Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network

Abnormal changes in groundwater level are key indicators of seismic precursors. Before an earthquake, the groundwater level often shows varying degrees of abnormality. These anomalies typically manifest as a sudden rise or fall in groundwater levels and will last for a period of time. On Jul. 12, 20...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinfang Chen, Lijia Yang, Xin Liao, Hanqing Zhao, Shiwei Wang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10767234/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850138806668230656
author Xinfang Chen
Lijia Yang
Xin Liao
Hanqing Zhao
Shiwei Wang
author_facet Xinfang Chen
Lijia Yang
Xin Liao
Hanqing Zhao
Shiwei Wang
author_sort Xinfang Chen
collection DOAJ
description Abnormal changes in groundwater level are key indicators of seismic precursors. Before an earthquake, the groundwater level often shows varying degrees of abnormality. These anomalies typically manifest as a sudden rise or fall in groundwater levels and will last for a period of time. On Jul. 12, 2020, at 6:38 AM, a 5.1 magnitude earthquake occurred in Guye District, Tangshan City, Hebei Province, China (39.78°N, 118.44°E). This study uses this earthquake as a case study to analyze the groundwater level data from two observation wells, the Zhaogezhuang well and Yutian Ji 03 well. To accurately identify seismic precursor anomalies, the groundwater level data were divided into seismically active (SA) and seismically inactive (non-SA) periods, forming the basis for dataset segmentation. This paper proposes a TCN-LSTM-Attention model that combines the advantages of effective feature extraction with TCN and capturing complex temporal dependencies with LSTM. Experiments show that the designed model has strong abilities in predicting groundwater levels and identifying earthquake precursor anomalies. To enhance the accuracy of anomaly detection, this study employed an Exponentially Weighted Moving Average (EWMA) control chart to precisely pinpoint the onset of anomalies. Through validation with earthquakes in Jianshui County, Yunnan Province, China, the model effectively identified groundwater level anomalies under different geological conditions, confirming its generalization and practicality. Finally, this article conducted cross validation on the designed model, which has improved its reliability in practical applications. This study has certain scientific innovation and practical value in earthquake precursor analysis, providing new technical support and analysis methods for the development of earthquake warning technology and disaster prevention and reduction work.
format Article
id doaj-art-5c0240d2d5b74bbb96c12de1088cb618
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-5c0240d2d5b74bbb96c12de1088cb6182025-08-20T02:30:30ZengIEEEIEEE Access2169-35362024-01-011217669617671810.1109/ACCESS.2024.350594210767234Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention NetworkXinfang Chen0https://orcid.org/0000-0001-6899-5858Lijia Yang1https://orcid.org/0009-0002-5667-0866Xin Liao2Hanqing Zhao3Shiwei Wang4https://orcid.org/0009-0006-0232-3219College of Information Engineering, Institute of Disaster Prevention, Sanhe, Hebei, ChinaCollege of Information Engineering, Institute of Disaster Prevention, Sanhe, Hebei, ChinaCollege of Information Engineering, Institute of Disaster Prevention, Sanhe, Hebei, ChinaCollege of Information Engineering, Institute of Disaster Prevention, Sanhe, Hebei, ChinaCollege of Information Engineering, Institute of Disaster Prevention, Sanhe, Hebei, ChinaAbnormal changes in groundwater level are key indicators of seismic precursors. Before an earthquake, the groundwater level often shows varying degrees of abnormality. These anomalies typically manifest as a sudden rise or fall in groundwater levels and will last for a period of time. On Jul. 12, 2020, at 6:38 AM, a 5.1 magnitude earthquake occurred in Guye District, Tangshan City, Hebei Province, China (39.78°N, 118.44°E). This study uses this earthquake as a case study to analyze the groundwater level data from two observation wells, the Zhaogezhuang well and Yutian Ji 03 well. To accurately identify seismic precursor anomalies, the groundwater level data were divided into seismically active (SA) and seismically inactive (non-SA) periods, forming the basis for dataset segmentation. This paper proposes a TCN-LSTM-Attention model that combines the advantages of effective feature extraction with TCN and capturing complex temporal dependencies with LSTM. Experiments show that the designed model has strong abilities in predicting groundwater levels and identifying earthquake precursor anomalies. To enhance the accuracy of anomaly detection, this study employed an Exponentially Weighted Moving Average (EWMA) control chart to precisely pinpoint the onset of anomalies. Through validation with earthquakes in Jianshui County, Yunnan Province, China, the model effectively identified groundwater level anomalies under different geological conditions, confirming its generalization and practicality. Finally, this article conducted cross validation on the designed model, which has improved its reliability in practical applications. This study has certain scientific innovation and practical value in earthquake precursor analysis, providing new technical support and analysis methods for the development of earthquake warning technology and disaster prevention and reduction work.https://ieeexplore.ieee.org/document/10767234/Abnormal earthquake precursorsEWMA control chartgroundwater level predictionseismically active periodTCN-LSTM-Attention
spellingShingle Xinfang Chen
Lijia Yang
Xin Liao
Hanqing Zhao
Shiwei Wang
Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network
IEEE Access
Abnormal earthquake precursors
EWMA control chart
groundwater level prediction
seismically active period
TCN-LSTM-Attention
title Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network
title_full Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network
title_fullStr Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network
title_full_unstemmed Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network
title_short Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network
title_sort groundwater level prediction and earthquake precursor anomaly analysis based on tcn lstm attention network
topic Abnormal earthquake precursors
EWMA control chart
groundwater level prediction
seismically active period
TCN-LSTM-Attention
url https://ieeexplore.ieee.org/document/10767234/
work_keys_str_mv AT xinfangchen groundwaterlevelpredictionandearthquakeprecursoranomalyanalysisbasedontcnlstmattentionnetwork
AT lijiayang groundwaterlevelpredictionandearthquakeprecursoranomalyanalysisbasedontcnlstmattentionnetwork
AT xinliao groundwaterlevelpredictionandearthquakeprecursoranomalyanalysisbasedontcnlstmattentionnetwork
AT hanqingzhao groundwaterlevelpredictionandearthquakeprecursoranomalyanalysisbasedontcnlstmattentionnetwork
AT shiweiwang groundwaterlevelpredictionandearthquakeprecursoranomalyanalysisbasedontcnlstmattentionnetwork