Water-Richness Zoning Technology of Karst Aquifers at in the Roofs of Deep Phosphate Mines Based on Random Forest Model

Xin Li, Bo Li (), Ye Luo, Tao Li, Hang Han, Wenjie Zhang and Beibei Zhang
Additional contact information
Xin Li: College of Resource and Environmental Engineering, Guizhou University, Guiyang 550025, China
Bo Li: College of Resource and Environmental Engineering, Guizhou University, Guiyang 550025, China
Ye Luo: Guizhou Kailin Phophate Industry Co., Ltd., Guiyang 550025, China
Tao Li: School of Mines and Civil Engineering, Liupanshui Normal University, Liupanshui 553004, China
Hang Han: Key Laboratory of Karst Georesources and Environment, Ministry of Education, Guizhou University, Guiyang 550025, China
Wenjie Zhang: College of Resource and Environmental Engineering, Guizhou University, Guiyang 550025, China
Beibei Zhang: College of Building Science and Engineering, Guiyang University, Guiyang 550025, China

Sustainability, 2023, vol. 15, issue 18, 1-17

Abstract: The development of fractures and conduits in karst aquifers and the strength of their water richness are key factors in determining whether a water intrusion will occur in a mine. In the phosphorus mining process, if the mining of water-rich areas is carried out, sudden water disasters can easily occur. Therefore, water-richness zoning of the karst aquifer on the roof of the phosphate mine is very important to protect against the incidence of water disasters in the mine. This paper proposes a random-forest-based partitioning model of the water richness of phosphate mine roofs in karst areas based on the random forest intelligence algorithm in machine learning. Taking a productive phosphate mine in southern China as a typical case, seven main assessment indicators affecting the water richness of the phosphate mine roof aquifer were determined. The proposed random forest model was utilized to determine the weight of each evaluation index, and the water richness of the karst aquifer on the roof of this phosphate mine was studied by zoning. The whole structure of the mine is highly water-rich, with strongly water-rich areas mainly concentrated in the central and northeastern part of the mine. The water-richness fitting rates (WFP) introduced for validation were all in agreement with the evaluation results, and the constructed model met the accuracy requirements. The study’s findings can serve as a guide for mine design and water-disaster warnings in karst regions.

Keywords: water-richness evaluation; random forest model; karst aquifer; phosphate mining; machine learning (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/18/13852/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/18/13852/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:18:p:13852-:d:1242145

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().