Enhancing hazard prediction in coal mining with an optimized extra gradient boosting classification model for seismic bump processes.
Saved in:
| Title: | Enhancing hazard prediction in coal mining with an optimized extra gradient boosting classification model for seismic bump processes. |
|---|---|
| Authors: | Li, Fei1 (AUTHOR) feili@zzuli.edu.cn |
| Source: | Sādhanā: Academy Proceedings in Engineering Sciences. Jun2026, Vol. 51 Issue 2, p1-20. 20p. |
| Subjects: | Coal mining, Boosting algorithms, Loss control, Risk assessment, Mine safety, Prediction models, Optimization algorithms, Rock bursts |
| Abstract: | Natural disasters can have a high impact on property and life, and in most scenarios, such an impact can hardly be averted. In mining operations, high incidences of seismically-related events, apart from fires and explosion-related events, compound miners' multi-faceted peril. Due to the complex processes involved in seismic activity, predicting with accuracy is not easy, even with modern tools for observation. To counteract financial loss and maximize miner security, an Extra Gradient Boosting Classification (XGBC) model is adopted to classify dangerous and safe areas in underground mining environments. An attributed analysis technique determined each contributing variable in diagnosing a case. Despite an initial run of the XGBC model producing less than satisfactory output, improvement became necessary. In an endeavor to maximize predictive performance, three improvement techniques, namely, Fox-inspired Optimization Algorithm (FOA), Coot Optimization Algorithm (COA), and Adaptive Opposition Slime Mould Algorithm (AOSM) have been adopted. Output revealed that XGFO, incorporating FOA, showed a supreme performance with a high 97.5% accuracy level. Due to its high accuracy and usability, the XGFO model is recommended for real-life use. With its optimized model, a high level of improvement in terms of security and financial loss in mining operations can be achieved, and a high demand for a reliable prediction of danger can be met. [ABSTRACT FROM AUTHOR] |
| Copyright of Sādhanā: Academy Proceedings in Engineering Sciences is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Natural disasters can have a high impact on property and life, and in most scenarios, such an impact can hardly be averted. In mining operations, high incidences of seismically-related events, apart from fires and explosion-related events, compound miners' multi-faceted peril. Due to the complex processes involved in seismic activity, predicting with accuracy is not easy, even with modern tools for observation. To counteract financial loss and maximize miner security, an Extra Gradient Boosting Classification (XGBC) model is adopted to classify dangerous and safe areas in underground mining environments. An attributed analysis technique determined each contributing variable in diagnosing a case. Despite an initial run of the XGBC model producing less than satisfactory output, improvement became necessary. In an endeavor to maximize predictive performance, three improvement techniques, namely, Fox-inspired Optimization Algorithm (FOA), Coot Optimization Algorithm (COA), and Adaptive Opposition Slime Mould Algorithm (AOSM) have been adopted. Output revealed that XGFO, incorporating FOA, showed a supreme performance with a high 97.5% accuracy level. Due to its high accuracy and usability, the XGFO model is recommended for real-life use. With its optimized model, a high level of improvement in terms of security and financial loss in mining operations can be achieved, and a high demand for a reliable prediction of danger can be met. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 02562499 |
| DOI: | 10.1007/s12046-025-03036-x |
