topic><topic>Spatial data</topic><topic>Strain energy</topic><topic>Underground structures</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jia, Zhi-Chao</creatorcontrib><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Wang, Jun-Hui</creatorcontrib><creatorcontrib>Pei, Qiu-Yan</creatorcontrib><creatorcontrib>Zhang, Yan-Qi</creatorcontrib><collection>CrossRef</collection><collection>Oceanic Abstracts</collection><collection>Water Resources Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Engineering Research Database</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>Civil Engineering Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><jtitle>Rock mechanics and rock engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jia, Zhi-Chao</au><au>Wang, Yi</au><au>Wang, Jun-Hui</au><au>Pei, Qiu-Yan</au><au>Zhang, Yan-Qi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Rockburst Intensity Grade Prediction Based on Data Preprocessing Techniques and Multi-model Ensemble Learning Algorithms</atitle><jtitle>Rock mechanics and rock engineering</jtitle><stitle>Rock Mech Rock Eng</stitle><date>2024-07-01</date><risdate>2024</risdate><volume>57</volume><issue>7</issue><spage>5207</spage><epage>5227</epage><pages>5207-5227</pages><issn>0723-2632</issn><eissn>1434-453X</eissn><abstract>Rockburst is a mine dynamic disaster caused by the rapid release of elastic strain energy of surrounding rock. As the depth of engineering project operations increases, accurate classification of rockburst intensity cannot be achieved based on conventional criteria due to high uncertainty and unpredictability of rockburst. In this regard, an AOA-Voting-Soft ensemble machine learning was proposed in this study by combining seven individual classifiers, i.e., eXtreme gradient boosting, support vector machines, multilayer perceptron, k -nearest neighbor, random forest, naive Bayesian, and gradient boosting decision Tree. In addition, outliers were eliminated by means of density-based spatial clustering of applications with noise, and CURE-MeanradiusSMOTE was adopted to obtain a balanced data structure. Furthermore, the optimal combination of classifiers in Voting was determined by the game theory and the exhaustive search method. Weights of individual learners in Voting were determined through the arithmetic optimization algorithm and fivefold cross-validation. The results show that the prediction accuracy of the ensemble algorithm proposed in this study is 4.4% higher than that of the individual classifier with optimal performance. The importance analysis indicates that the elastic energy index is the most important variable that affects rockburst intensity grades. Moreover, this rockburst ensemble method can be applied further to solve other classification problems in underground engineering projects. Highlights This study improves the data preprocessing method, outliers were eliminated by means of density-based spatial clustering of applications with noise, and CURE-MeanradiusSMOTE was proposed to obtain a balanced data structure. This study presents a hybrid ensemble model for Rockburst intensity grade prediction, combining a new metaheuristic method with the Voting-Soft model. This study combines game theory and method of exhaustion to determine the best classifier combination in voting. The weights of individual learners in Voting were determined through arithmetic optimization algorithm and fivefold cross-validation. Sensitivity study was conducted on input variables with RBD-FAST, and the results suggest that W et is the most important input variable.</abstract><cop>Vienna</cop><pub>Springer Vienna</pub><doi>10.1007/s00603-024-03811-y</doi><tpages>21</tpages><orcidid>https://orcid.org/0009-0004-9212-0700</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0723-2632
ispartof Rock mechanics and rock engineering, 2024-07, Vol.57 (7), p.5207-5227
issn 0723-2632
1434-453X
language eng
recordid cdi_proquest_journals_3078183929
source Springer Nature
subjects Algorithms
Arithmetic
Bayesian analysis
Civil Engineering
Classification
Clustering
Data analysis
Data structures
Decision trees
Density
Earth and Environmental Science
Earth Sciences
Elastic analysis
Ensemble learning
Game theory
Geophysics/Geodesy
Heuristic methods
Machine learning
Mathematical analysis
Multilayer perceptrons
Noise prediction
Optimization
Optimization algorithms
Original Paper
Outliers (landforms)
Outliers (statistics)
Predictions
Preprocessing
Probability theory
Quality
Rockbursts
Spatial data
Strain energy
Underground structures
title Rockburst Intensity Grade Prediction Based on Data Preprocessing Techniques and Multi-model Ensemble Learning Algorithms
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T22%3A01%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Rockburst%20Intensity%20Grade%20Prediction%20Based%20on%20Data%20Preprocessing%20Techniques%20and%20Multi-model%20Ensemble%20Learning%20Algorithms&rft.jtitle=Rock%20mechanics%20and%20rock%20engineering&rft.au=Jia,%20Zhi-Chao&rft.date=2024-07-01&rft.volume=57&rft.issue=7&rft.spage=5207&rft.epage=5227&rft.pages=5207-5227&rft.issn=0723-2632&rft.eissn=1434-453X&rft_id=info:doi/10.1007/s00603-024-03811-y&rft_dat=%3Cproquest_cross%3E3078183929%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c319t-877f0d675507d218f7807827a504dcdc59cbe8afd16541e4fa3ae9c2451ed89b3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3078183929&rft_id=info:pmid/&rfr_iscdi=true