Application of Bayesian optimized XGBoost in seismic interpretation of small-scale faults
In order to further improve the identification accuracy of small-scale faults in seismic interpretation, Bayesian optimized extreme gradient boosting (XGBoost) model was constructed to recognize small-scale faults across coalbeds using reduced seismic attributes based on the theory of information va...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of China Coal Society
2023-06-01
|
| Series: | Meitan xuebao |
| Subjects: | |
| Online Access: | http://www.mtxb.com.cn/article/doi/10.13225/j.cnki.jccs.2021.1932 |
| _version_ | 1797788063107121152 |
|---|---|
| author | Changwei DING Xin WANG Tongjun CHEN Ting YU |
| author_facet | Changwei DING Xin WANG Tongjun CHEN Ting YU |
| author_sort | Changwei DING |
| collection | DOAJ |
| description | In order to further improve the identification accuracy of small-scale faults in seismic interpretation, Bayesian optimized extreme gradient boosting (XGBoost) model was constructed to recognize small-scale faults across coalbeds using reduced seismic attributes based on the theory of information value(IV). Firstly, the seismic attribute data of the mining area were preprocessed to remove abnormal samples and large noise samples. Secondly, chi-square bins were performed for each feature of the processed model, the weight of evidence (WOE) was calculated in each container, and the information value of each element was obtained, which is used as the importance of each feature. Features with low information values were reduced to remove high-noise feature attributes. At the same time,a certain degree of noise is added to the seismic data of small-scale faults to enhance the anti-noise ability of the model. Finally, the Bayesian optimized XGBoost model was constructed. The method to improve the XGBoost objective function was proposed to balance the training weights of the positive and negative examples. As the acquisition function of the Bayesian optimized algorithm quickly falls into the local optimum, it does not easily balance the “exploit” and “explore” approach. Therefore, this paper proposes an adaptive balance factor change algorithm, which dynamically ground balances the process of “mining” and “exploring” the pi acquisition function to improve the robustness of the parameter optimization process. Comparing the identification outcomes, the new XGBoost model framework (SAPI-Bay-ImpXGBoost) has a higher prediction accuracy than BP neural network, Support Vector Machine(SVM), K-nearst neighbors(KNN) and Adaptive Boosting(AdaBoost). In summary, the proposed method can further strengthen the identification of small-scale faults in coal mining areas. |
| first_indexed | 2024-03-13T01:30:15Z |
| format | Article |
| id | doaj.art-a0a59bd5c7f143cf9a4438859fec1896 |
| institution | Directory Open Access Journal |
| issn | 0253-9993 |
| language | zho |
| last_indexed | 2024-03-13T01:30:15Z |
| publishDate | 2023-06-01 |
| publisher | Editorial Office of Journal of China Coal Society |
| record_format | Article |
| series | Meitan xuebao |
| spelling | doaj.art-a0a59bd5c7f143cf9a4438859fec18962023-07-04T08:24:08ZzhoEditorial Office of Journal of China Coal SocietyMeitan xuebao0253-99932023-06-014862530253910.13225/j.cnki.jccs.2021.19322021-1932Application of Bayesian optimized XGBoost in seismic interpretation of small-scale faultsChangwei DING0Xin WANG1Tongjun CHEN2Ting YU3School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Resources and Earth Science, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaIn order to further improve the identification accuracy of small-scale faults in seismic interpretation, Bayesian optimized extreme gradient boosting (XGBoost) model was constructed to recognize small-scale faults across coalbeds using reduced seismic attributes based on the theory of information value(IV). Firstly, the seismic attribute data of the mining area were preprocessed to remove abnormal samples and large noise samples. Secondly, chi-square bins were performed for each feature of the processed model, the weight of evidence (WOE) was calculated in each container, and the information value of each element was obtained, which is used as the importance of each feature. Features with low information values were reduced to remove high-noise feature attributes. At the same time,a certain degree of noise is added to the seismic data of small-scale faults to enhance the anti-noise ability of the model. Finally, the Bayesian optimized XGBoost model was constructed. The method to improve the XGBoost objective function was proposed to balance the training weights of the positive and negative examples. As the acquisition function of the Bayesian optimized algorithm quickly falls into the local optimum, it does not easily balance the “exploit” and “explore” approach. Therefore, this paper proposes an adaptive balance factor change algorithm, which dynamically ground balances the process of “mining” and “exploring” the pi acquisition function to improve the robustness of the parameter optimization process. Comparing the identification outcomes, the new XGBoost model framework (SAPI-Bay-ImpXGBoost) has a higher prediction accuracy than BP neural network, Support Vector Machine(SVM), K-nearst neighbors(KNN) and Adaptive Boosting(AdaBoost). In summary, the proposed method can further strengthen the identification of small-scale faults in coal mining areas.http://www.mtxb.com.cn/article/doi/10.13225/j.cnki.jccs.2021.1932small-scale faultsweight of evidencebayesian optimizationacquisition functionxgboost |
| spellingShingle | Changwei DING Xin WANG Tongjun CHEN Ting YU Application of Bayesian optimized XGBoost in seismic interpretation of small-scale faults Meitan xuebao small-scale faults weight of evidence bayesian optimization acquisition function xgboost |
| title | Application of Bayesian optimized XGBoost in seismic interpretation of small-scale faults |
| title_full | Application of Bayesian optimized XGBoost in seismic interpretation of small-scale faults |
| title_fullStr | Application of Bayesian optimized XGBoost in seismic interpretation of small-scale faults |
| title_full_unstemmed | Application of Bayesian optimized XGBoost in seismic interpretation of small-scale faults |
| title_short | Application of Bayesian optimized XGBoost in seismic interpretation of small-scale faults |
| title_sort | application of bayesian optimized xgboost in seismic interpretation of small scale faults |
| topic | small-scale faults weight of evidence bayesian optimization acquisition function xgboost |
| url | http://www.mtxb.com.cn/article/doi/10.13225/j.cnki.jccs.2021.1932 |
| work_keys_str_mv | AT changweiding applicationofbayesianoptimizedxgboostinseismicinterpretationofsmallscalefaults AT xinwang applicationofbayesianoptimizedxgboostinseismicinterpretationofsmallscalefaults AT tongjunchen applicationofbayesianoptimizedxgboostinseismicinterpretationofsmallscalefaults AT tingyu applicationofbayesianoptimizedxgboostinseismicinterpretationofsmallscalefaults |