Monitoring and early warning of a metal mine tailings pond based on a deep learning bidirectional recurrent long and short memory network

• Published in: PloS one Vol. 17; no. 10; p. e0273073
• Main Authors: Jing, Zhanjie, Gao, Xiaohong
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 13.10.2022; Public Library of Science (PLoS)
• Subjects: Algorithms; Analysis; Artificial intelligence; Biology and Life Sciences; Computational linguistics; Computer and Information Sciences; Data processing; Deep Learning; Early warning systems; Earth Sciences; Earthquakes; Emergency communications systems; Environmental Monitoring; Failure; Fault diagnosis; Infiltration; Language processing; Lateral displacement; Machine learning; Metals; Mine tailings; Mine wastes; Mineral resources; Modelling; Monitoring; Multilayer perceptrons; Multivariate analysis; Natural language interfaces; Neural networks; Optimization; Physical Sciences; Ponds; Prediction models; Rain; Research and Analysis Methods; Reservoir management; Reservoirs; Risk management; Root-mean-square errors; Safety management; Shear strength; Storm damage; Tailings; Technical services; Time series; Warning systems; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0273073

The effective monitoring and early warning capability of metal mine tailings ponds can improve the associated safety risk management level. The infiltration line is an important core index of tailings pond stability. In this paper, a tailings pond monitoring and early warning system, which provides technical support for the design and daily management of tailings reservoir early warning systems, is constructed. Based on a deep learning bidirectional recurrent long and short memory network, an infiltration line prediction model with univariate input and an infiltration line prediction model with multivariate input are proposed. The data adopted are those from four monitoring points of the same cross-section at different positions and data from one adjacent internal lateral displacement and internal vertical displacement monitoring point. Using the adaptive moment estimation (Adam) optimization algorithm and the root mean square error (RMSE) model evaluation metric, the multilayer perceptron model, univariate input model, and multivariate input model are compared. This work shows that their RMSEs are 0.10611, 0.09966, and 0.11955, respectively.