This study focuses on the construction and interpretation of a mine water inrush source identification model to enhance the precision and credibility of the model. For water inrush source identification and feature analysis, a novel method combining XGBoost and SHAP is suggested. The model uses Ca, Mg, K + Na, HCO, Cl, SO, Hardness, and pH as discriminators, and the key parameters in the XGBoost model are optimized by introducing the improved sparrow search algorithm. The Sparrow Search Algorithm combines Tent chaos mapping and Levy flight strategy (CLSSA), which makes the optimization process better balance the global search ability and local search ability, so as to improve the efficiency and effect of parameter optimization. Specifically, CLSSA is used to optimize key parameters of XGBoost, including the number of weak estimators (NE), tree depth (TD), model learning rate (LR), and then establishes a mine water inrush source identification model based on the CLSSA-XGBoost. Moreover, the model combines SHAP explainable framework to analyze key features of the identification results and interpret the impact of these features. Verified by 160 sample sets in Xinzhuangzi Mine, the average prediction precision of the CLSSA-XGBoost is 97.78%, the average prediction recall rate is 97.59% and the F1 is 97.61%, which are better than other comparison models. The SHAP provides global and local predictive explanatory analysis, revealing key factors for identifying different water inrush sources, enhancing the credibility of prediction results, and helping mine safety personnel make accurate decisions.

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-024-83710-yDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11697395PMC

Publication Analysis

Top Keywords

water inrush
20
inrush source
16
identification model
12
mine water
12
source identification
12
xgboost shap
8
key parameters
8
parameters xgboost
8
sparrow search
8
search algorithm
8

Similar Publications

This study focuses on the construction and interpretation of a mine water inrush source identification model to enhance the precision and credibility of the model. For water inrush source identification and feature analysis, a novel method combining XGBoost and SHAP is suggested. The model uses Ca, Mg, K + Na, HCO, Cl, SO, Hardness, and pH as discriminators, and the key parameters in the XGBoost model are optimized by introducing the improved sparrow search algorithm.

View Article and Find Full Text PDF

Mechanized tunneling in harsh environments faces many hazards, which can stop tunneling operations for a long time. Due to the high investment volume in tunneling projects, it is imperative to predict and assess the geotechnical hazards. This research has tried to evaluate and introduce the most dangerous section of the Kerman water conveyance tunnel (KWCT) using multi-index decision-making techniques including PROMETHEE II, WASPAS, and CoCoSo models.

View Article and Find Full Text PDF

To explore the mechanism of water inrush from the mine roof strata, a series of seepage-acoustic emission (SAE) experiments on red sandstone disc samples were carried out. The effects of the height to diameter ratio (H/D) and pore pressure on the mechanical, hydraulic and crack propagation properties of red sandstones were investigated. Test results show that, the peak load of rock samples declines with the decreasing H/D and increasing pore pressure.

View Article and Find Full Text PDF

Geothermal energy is a crucial component contributing to the development of local thermal energy systems as a carbon-neutral and reliable energy source. Insights into its availability derive from knowledge of geology, hydrogeology and the thermal regime of the subsurface. This expertise helps to locate and monitor geothermal installations as well as observe diverse aspects of natural and man-made thermal effects.

View Article and Find Full Text PDF

Ultrasonic detection has emerged as a rapid method for acquiring rock mass sound velocity and converting it into an elastic modulus parameter, a pivotal technique for investigating the in-situ mechanical properties of rock masses. Despite its significance, accurately deducing rock mass strength from elastic modulus remains a formidable challenge and a pressing issue in the realm of protorock parameter research. This study introduces an innovative artificial intelligence-driven methodology for transforming elastic modulus and strength parameters specific to coal measures through rigorous data analysis and experimental validation.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!