Hybrid PSO with tree-based models for predicting uniaxial compressive strength and elastic modulus of rock samples
The mechanical characteristics of rocks, specifically uniaxial compressive strength (UCS) and elastic modulus (E), serve as crucial factors in ensuring the integrity and stability of relevant projects in mining and civil engineering. This study proposes a novel hybrid PSO (particle swarm optimizatio...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-02-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2024.1337823/full |
| _version_ | 1797306989340000256 |
|---|---|
| author | Niaz Muhammad Shahani Niaz Muhammad Shahani Qin Xiaowei Xin Wei Li Jun Tuerhong Aizitiliwumaier Ma Xiaohu Qiu Shigui Cao Weikang Liu Longhe |
| author_facet | Niaz Muhammad Shahani Niaz Muhammad Shahani Qin Xiaowei Xin Wei Li Jun Tuerhong Aizitiliwumaier Ma Xiaohu Qiu Shigui Cao Weikang Liu Longhe |
| author_sort | Niaz Muhammad Shahani |
| collection | DOAJ |
| description | The mechanical characteristics of rocks, specifically uniaxial compressive strength (UCS) and elastic modulus (E), serve as crucial factors in ensuring the integrity and stability of relevant projects in mining and civil engineering. This study proposes a novel hybrid PSO (particle swarm optimization) with tree-based models, such as gradient boosting regressor (GBR), light gradient boosting machine (LightGBM), random forest (RF), and extreme gradient boosting (XGBoost) for predicting UCS and E of rock samples from Block IX of the Thar Coalfield in Pakistan. A total of 122 datasets were divided into training and testing sets, with an 80:20 ratio, respectively, to develop the predictive models. Key performance metrics, including the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE), were employed to assess the model’s predictive performance. The results indicate that the PSO-XGBoost model demonstrated the highest accuracy in predicting UCS and E, outperforming the other models, which exhibited inferior predictive performance. Furthermore, this study utilized the SHAP (Shapley Additive exPlanations) machine learning method to enhance our understanding of how each input feature variable influences the output values of UCS and E. In conclusion, the proposed framework offers significant advantages in evaluating the strength and deformation of rocks at Thar Coalfield, with promising applications in the field of mining and rock engineering. |
| first_indexed | 2024-03-08T00:50:50Z |
| format | Article |
| id | doaj.art-4441105871f74ad19270bc9df5a1aa8e |
| institution | Directory Open Access Journal |
| issn | 2296-6463 |
| language | English |
| last_indexed | 2024-03-08T00:50:50Z |
| publishDate | 2024-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj.art-4441105871f74ad19270bc9df5a1aa8e2024-02-15T04:50:03ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632024-02-011210.3389/feart.2024.13378231337823Hybrid PSO with tree-based models for predicting uniaxial compressive strength and elastic modulus of rock samplesNiaz Muhammad Shahani0Niaz Muhammad Shahani1Qin Xiaowei2Xin Wei3Li Jun4Tuerhong Aizitiliwumaier5Ma Xiaohu6Qiu Shigui7Cao Weikang8Liu Longhe9School of Mines, China University of Mining and Technology, Xuzhou, Jiangsu, ChinaShanxi Guxian Jingu Coal Industry Co., Ltd., Linfen, Shanxi, ChinaShanxi Guxian Jingu Coal Industry Co., Ltd., Linfen, Shanxi, ChinaSchool of Mines, China University of Mining and Technology, Xuzhou, Jiangsu, ChinaRenjiazhuan CoLLiery, Ningxia Coal Industry Co., Ltd., Lingwu, ChinaSchool of Mines, China University of Mining and Technology, Xuzhou, Jiangsu, ChinaSchool of Mines, China University of Mining and Technology, Xuzhou, Jiangsu, ChinaSchool of Mines, China University of Mining and Technology, Xuzhou, Jiangsu, ChinaShanxi Guxian Jingu Coal Industry Co., Ltd., Linfen, Shanxi, ChinaSchool of Mines, China University of Mining and Technology, Xuzhou, Jiangsu, ChinaThe mechanical characteristics of rocks, specifically uniaxial compressive strength (UCS) and elastic modulus (E), serve as crucial factors in ensuring the integrity and stability of relevant projects in mining and civil engineering. This study proposes a novel hybrid PSO (particle swarm optimization) with tree-based models, such as gradient boosting regressor (GBR), light gradient boosting machine (LightGBM), random forest (RF), and extreme gradient boosting (XGBoost) for predicting UCS and E of rock samples from Block IX of the Thar Coalfield in Pakistan. A total of 122 datasets were divided into training and testing sets, with an 80:20 ratio, respectively, to develop the predictive models. Key performance metrics, including the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE), were employed to assess the model’s predictive performance. The results indicate that the PSO-XGBoost model demonstrated the highest accuracy in predicting UCS and E, outperforming the other models, which exhibited inferior predictive performance. Furthermore, this study utilized the SHAP (Shapley Additive exPlanations) machine learning method to enhance our understanding of how each input feature variable influences the output values of UCS and E. In conclusion, the proposed framework offers significant advantages in evaluating the strength and deformation of rocks at Thar Coalfield, with promising applications in the field of mining and rock engineering.https://www.frontiersin.org/articles/10.3389/feart.2024.1337823/fullmetaheuristic algorithmmining rock mechanicstree-based modelsuniaxial compressive strength and elastic modulusThar Coalfield |
| spellingShingle | Niaz Muhammad Shahani Niaz Muhammad Shahani Qin Xiaowei Xin Wei Li Jun Tuerhong Aizitiliwumaier Ma Xiaohu Qiu Shigui Cao Weikang Liu Longhe Hybrid PSO with tree-based models for predicting uniaxial compressive strength and elastic modulus of rock samples Frontiers in Earth Science metaheuristic algorithm mining rock mechanics tree-based models uniaxial compressive strength and elastic modulus Thar Coalfield |
| title | Hybrid PSO with tree-based models for predicting uniaxial compressive strength and elastic modulus of rock samples |
| title_full | Hybrid PSO with tree-based models for predicting uniaxial compressive strength and elastic modulus of rock samples |
| title_fullStr | Hybrid PSO with tree-based models for predicting uniaxial compressive strength and elastic modulus of rock samples |
| title_full_unstemmed | Hybrid PSO with tree-based models for predicting uniaxial compressive strength and elastic modulus of rock samples |
| title_short | Hybrid PSO with tree-based models for predicting uniaxial compressive strength and elastic modulus of rock samples |
| title_sort | hybrid pso with tree based models for predicting uniaxial compressive strength and elastic modulus of rock samples |
| topic | metaheuristic algorithm mining rock mechanics tree-based models uniaxial compressive strength and elastic modulus Thar Coalfield |
| url | https://www.frontiersin.org/articles/10.3389/feart.2024.1337823/full |
| work_keys_str_mv | AT niazmuhammadshahani hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples AT niazmuhammadshahani hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples AT qinxiaowei hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples AT xinwei hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples AT lijun hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples AT tuerhongaizitiliwumaier hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples AT maxiaohu hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples AT qiushigui hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples AT caoweikang hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples AT liulonghe hybridpsowithtreebasedmodelsforpredictinguniaxialcompressivestrengthandelasticmodulusofrocksamples |