Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

To enhance the accuracy of predicting the height of water-conducting fracture zones (WCFZ) in coal mines, this study proposes a novel stacked ensemble learning model. The model integrates XGBoost and Support Vector Regression (SVR) as base learners, with CatBoost serving as the meta-learner, forming a two-layer architecture. Key geological and mining features-such as mining height, burial depth, working face length, and lithologic proportion coefficient-are used as input variables to better capture the complex influencing factors. Validation using data from the No. 3 coal seam of Husheng Coal Mine demonstrates that the proposed model achieves a predicted WCFZ height of 50.79 m, closely aligning with the measured value and outperforming empirical formulas (61.4 m), standalone SVR (58.14 m), XGBoost (56.62 m), and FLAC3D simulation (55 m). The model also achieves an R² of 0.98 and RMSE of 2.08, indicating excellent predictive performance. This research is the first to introduce stacked ensemble learning for WCFZ height prediction, overcoming the limitations of single-model and simulation-based methods. The proposed approach offers a more accurate and intelligent tool for mine water hazard assessment and represents a significant advancement in applying machine learning to underground geological engineering.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12317089PMC
http://dx.doi.org/10.1038/s41598-025-13627-7DOI Listing

Publication Analysis

Top Keywords

coal mine
8
mine water
8
learning model
8
stacked ensemble
8
ensemble learning
8
model achieves
8
wcfz height
8
height
5
model
5
prediction coal
4

Similar Publications

Naomaohu lignite (NL) from Hami, Xinjiang, was ultrasonically extracted with a mixed solvent of CS and acetone (in equal volumes) to obtain the extract residue (ER). The ER was then separated based on density differences with CCl to yield the corresponding light residue (NL-L). The composition and structural characteristics of the light residue were characterized by proximate, ultimate, infrared, and thermogravimetric analyses (TG-DTG).

View Article and Find Full Text PDF

Zeolite synthesis from fly ash offers recycling and environmental benefits for carbon dioxide capture, but varying fly ash composition from different sources has different compositions, leading to inconsistent adsorption results. To achieve high CO adsorption performance and stability in zeolite synthesis from fly ash systems, this study established an element-controlled simulated fly ash system with Ca/Fe gradient differences. Hydrothermal synthesis yielded zeolites with optimized oxide ratios for CO adsorption.

View Article and Find Full Text PDF

Hydrogen energy is pivotal for driving sustainable development and achieving deep decarbonization; yet, its storage remains a significant challenge. Notably, depleted methane reservoirs can serve as a promising large-scale solution for underground hydrogen storage (UHS). Based on adsorption experiments, Monte Carlo and molecular dynamics methods, the adsorption behavior of H and CH in anthracite and the applicability of five models were discussed.

View Article and Find Full Text PDF

The Influence of Embedded Properties on the Liberation Characteristics of Macerals in Subbituminous Coal.

ACS Omega

September 2025

CHN ENERGY CORNERSTONE CHEMICAL TECHNOLOGY (SHANGHAI) CO.,LTD, Shanghai 201100, China.

The utilization pathways of coal macerals exhibit a significant variability. The efficient separation of active and inert components in coal is critical for realizing their high value-added applications. The liberation efficiency of coal macerals directly influences the accuracy of subsequent separation processes.

View Article and Find Full Text PDF

Study on Permeability and Flow Characteristics of Composite Thermosensitive Hydrogel and Its Fire Prevention and Extinguishment Performance.

ACS Omega

September 2025

State Key Laboratory for Fine Exploration and Intelligent Development of Coal Resources, China University of Mining and Technology, Xuzhou, Jiangsu 221116, People's Republic of China.

This study focuses on the issues of poor fluidity, low penetration into residual coal, and suboptimal inhibition of coal spontaneous combustion associated with traditional coal mine gel fire retardants. The permeability and flow characteristics of a sodium alginate-based composite thermosensitive hydrogel, as well as its fire prevention and extinguishment performance, were investigated. The findings suggest that the thermosensitive hydrogel behaves as a pseudoplastic fluid at 40 °C and a yield-pseudoplastic fluid at 65 °C, exhibiting shear-thinning behavior with increasing shear rate.

View Article and Find Full Text PDF