Impact of a multiple oversampling technique-based assessment framework on shallow rockburst prediction models
The occurrence of class-imbalanced datasets is a frequent observation in natural science research, emphasizing the paramount importance of effectively harnessing them to construct highly accurate models for rockburst prediction. Initially, genuine rockburst incidents within a burial depth of 500 m w...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2024.1514591/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832593944662245376 |
|---|---|
| author | Guozhu Rao Guozhu Rao Yunzhang Rao Yunzhang Rao Yangjun Xie Qiang Huang Jiazheng Wan Jiyong Zhang |
| author_facet | Guozhu Rao Guozhu Rao Yunzhang Rao Yunzhang Rao Yangjun Xie Qiang Huang Jiazheng Wan Jiyong Zhang |
| author_sort | Guozhu Rao |
| collection | DOAJ |
| description | The occurrence of class-imbalanced datasets is a frequent observation in natural science research, emphasizing the paramount importance of effectively harnessing them to construct highly accurate models for rockburst prediction. Initially, genuine rockburst incidents within a burial depth of 500 m were sourced from literature, revealing a small dataset imbalance issue. Utilizing various mainstream oversampling techniques, the dataset was expanded to generate six new datasets, subsequently subjected to 12 classifiers across 84 classification processes. The model incorporating the highest-scoring model from the original dataset and the top two models from the expanded dataset, yielded a high-performance model. Findings indicate that the KMeansSMOTE oversampling technique exhibits the most substantial enhancement across the combined 12 classifiers, whereas individual classifiers favor ET+SVMSMOTE and RF+SMOTENC. Following multiple rounds of hyper parameter adjustment via random cross-validation, the ET+SVMSMOTE combination attained the highest accuracy rate of 93.75%, surpassing mainstream models for rockburst prediction. Moreover, the SVMSMOTE technique, augmenting samples with fewer categories, demonstrated notable benefits in mitigating overfitting, enhancing generalization, and improving Recall and F1 score within RF classifiers. Validated for its high generalization performance, accuracy, and reliability. This process also provides an efficient framework for model development. |
| format | Article |
| id | doaj-art-918f6c36c17040d5a1aef2c379690ef4 |
| institution | Kabale University |
| issn | 2296-6463 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj-art-918f6c36c17040d5a1aef2c379690ef42025-01-20T07:20:33ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632025-01-011210.3389/feart.2024.15145911514591Impact of a multiple oversampling technique-based assessment framework on shallow rockburst prediction modelsGuozhu Rao0Guozhu Rao1Yunzhang Rao2Yunzhang Rao3Yangjun Xie4Qiang Huang5Jiazheng Wan6Jiyong Zhang7School of Emergency Management and Safety Engineering, Jiangxi University of Science and Technology, Ganzhou, ChinaJiangxi Province Key Laboratory of Safe and Efficient Mining of Rare Metal Resources, Jiangxi University of Science and Technology, Ganzhou, ChinaSchool of Resources and Environmental Engineering, Jiangxi University of Science and Technology, Ganzhou, ChinaJiangxi Provincial Key Laboratory of Low-Carbon Processing and Utilization of Strategic Metal Mineral Resources, Jiangxi University of Science and Technology, Ganzhou, ChinaSchool of Resources and Environmental Engineering, Jiangxi University of Science and Technology, Ganzhou, ChinaSchool of Resources and Environmental Engineering, Jiangxi University of Science and Technology, Ganzhou, ChinaSchool of Resources and Environmental Engineering, Jiangxi University of Science and Technology, Ganzhou, ChinaSchool of Resources and Environmental Engineering, Jiangxi University of Science and Technology, Ganzhou, ChinaThe occurrence of class-imbalanced datasets is a frequent observation in natural science research, emphasizing the paramount importance of effectively harnessing them to construct highly accurate models for rockburst prediction. Initially, genuine rockburst incidents within a burial depth of 500 m were sourced from literature, revealing a small dataset imbalance issue. Utilizing various mainstream oversampling techniques, the dataset was expanded to generate six new datasets, subsequently subjected to 12 classifiers across 84 classification processes. The model incorporating the highest-scoring model from the original dataset and the top two models from the expanded dataset, yielded a high-performance model. Findings indicate that the KMeansSMOTE oversampling technique exhibits the most substantial enhancement across the combined 12 classifiers, whereas individual classifiers favor ET+SVMSMOTE and RF+SMOTENC. Following multiple rounds of hyper parameter adjustment via random cross-validation, the ET+SVMSMOTE combination attained the highest accuracy rate of 93.75%, surpassing mainstream models for rockburst prediction. Moreover, the SVMSMOTE technique, augmenting samples with fewer categories, demonstrated notable benefits in mitigating overfitting, enhancing generalization, and improving Recall and F1 score within RF classifiers. Validated for its high generalization performance, accuracy, and reliability. This process also provides an efficient framework for model development.https://www.frontiersin.org/articles/10.3389/feart.2024.1514591/fulloversampling techniquesmachine learningshallow rockburst intensity predictionassessmentgeneralization capability |
| spellingShingle | Guozhu Rao Guozhu Rao Yunzhang Rao Yunzhang Rao Yangjun Xie Qiang Huang Jiazheng Wan Jiyong Zhang Impact of a multiple oversampling technique-based assessment framework on shallow rockburst prediction models Frontiers in Earth Science oversampling techniques machine learning shallow rockburst intensity prediction assessment generalization capability |
| title | Impact of a multiple oversampling technique-based assessment framework on shallow rockburst prediction models |
| title_full | Impact of a multiple oversampling technique-based assessment framework on shallow rockburst prediction models |
| title_fullStr | Impact of a multiple oversampling technique-based assessment framework on shallow rockburst prediction models |
| title_full_unstemmed | Impact of a multiple oversampling technique-based assessment framework on shallow rockburst prediction models |
| title_short | Impact of a multiple oversampling technique-based assessment framework on shallow rockburst prediction models |
| title_sort | impact of a multiple oversampling technique based assessment framework on shallow rockburst prediction models |
| topic | oversampling techniques machine learning shallow rockburst intensity prediction assessment generalization capability |
| url | https://www.frontiersin.org/articles/10.3389/feart.2024.1514591/full |
| work_keys_str_mv | AT guozhurao impactofamultipleoversamplingtechniquebasedassessmentframeworkonshallowrockburstpredictionmodels AT guozhurao impactofamultipleoversamplingtechniquebasedassessmentframeworkonshallowrockburstpredictionmodels AT yunzhangrao impactofamultipleoversamplingtechniquebasedassessmentframeworkonshallowrockburstpredictionmodels AT yunzhangrao impactofamultipleoversamplingtechniquebasedassessmentframeworkonshallowrockburstpredictionmodels AT yangjunxie impactofamultipleoversamplingtechniquebasedassessmentframeworkonshallowrockburstpredictionmodels AT qianghuang impactofamultipleoversamplingtechniquebasedassessmentframeworkonshallowrockburstpredictionmodels AT jiazhengwan impactofamultipleoversamplingtechniquebasedassessmentframeworkonshallowrockburstpredictionmodels AT jiyongzhang impactofamultipleoversamplingtechniquebasedassessmentframeworkonshallowrockburstpredictionmodels |