Coal Mine Water Inflow Prediction Model Based on Multi-Factor Pearson Correlation Analysis
Source abstract
Abstract
Since geological structures around coal mines are complex, sudden coal mine water inflow is seriously threatening coal mining safety. To improve the accuracy of predicting coal mine water inflow, a multi-source dataset is collected to develop a coal mine water inflow prediction model based on multi-factor Pearson correlation analysis, where a convolutional neural network and bidirectional long short-term memory neural network are adopted to extract features from time-series data. To validate the performance of the present prediction model, a case study is conducted, where the predicted coal mine water inflow is close to the collected coal mine water inflow. Meanwhile, compared to other prediction models, the present prediction model can predict the magnitude and development trend of coal mine water inflow in the next 8 h more accurately, where the mean absolute percentage error is 5.76% and the correlation coefficient is 0.922.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geoscience and Mining Technology · Coal Properties and Utilization · Geomechanics and Mining Engineering
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Engineering, China University of Geosciences, Wuhan 430074, China
China Coal Science and Industry Xi’an Research Institute Co., Ltd., Xi’an 710054, China
General Research Institute of Coal Science, Beijing 100013, China
Funding
National Natural Science Foundation of China · National Key R&D Program of China · Open Fund Project of Shaanxi Provincial Key Laboratory of Coal Mine Water Hazard Prevention and Control Technology · Fundamental Research Funds for the Central Universities, China University of Geosciences · Open Fund Project of State Key Laboratory of Gas Disaster Detecting, Preventing and Emergency Controlling
References (26)
Show source-provided references
1. Dong, D., Sun, W., and Li, H. (2010, January 16–18). A decision support system for water inrush in coalmine based on BN (Bayesian network) and GIS. Proceedings of the 2nd International Conference on Computer Engineering and Technology, Chengdu, China.10.1109/ICCET.2010.5486334 ↗
2. Li, F., and Zheng, J. (2010, January 17–18). The prediction and forecast of coal floor water-inrush based on GIS: A case study. Proceedings of the 2nd Conference on Environmental Science and Information Application Technology, Wuhan, China.
3. An approach for water-inrush risk assessment of deep coal seam mining: A case study in Xinlongzhuang coal mine10.1007/s11356-020-10225-0 ↗
4. Xie, D. (2023). Prediction of the water inrush risk from an overlying separation layer in the thick overburden of a thick coal seam. Sustainability, 15.10.3390/su151813988 ↗
5. Yang, Z., Lv, H., and Wang, X. (2023). Classification of Water Source in Coal Mine Based on PCA-GA-ET. Water, 15.10.3390/w15101945 ↗
6. A deep learning-based data-driven approach for predicting mining water inrush from coal seam floor using micro-seismic monitoring data10.1109/TGRS.2023.3331904 ↗
7. Liu, W., Ren, Y., and Meng, X. (2024). Analysis of Potential Water Inflow Rates at an Underground Coal Mine Using a WOA-CNN-SVM Approach. Water, 16.10.3390/w16060813 ↗
8. Hybrid Approach for Early Warning of Mine Water: Energy Density Based Identification of Water-Conducting Channels Combined with Water Inflow Prediction By SA-LSTM
9. Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas10.1016/j.jhydrol.2018.04.065 ↗
10. Deep learning with long short-term memory for time series prediction10.1109/MCOM.2019.1800155 ↗
11. EA-LSTM: Evolutionary attention-based LSTM for time series prediction10.1016/j.knosys.2019.05.028 ↗
12. Transductive LSTM for time-series prediction: An application to weather forecasting10.1016/j.neunet.2019.12.030 ↗
13. Optimizing LSTM for time series prediction in Indian stock market10.1016/j.procs.2020.03.257 ↗
14. A survey on long short-term memory networks for time series prediction10.1016/j.procir.2021.03.088 ↗
15. Reconstruction of missing groundwater level data by using Long Short-Term Memory (LSTM) deep neural network10.1016/j.jhydrol.2020.125776 ↗
16. Chen, Y., Li, Z., and Li, H. (2022, January 26–28). Attention-GRU Based Method for Predicting Coal Mine Water Surge Analysis. Proceedings of the 7th International Conference on Image, Vision and Computing, Xi’an, China.10.1109/ICIVC55077.2022.9886453 ↗
17. A novel multivariate time series prediction of crucial water quality parameters with Long Short-Term Memory (LSTM) networks10.1016/j.jconhyd.2023.104262 ↗
18. Time series prediction based on LSTM-attention-LSTM model10.1109/ACCESS.2023.3276628 ↗
19. Application of robust deep learning models to predict mine water inflow: Implication for groundwater environment management10.1016/j.scitotenv.2023.162056 ↗
20. Shi, J., Wang, S., and Qu, P. (2024). Time series prediction model using LSTM-Transformer neural network for mine water inflow. Sci. Rep., 14.10.1038/s41598-024-69418-z ↗
21. Chen, W., He, H., and Liu, J. (2023). Photovoltaic power prediction based on sliced bidirectional long short term memory and attention mechanism. Front. Energy Res., 11.10.3389/fenrg.2023.1123558 ↗
22. Wang, Y., Yao, Y., and Zou, Q. (2024). Forecasting a Short-Term Photovoltaic Power Model Based on Improved Snake Optimization, Convolutional Neural Network, and Bidirectional Long Short-Term Memory Network. Sensors, 24.10.2139/ssrn.4823036 ↗
23. Recognition Algorithm of Dangerous Goods in Security Inspection Based on Multi-Layer Attention Mechanism
24. A General Survey on Attention Mechanisms in Deep Learning10.1109/TKDE.2021.3126456 ↗
25. A Pearson correlation-based adaptive variable grouping method for large-scale multi-objective optimization10.1016/j.ins.2023.02.055 ↗
26. Wang, X., Yao, Y., and Li, Z. (2024). Protocol Reverse Analysis of Ethernet for Control Automation Technology Based on Sequence Alignment and Pearson Correlation Coefficient. Sensors, 24.10.3390/s24247922 ↗