Interpretable model for rockburst intensity prediction based on Shapley values-based Optuna-random forest
To address the limitation of traditional machine learning models in explaining the rockburst intensity prediction process, this study proposes an interpretable rockburst intensity prediction model. The model was developed using 350 sets of actual rockburst sample data to explore the impact of input...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-04-01
|
| Series: | Underground Space |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2467967424001089 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850035296863780864 |
|---|---|
| author | Yaxi Shen Shunchuan Wu Yongbing Wang Jiaxin Wang Zhiquan Yang |
| author_facet | Yaxi Shen Shunchuan Wu Yongbing Wang Jiaxin Wang Zhiquan Yang |
| author_sort | Yaxi Shen |
| collection | DOAJ |
| description | To address the limitation of traditional machine learning models in explaining the rockburst intensity prediction process, this study proposes an interpretable rockburst intensity prediction model. The model was developed using 350 sets of actual rockburst sample data to explore the impact of input metrics on the final rockburst intensity level. The collected data underwent pre-processing using the isolation forest algorithm and synthetic minority oversampling technique. The random forest model was optimized through 5-fold cross-validation and the Optuna framework, resulting in the establishment of an Optuna-random forest (Op-RF) model that generates decision rules through its internal decision tree, utilizing the properties of the random forest model. The model was further interpreted using the Shapley additive explanations algorithm, both locally and globally. The results demonstrate that the proposed model achieved an area under curve score of 0.984. In comparison to eight other machine learning models, the proposed Op-RF model demonstrated superior accuracy, precision, recall, and F1 score. The model provides a transparent explanation of the prediction process, linking impact characteristics to the final output. Additionally, a cloud deployment method for the rockburst intensity prediction model is provided and its effectiveness is demonstrated through engineering verification. The proposed model offers a new approach to the application of machine learning in rockburst intensity prediction. |
| format | Article |
| id | doaj-art-2c4b8fcc9b0a414fa49e5ce6e46687b4 |
| institution | DOAJ |
| issn | 2467-9674 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Underground Space |
| spelling | doaj-art-2c4b8fcc9b0a414fa49e5ce6e46687b42025-08-20T02:57:32ZengKeAi Communications Co., Ltd.Underground Space2467-96742025-04-012119821410.1016/j.undsp.2024.09.002Interpretable model for rockburst intensity prediction based on Shapley values-based Optuna-random forestYaxi Shen0Shunchuan Wu1Yongbing Wang2Jiaxin Wang3Zhiquan Yang4Department of Civil Engineering, Tianjin University, Tianjin 300072, China; Faculty of Public Safety and Emergency Management, Kunming University of Science and Technology, Kunming 650093, ChinaFaculty of Public Safety and Emergency Management, Kunming University of Science and Technology, Kunming 650093, China; Faculty of Land Resources Engineering, Kunming University of Science and Technology, Kunming 650093, China; Corresponding author at: Faculty of Land Resources Engineering, Kunming University of Science and Technology, Kunming 650093, China.Huize Mining Company, Yunnan Chihong Zinc and Germanium Co., Ltd., Qujing 655000, ChinaFaculty of Land Resources Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaFaculty of Public Safety and Emergency Management, Kunming University of Science and Technology, Kunming 650093, ChinaTo address the limitation of traditional machine learning models in explaining the rockburst intensity prediction process, this study proposes an interpretable rockburst intensity prediction model. The model was developed using 350 sets of actual rockburst sample data to explore the impact of input metrics on the final rockburst intensity level. The collected data underwent pre-processing using the isolation forest algorithm and synthetic minority oversampling technique. The random forest model was optimized through 5-fold cross-validation and the Optuna framework, resulting in the establishment of an Optuna-random forest (Op-RF) model that generates decision rules through its internal decision tree, utilizing the properties of the random forest model. The model was further interpreted using the Shapley additive explanations algorithm, both locally and globally. The results demonstrate that the proposed model achieved an area under curve score of 0.984. In comparison to eight other machine learning models, the proposed Op-RF model demonstrated superior accuracy, precision, recall, and F1 score. The model provides a transparent explanation of the prediction process, linking impact characteristics to the final output. Additionally, a cloud deployment method for the rockburst intensity prediction model is provided and its effectiveness is demonstrated through engineering verification. The proposed model offers a new approach to the application of machine learning in rockburst intensity prediction.http://www.sciencedirect.com/science/article/pii/S2467967424001089Rockburst intensityIsolation forestSynthetic minority oversamplingRandom forestInterpretable model |
| spellingShingle | Yaxi Shen Shunchuan Wu Yongbing Wang Jiaxin Wang Zhiquan Yang Interpretable model for rockburst intensity prediction based on Shapley values-based Optuna-random forest Underground Space Rockburst intensity Isolation forest Synthetic minority oversampling Random forest Interpretable model |
| title | Interpretable model for rockburst intensity prediction based on Shapley values-based Optuna-random forest |
| title_full | Interpretable model for rockburst intensity prediction based on Shapley values-based Optuna-random forest |
| title_fullStr | Interpretable model for rockburst intensity prediction based on Shapley values-based Optuna-random forest |
| title_full_unstemmed | Interpretable model for rockburst intensity prediction based on Shapley values-based Optuna-random forest |
| title_short | Interpretable model for rockburst intensity prediction based on Shapley values-based Optuna-random forest |
| title_sort | interpretable model for rockburst intensity prediction based on shapley values based optuna random forest |
| topic | Rockburst intensity Isolation forest Synthetic minority oversampling Random forest Interpretable model |
| url | http://www.sciencedirect.com/science/article/pii/S2467967424001089 |
| work_keys_str_mv | AT yaxishen interpretablemodelforrockburstintensitypredictionbasedonshapleyvaluesbasedoptunarandomforest AT shunchuanwu interpretablemodelforrockburstintensitypredictionbasedonshapleyvaluesbasedoptunarandomforest AT yongbingwang interpretablemodelforrockburstintensitypredictionbasedonshapleyvaluesbasedoptunarandomforest AT jiaxinwang interpretablemodelforrockburstintensitypredictionbasedonshapleyvaluesbasedoptunarandomforest AT zhiquanyang interpretablemodelforrockburstintensitypredictionbasedonshapleyvaluesbasedoptunarandomforest |