共 33 条
Application of robust deep learning models to predict mine water inflow: Implication for groundwater environment management
被引:23
|作者:
Yang, Songlin
[1
]
Lian, Huiqing
[3
]
Xu, Bin
[3
]
Thanh, Hung Vo
[4
,5
]
Chen, Wei
[1
]
Yin, Huichao
[1
,6
]
Dai, Zhenxue
[1
,2
]
机构:
[1] Jilin Univ, Coll Civil Engn, Changchun, Peoples R China
[2] Jilin Univ, Key Lab Groundwater Resources & Environm, Minist Educ, Changchun, Peoples R China
[3] North China Inst Sci & Technol, Hebei State Key Lab Mine Disaster Prevent, Yanjiao 101601, Peoples R China
[4] Van Lang Univ, Inst Computat Sci & Arti fi cial Intelligence, Lab Computat Mech, Ho Chi Minh City, Vietnam
[5] Van Lang Univ, Fac Mech Elect & Comp Engn, Sch Technol, Ho Chi Minh City, Vietnam
[6] Inst Disaster Prevent, Sch Informat Engn, Langfang 065201, Peoples R China
基金:
中国国家自然科学基金;
关键词:
Mine water inflow prediction;
Difference method;
Deep learning models;
Temporal convolutional networks;
Long Short-Term Memory;
TEMPORAL CONVOLUTIONAL NETWORKS;
NEURAL-NETWORK;
LSTM;
D O I:
10.1016/j.scitotenv.2023.162056
中图分类号:
X [环境科学、安全科学];
学科分类号:
08 ;
0830 ;
摘要:
Traditional mine water inflow prediction is characterized by a high degree of uncertainty in model parameters and complex mechanisms involved in the water inflow process. Data-driven models play a key role in predicting inflow mechanisms without considering physical changes. However, the existing models are limited by nonlinearity and non-stationarity. Thus, the principal objective of this study was to propose two robust models, the DIFF-TCN model and the DIFF-LSTM model, for predicting the average water inflow per day. The models consist of three methods, namely Difference Method (DIFF), Temporal Convolutional Neural Network (TCN), and Long Short-Term Memory Neural Network (LSTM). When applied to the Tingnan Coal Mine, Shanxi Province, China, the DIFF-TCN performs bet-ter in predicting the average daily water inflow, the model has a MAE of 5.88 m3/h, RMSE of 6.85 m3/h and R2 of 0.96 in the test stage of the water inflow event. Comparison with the other deep learning models (with similar complex structures) and traditional time series model shows the superiority of our proposed DIFF-TCN model. The SHAP value is used to explain the contribution of each model input to the predicted values, and it indicates that the historical time of water inflow data are the most important input, and the advance distance and the groundwater level data also contribute to the model predictions, but groundwater level data for some periods in the past may have a detrimental effect on the model. The findings of this study can provide better understanding about potential of robust deep learning models for smart hydrological forecasting, and they can also provide technical guidance for mining safety production and protection of water resources and water environment around the mining area.
引用
收藏
页数:15
相关论文