Precursory Pattern Based Feature Extraction Techniques for Earthquake Prediction
Earthquake prediction is an important and complex task in the real world. Although many data mining-based methods have been proposed to solve this problem, the prediction accuracy is still far from satisfactory due to the deficiency of feature extraction techniques. To this end, in this paper, we pr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8654622/ |
| _version_ | 1818924067531522048 |
|---|---|
| author | Lei Zhang Langchun Si Haipeng Yang Yuanzhi Hu Jianfeng Qiu |
| author_facet | Lei Zhang Langchun Si Haipeng Yang Yuanzhi Hu Jianfeng Qiu |
| author_sort | Lei Zhang |
| collection | DOAJ |
| description | Earthquake prediction is an important and complex task in the real world. Although many data mining-based methods have been proposed to solve this problem, the prediction accuracy is still far from satisfactory due to the deficiency of feature extraction techniques. To this end, in this paper, we propose a precursory pattern-based feature extraction method to enhance the performance of earthquake prediction. Especially, the raw seismic data is firstly divided into fixed day time periods, and the magnitude of the largest earthquake in each fixed time period is labeled as the main shock. The precursory pattern is a part of the seismic sequence before the main shock, on which the existing mathematical statistic features can be directly generated as seismic indicators. Based on these precursory pattern-based features, a simple yet effective classification and regression tree algorithm is adopted to predict the label of the main shock in a pre-defined future time period. The experimental results on two historical earthquake records of the Changding-Garzê and Wudu-Mabian seismic zones of China demonstrate the effectiveness of the proposed precursory pattern-based features with the selected CART algorithm for earthquake prediction. |
| first_indexed | 2024-12-20T02:19:26Z |
| format | Article |
| id | doaj.art-32384824013842d3a6ef6385ab8af829 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T02:19:26Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-32384824013842d3a6ef6385ab8af8292022-12-21T19:56:50ZengIEEEIEEE Access2169-35362019-01-017309913100110.1109/ACCESS.2019.29022248654622Precursory Pattern Based Feature Extraction Techniques for Earthquake PredictionLei Zhang0https://orcid.org/0000-0002-6447-2053Langchun Si1Haipeng Yang2Yuanzhi Hu3Jianfeng Qiu4Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Anhui, ChinaSchool of Computer Science and Technology, Anhui University, Anhui, ChinaSchool of Computer Science and Technology, Anhui University, Anhui, ChinaSchool of Computer Science and Technology, Anhui University, Anhui, ChinaKey Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Anhui, ChinaEarthquake prediction is an important and complex task in the real world. Although many data mining-based methods have been proposed to solve this problem, the prediction accuracy is still far from satisfactory due to the deficiency of feature extraction techniques. To this end, in this paper, we propose a precursory pattern-based feature extraction method to enhance the performance of earthquake prediction. Especially, the raw seismic data is firstly divided into fixed day time periods, and the magnitude of the largest earthquake in each fixed time period is labeled as the main shock. The precursory pattern is a part of the seismic sequence before the main shock, on which the existing mathematical statistic features can be directly generated as seismic indicators. Based on these precursory pattern-based features, a simple yet effective classification and regression tree algorithm is adopted to predict the label of the main shock in a pre-defined future time period. The experimental results on two historical earthquake records of the Changding-Garzê and Wudu-Mabian seismic zones of China demonstrate the effectiveness of the proposed precursory pattern-based features with the selected CART algorithm for earthquake prediction.https://ieeexplore.ieee.org/document/8654622/Earthquake predictionpattern discoverytime seriesprecursory patternCART |
| spellingShingle | Lei Zhang Langchun Si Haipeng Yang Yuanzhi Hu Jianfeng Qiu Precursory Pattern Based Feature Extraction Techniques for Earthquake Prediction IEEE Access Earthquake prediction pattern discovery time series precursory pattern CART |
| title | Precursory Pattern Based Feature Extraction Techniques for Earthquake Prediction |
| title_full | Precursory Pattern Based Feature Extraction Techniques for Earthquake Prediction |
| title_fullStr | Precursory Pattern Based Feature Extraction Techniques for Earthquake Prediction |
| title_full_unstemmed | Precursory Pattern Based Feature Extraction Techniques for Earthquake Prediction |
| title_short | Precursory Pattern Based Feature Extraction Techniques for Earthquake Prediction |
| title_sort | precursory pattern based feature extraction techniques for earthquake prediction |
| topic | Earthquake prediction pattern discovery time series precursory pattern CART |
| url | https://ieeexplore.ieee.org/document/8654622/ |
| work_keys_str_mv | AT leizhang precursorypatternbasedfeatureextractiontechniquesforearthquakeprediction AT langchunsi precursorypatternbasedfeatureextractiontechniquesforearthquakeprediction AT haipengyang precursorypatternbasedfeatureextractiontechniquesforearthquakeprediction AT yuanzhihu precursorypatternbasedfeatureextractiontechniquesforearthquakeprediction AT jianfengqiu precursorypatternbasedfeatureextractiontechniquesforearthquakeprediction |