首页|期刊简介|投稿指南|分类索引|刊文选读|订阅指南|资料|样刊邮寄查询|常见问题解答|联系我们
刘海军,单维锋,耿贵珍. 基于溶解氡数据和长短期记忆网络的地震预报[J]. 科学技术与工程, 2020, 20(10): 4029-4035.
刘海军,单维锋,耿贵珍.Prediction of earthquake precursor data with Long Short-Term Memory ——take dissolved gas radon concentration data from Guzan earthquake station as an example[J].Science Technology and Engineering,2020,20(10):4029-4035.
基于溶解氡数据和长短期记忆网络的地震预报
Prediction of earthquake precursor data with Long Short-Term Memory ——take dissolved gas radon concentration data from Guzan earthquake station as an example
投稿时间:2018-12-03  修订日期:2019-03-24
DOI:
中文关键词:  时间序列分析 长短期记忆网络 前兆数据 趋势预测 循环神经网络
英文关键词:time series analysis long-short-term network precursor data trend prediction RNN
基金项目:中国地震局教师科研基金项目(20150110)
        
作者单位
刘海军 防灾科技学院应急管理学院
单维锋 防灾科技学院应急管理学院
耿贵珍 防灾科技学院经济管理学院
摘要点击次数: 119
全文下载次数: 44
中文摘要:
      溶解气氡浓度异常为可靠地震前兆,通过对历史观测数据进行建模,预测溶解气氡未来趋势,是快速检测溶解气氡浓度异常、研究震-氡机制的前提。溶解气氡浓度数据为典型的时间序列数据,传统的时间序列预测技术主要为AR方法和ARMA方法。这些方法以线性方法为主,其拟合精度有限。论文采用目前最流行的深度学习技术LSTM模型对姑咱地震台4年溶解气氡日观测数据集溶解气氡浓度数据进行建模,采用90%的数据作为训练数据训练LSTM网络,10%的数据作为预测数据,采用RMSE评价指标来评价模型的效果。在该数据集上,LSTM的预测误差RMSE值为0.2915,明显低于AR和ARMA方法。该结果表明,LSTM的预测精度高于传统的AR、ARMA方法
英文摘要:
      Abnormal dissolved gas radon concentrations are reliable seismic anomaly. Studying potential patterns from historical data to predict future trend helps to quickly detect anomaly, which is vital for research on seismo-radon mechanism. Dissolved gas radon concentration observations are typical time series data. Traditional methods to solve this problem are mainly based on linear algorithms, such as Auto-Regressive (AR) model and Auto-Regressive and Moving Average (ARMA) model, which are of limit fitting ability to make precise prediction. This paper adopted the state of the art deep learning technique, Long Short-Term Memory (LSTM), to model dissolved gas radon concentration. In our experiment, we selected 4 years of dissolved gas radon concentration data collected from Guzan seismo station. We selected 90% of the data to train our model and 10% of the data to test our model. Comparison experiments were carried out on the same dataset with Auto-Regressive (AR) model and Auto-Regressive and Moving Average (ARMA) Model. Results showed that LSTM gains smaller RSME than AR and ARMA, which means that LSTM gain higher precision than AR and ARMA in our dataset.
查看全文  查看/发表评论  下载PDF阅读器
关闭
你是第30495863位访问者
版权所有:科学技术与工程编辑部
主管:中国科学技术协会    主办:中国技术经济学会
Tel:(010)62118920 E-mail:stae@vip.163.com
京ICP备05035734号-4
技术支持:本系统由北京勤云科技发展有限公司设计

京公网安备 11010802029091号