Anomaly Detection Using Machine Learning in Hydrochemical Data From Hot Springs: Implications for Earthquake Prediction
Abstract This study explores the potential of machine learning algorithms for earthquake prediction, utilizing fluid chemical anomaly data from hot springs. Six hot springs, located within an active fault zone along the southeastern coast of China, were carefully chosen as hydrochemical monitoring s...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-06-01
|
| Series: | Water Resources Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023WR034748 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849422833599381504 |
|---|---|
| author | Ruijie Zhu Fengtian Yang Xiaocheng Zhou Jiao Tian Yongxian Zhang Miao He Jingchao Li Jinyuan Dong Ying Li |
| author_facet | Ruijie Zhu Fengtian Yang Xiaocheng Zhou Jiao Tian Yongxian Zhang Miao He Jingchao Li Jinyuan Dong Ying Li |
| author_sort | Ruijie Zhu |
| collection | DOAJ |
| description | Abstract This study explores the potential of machine learning algorithms for earthquake prediction, utilizing fluid chemical anomaly data from hot springs. Six hot springs, located within an active fault zone along the southeastern coast of China, were carefully chosen as hydrochemical monitoring sites for an extended period of two and a half years. Using this data, a prediction model integrating six algorithms was developed to forecast M ≥ 5 earthquakes in Taiwan. The model's performance was validated against recorded earthquake events, and the factors influencing its predictive capability were analyzed. Our comprehensive analysis conclusively demonstrates the superiority of machine learning algorithms over traditional statistical methods for earthquake prediction. Additionally, including sampling time in the data sets significantly improves the model's predictive performance. However, it is important to note that the model's predictive performance varies across different hot spring and indicators type, highlighting the importance of identifying optimal indicators for specific scenarios. The model parameters, including the anomaly detection rate (P) and earthquake response time threshold (M), significantly impact the model's predictive capabilities. Therefore, adjustments are needed to optimize the model's performance for practical use. Despite limitations such as the inability to differentiate pre‐earthquake anomalies from post‐earthquake anomalies and pinpoint the precise location of earthquakes, this study successfully showcases the potential of machine learning algorithms in earthquake prediction, paving the way for further research and improved prediction methods. |
| format | Article |
| id | doaj-art-04a07f3dfd99410697cf30cf6098e66a |
| institution | Kabale University |
| issn | 0043-1397 1944-7973 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Water Resources Research |
| spelling | doaj-art-04a07f3dfd99410697cf30cf6098e66a2025-08-20T03:30:55ZengWileyWater Resources Research0043-13971944-79732024-06-01606n/an/a10.1029/2023WR034748Anomaly Detection Using Machine Learning in Hydrochemical Data From Hot Springs: Implications for Earthquake PredictionRuijie Zhu0Fengtian Yang1Xiaocheng Zhou2Jiao Tian3Yongxian Zhang4Miao He5Jingchao Li6Jinyuan Dong7Ying Li8Key Laboratory of Groundwater Resources and Environment Ministry of Education Jilin University Changchun ChinaKey Laboratory of Groundwater Resources and Environment Ministry of Education Jilin University Changchun ChinaUnited Laboratory of High‐Pressure Physics and Earthquake Science Institute of Earthquake Forecasting China Earthquake Administration Beijing ChinaUnited Laboratory of High‐Pressure Physics and Earthquake Science Institute of Earthquake Forecasting China Earthquake Administration Beijing ChinaUnited Laboratory of High‐Pressure Physics and Earthquake Science Institute of Earthquake Forecasting China Earthquake Administration Beijing ChinaUnited Laboratory of High‐Pressure Physics and Earthquake Science Institute of Earthquake Forecasting China Earthquake Administration Beijing ChinaUnited Laboratory of High‐Pressure Physics and Earthquake Science Institute of Earthquake Forecasting China Earthquake Administration Beijing ChinaUnited Laboratory of High‐Pressure Physics and Earthquake Science Institute of Earthquake Forecasting China Earthquake Administration Beijing ChinaUnited Laboratory of High‐Pressure