Optimizing identification of mine water inrush source with manifold reduction and semi-supervised learning using improved autoencoder

To enhance the accuracy of identifying water sources in mine inrush incidents, this study, taking the Shengquan coal mine in Shandong, China, as a case study, proposes a novel water source identification model based on an improved autoencoder—the “Masked Autoencoder-based Classifier” model. This mod...

Full description

Saved in:
Bibliographic Details
Published in:Stochastic environmental research and risk assessment Vol. 38; no. 5; pp. 1701 - 1720
Main Authors: Wang, Shichao, Zhai, Peihe, Yu, Xiaoge, Han, Jin, Shi, Longqing
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.05.2024
Springer Nature B.V
Subjects:
Accuracy
Aquatic Pollution
Aquifers
Case studies
Chemistry and Earth Sciences
Classifiers
Coal mines
Coal mining
Computational Intelligence
Computer Science
Earth and Environmental Science
Earth science
Earth Sciences
Environment
Environmental research
Groundwater
Groundwater data
Identification
Machine learning
Math. Appl. in Environmental Science
Mine drainage
Mine waters
Neural networks
Original Paper
Physics
Principal components analysis
Probability Theory and Stochastic Processes
Risk assessment
Semi-supervised learning
Statistics for Engineering
Waste Water Technology
Water analysis
Water inrush
Water Management
Water Pollution Control
Water sampling
Water source identification
Semi-supervised learning
Autoencoder
Manifold reduction
Mine water
ISSN:1436-3240, 1436-3259
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To enhance the accuracy of identifying water sources in mine inrush incidents, this study, taking the Shengquan coal mine in Shandong, China, as a case study, proposes a novel water source identification model based on an improved autoencoder—the “Masked Autoencoder-based Classifier” model. This model, through a unique autoencoder framework and a custom ‘masked_loss’ loss function, achieves semi-supervised learning and dimensionality reduction of groundwater sample ionic data. By configuring the hidden layers, the classifier component of the model directly receives data processed by the encoder component. This not only improves the model's performance but also optimizes its complexity. Through an evaluation of the model's fitting effectiveness, our model achieved an average accuracy of 88.8% across 20 runs, with precision, recall, F1-score, and MCC reaching 88.1%, 80.6%, 0.827, and 0.833, respectively, significantly outperforming other classic models. The model successfully identified the sources of three sets of inrush water samples, with a high number of successful runs and clear average probabilities. This work contributes not only to the field of mine water inrush source identification but also offers a new perspective for the broader field of machine learning.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1436-3240
1436-3259
DOI:10.1007/s00477-023-02647-2