View in EDS HTML Full Text PDF Full Text

Interpretable Tree‐Based Models for Predicting Short‐Term Rockburst Risk Considering Multiple Factors.

Saved in:
Bibliographic Details
Title: Interpretable Tree‐Based Models for Predicting Short‐Term Rockburst Risk Considering Multiple Factors.
Authors: Chen, Shuai1 (AUTHOR) cscumt@cumt.edu.cn, Dou, Linming1,2 (AUTHOR), Li, Atao3 (AUTHOR), Cai, Wu2 (AUTHOR), Zhang, Lei1 (AUTHOR)
Source: Energy Science & Engineering. Jun2026, Vol. 14 Issue 6, p2941-2960. 20p.
Subject Terms: *Boosting algorithms, *Shapley Additive Explanations, *Risk assessment, *Machine learning, *Coal mining safety, *Random forest algorithms
Abstract: Rockbursts are typical dynamic disasters in underground coal mines. Their formation and occurrence are influenced by multiple factors, including geological conditions, mining disturbances, and microseismic activities. Machine learning models can support early warning by forecasting high‐energy microseismic (MS) activity associated with elevated rockburst risk. However, many of these models are black boxes that are difficult for humans to understand, which may diminish their credibility and constrain their practical applicability. To establish interpretable models for short‐term rockburst prediction considering multiple factors, we assess five tree‐based models (decision tree, random forest, LightGBM, XGBoost, and CatBoost) using field databases from Gao Jiapu coal mine and utilize the model explanation method SHAP to interpret the models. A day is labeled as rockburst risk if its daily maximum MS energy exceeds 1 × 10⁵ J, otherwise no risk. The results revealed that CatBoost exhibited the highest overall performance, followed by LightGBM, and both the random tree and XGBoost performed better than the decision tree. When considering the influence of time window length, all models displayed optimal performance under a 3‐day time window. Specifically, CatBoost achieved F1 scores of 0.856, 0.778, and 0.807 for the 3‐day, 5‐day, and 10‐day time windows, respectively. Global feature importance analysis showed that the average energy, energy deviation, and cumulative energy were the three most important predictors. Furthermore, local SHAP values were drawn to reveal the complex underlying relationships between the 12 factors and model predictions. The results show that factors such as energy‐related factors, coal depth, and working face advance positively contribute to rockburst risk prediction. Conversely, fold distance, total frequency, and source concentration degree negatively impact the model outcomes. The findings suggest that incorporating CatBoost and the SHAP method holds great potential in developing interpretable models for accurate rockburst risk prediction. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 194418751
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Interpretable Tree‐Based Models for Predicting Short‐Term Rockburst Risk Considering Multiple Factors.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Chen%2C+Shuai%22">Chen, Shuai</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> cscumt@cumt.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Dou%2C+Linming%22">Dou, Linming</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Atao%22">Li, Atao</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cai%2C+Wu%22">Cai, Wu</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Lei%22">Zhang, Lei</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energy+Science+%26+Engineering%22">Energy Science & Engineering</searchLink>. Jun2026, Vol. 14 Issue 6, p2941-2960. 20p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Boosting+algorithms%22">Boosting algorithms</searchLink><br />*<searchLink fieldCode="DE" term="%22Shapley+Additive+Explanations%22">Shapley Additive Explanations</searchLink><br />*<searchLink fieldCode="DE" term="%22Risk+assessment%22">Risk assessment</searchLink><br />*<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Coal+mining+safety%22">Coal mining safety</searchLink><br />*<searchLink fieldCode="DE" term="%22Random+forest+algorithms%22">Random forest algorithms</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Rockbursts are typical dynamic disasters in underground coal mines. Their formation and occurrence are influenced by multiple factors, including geological conditions, mining disturbances, and microseismic activities. Machine learning models can support early warning by forecasting high‐energy microseismic (MS) activity associated with elevated rockburst risk. However, many of these models are black boxes that are difficult for humans to understand, which may diminish their credibility and constrain their practical applicability. To establish interpretable models for short‐term rockburst prediction considering multiple factors, we assess five tree‐based models (decision tree, random forest, LightGBM, XGBoost, and CatBoost) using field databases from Gao Jiapu coal mine and utilize the model explanation method SHAP to interpret the models. A day is labeled as rockburst risk if its daily maximum MS energy exceeds 1 × 10⁵ J, otherwise no risk. The results revealed that CatBoost exhibited the highest overall performance, followed by LightGBM, and both the random tree and XGBoost performed better than the decision tree. When considering the influence of time window length, all models displayed optimal performance under a 3‐day time window. Specifically, CatBoost achieved F1 scores of 0.856, 0.778, and 0.807 for the 3‐day, 5‐day, and 10‐day time windows, respectively. Global feature importance analysis showed that the average energy, energy deviation, and cumulative energy were the three most important predictors. Furthermore, local SHAP values were drawn to reveal the complex underlying relationships between the 12 factors and model predictions. The results show that factors such as energy‐related factors, coal depth, and working face advance positively contribute to rockburst risk prediction. Conversely, fold distance, total frequency, and source concentration degree negatively impact the model outcomes. The findings suggest that incorporating CatBoost and the SHAP method holds great potential in developing interpretable models for accurate rockburst risk prediction. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=194418751
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/ese3.70513
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 20
        StartPage: 2941
    Subjects:
      – SubjectFull: Boosting algorithms
        Type: general
      – SubjectFull: Shapley Additive Explanations
        Type: general
      – SubjectFull: Risk assessment
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Coal mining safety
        Type: general
      – SubjectFull: Random forest algorithms
        Type: general
    Titles:
      – TitleFull: Interpretable Tree‐Based Models for Predicting Short‐Term Rockburst Risk Considering Multiple Factors.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chen, Shuai
      – PersonEntity:
          Name:
            NameFull: Dou, Linming
      – PersonEntity:
          Name:
            NameFull: Li, Atao
      – PersonEntity:
          Name:
            NameFull: Cai, Wu
      – PersonEntity:
          Name:
            NameFull: Zhang, Lei
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20500505
          Numbering:
            – Type: volume
              Value: 14
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Energy Science & Engineering
              Type: main
ResultId 1