Physics and Earthquake Science Institute of Earthquake Forecasting China Earthquake Administration Beijing ChinaAbstract This study explores the potential of machine learning algorithms for earthquake prediction, utilizing fluid chemical anomaly data from hot springs. Six hot springs, located within an active fault zone along the southeastern coast of China, were carefully chosen as hydrochemical monitoring sites for an extended period of two and a half years. Using this data, a prediction model integrating six algorithms was developed to forecast M ≥ 5 earthquakes in Taiwan. The model's performance was validated against recorded earthquake events, and the factors influencing its predictive capability were analyzed. Our comprehensive analysis conclusively demonstrates the superiority of machine learning algorithms over traditional statistical methods for earthquake prediction. Additionally, including sampling time in the data sets significantly improves the model's predictive performance. However, it is important to note that the model's predictive performance varies across different hot spring and indicators type, highlighting the importance of identifying optimal indicators for specific scenarios. The model parameters, including the anomaly detection rate (P) and earthquake response time threshold (M), significantly impact the model's predictive capabilities. Therefore, adjustments are needed to optimize the model's performance for practical use. Despite limitations such as the inability to differentiate pre‐earthquake anomalies from post‐earthquake anomalies and pinpoint the precise location of earthquakes, this study successfully showcases the potential of machine learning algorithms in earthquake prediction, paving the way for further research and improved prediction methods.https://doi.org/10.1029/2023WR034748earthquake predictionhot springhydrogeochemical anomaliesmachine learninganomaly detection algorithms |
| spellingShingle | Ruijie Zhu Fengtian Yang Xiaocheng Zhou Jiao Tian Yongxian Zhang Miao He Jingchao Li Jinyuan Dong Ying Li Anomaly Detection Using Machine Learning in Hydrochemical Data From Hot Springs: Implications for Earthquake Prediction Water Resources Research earthquake prediction hot spring hydrogeochemical anomalies machine learning anomaly detection algorithms |
| title | Anomaly Detection Using Machine Learning in Hydrochemical Data From Hot Springs: Implications for Earthquake Prediction |
| title_full | Anomaly Detection Using Machine Learning in Hydrochemical Data From Hot Springs: Implications for Earthquake Prediction |
| title_fullStr | Anomaly Detection Using Machine Learning in Hydrochemical Data From Hot Springs: Implications for Earthquake Prediction |
| title_full_unstemmed | Anomaly Detection Using Machine Learning in Hydrochemical Data From Hot Springs: Implications for Earthquake Prediction |
| title_short | Anomaly Detection Using Machine Learning in Hydrochemical Data From Hot Springs: Implications for Earthquake Prediction |
| title_sort | anomaly detection using machine learning in hydrochemical data from hot springs implications for earthquake prediction |
| topic | earthquake prediction hot spring hydrogeochemical anomalies machine learning anomaly detection algorithms |
| url | https://doi.org/10.1029/2023WR034748 |
| work_keys_str_mv | AT ruijiezhu anomalydetectionusingmachinelearninginhydrochemicaldatafromhotspringsimplicationsforearthquakeprediction AT fengtianyang anomalydetectionusingmachinelearninginhydrochemicaldatafromhotspringsimplicationsforearthquakeprediction AT xiaochengzhou anomalydetectionusingmachinelearninginhydrochemicaldatafromhotspringsimplicationsforearthquakeprediction AT jiaotian anomalydetectionusingmachinelearninginhydrochemicaldatafromhotspringsimplicationsforearthquakeprediction AT yongxianzhang anomalydetectionusingmachinelearninginhydrochemicaldatafromhotspringsimplicationsforearthquakeprediction AT miaohe anomalydetectionusingmachinelearninginhydrochemicaldatafromhotspringsimplicationsforearthquakeprediction AT jingchaoli anomalydetectionusingmachinelearninginhydrochemicaldatafromhotspringsimplicationsforearthquakeprediction AT jinyuandong anomalydetectionusingmachinelearninginhydrochemicaldatafromhotspringsimplicationsforearthquakeprediction AT yingli anomalydetectionusingmachinelearninginhydrochemicaldatafromhotspringsimplicationsforearthquakeprediction |