Journal Article10.1007/s11227-023-05369-y
A CNN-BiLSTM model with attention mechanism for earthquake prediction
Parisa Kavianpour,Mohammadreza Kavianpour,Ehsan Jahani,Amin Ramezani +3 more
TL;DR: A novel CNN-BiLSTM model with attention mechanism for earthquake prediction achieves high accuracy in predicting the maximum magnitude and number of earthquakes in the next month.
read more
Abstract: Earthquakes, as natural phenomena, have consistently caused damage and loss of human life throughout history. Earthquake prediction is an essential aspect of any society's plans and can increase public preparedness and reduce damage to a great extent. Despite advances in computing systems and deep learning methods, no substantial achievements have been made in earthquake prediction. One of the most important reasons is that the earthquake's nonlinear and chaotic behavior makes it hard to train the deep learning method. To tackle this drawback, this study tries to take an effective step in improving the performance of prediction results by employing a novel method in earthquake prediction. This method employs a deep learning model based on convolutional neural networks (CNN), bi-directional long short-term memory (BiLSTM), and an attention mechanism, as well as a zero-order hold (ZOH) pre-processing methodology. This study aims to predict the maximum magnitude and number of earthquakes in the next month with the least error. The proposed method was evaluated by an earthquake dataset from nine distinct regions of China. The results reveal that the proposed method outperforms other prediction methods in terms of performance and generalization.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Fig. 4. The flow chart of the proposed method 
TABLE II STRUCTURES OF PROPOSED METHOD 
Fig. 5. A visual representation of the division of China’s nine study areas 
Fig. 7. The comparison of proposed model and deep learning models for number of earthquake prediction in region 5. 
TABLE I RELATED WORKS ON EARTHQUAKE PREDICTION 
Fig. 1. schematic diagram of bidirectional LSTM
Citations
Improving earthquake prediction accuracy in Los Angeles with machine learning
Cemil Emre Yavas,Lei Chen,Christopher Kadlec,Yiming Ji +3 more
TL;DR: This research improves earthquake prediction accuracy in Los Angeles using machine learning and neural networks, achieving high accuracy with the Random Forest model in predicting maximum earthquake magnitude within 30 days.
4
DACA: A domain adaptive fault diagnosis approach with class-aware based on cross-domain extreme imbalance data
Y. G. Li,Ying Zhu,Yang Yu,Runze Mao,Li Ye,Бо Лю,Ruochen Liu,Tao Lang,Jinglin Zhang +8 more
TL;DR: This study introduces DACA, a novel domain adaptation framework addressing extreme imbalance data in fault diagnosis, leveraging adversarial clustering, cross-domain alignment, category reweighting, and re-margining to enhance minority category recognition and robust decision boundaries.
3
The Development and Validation of a Lightweight Automated Stock Trading System Using Deep Learning Models: Employing Technical Analysis Methods
Shimeng Yu,Sung‐Byung Yang,Sang-Hyeak Yoon +2 more
- 17 Aug 2023
TL;DR: The development and validation of a lightweight automated stock trading system using deep learning models employing technical analysis methods significantly reduces analysis time and empowers individual investors with an efficient approach to identify potential gains or losses.
3
Intelligent BiLSTM-Attention-IBPNN Method for Anomaly Detection in Financial Auditing
Shuixiang Wang
TL;DR: A new intelligent anomaly detection method is developed that combines the advantages of bidirectional long-short term memory (BiLSTM), improved backpropagation neural network (IBPNN) and an attention mechanism and significantly improves the anomaly detection quality and efficiency for financial auditing.
3
References
Short-Term Load Forecasting Based on CNN-BiLSTM with Bayesian Optimization and Attention Mechanism
Kai Miao,Qiang Hua,Huifeng Shi +2 more
- 28 Dec 2020
TL;DR: In this article, a short-term load forecasting based on Convolutional Neural Networks and Bidirectional Long Short-Term Memory (CNN-BiLSTM) with Bayesian Optimization (BO) and Attention Mechanism (AM) was proposed.
23
A location-dependent earthquake prediction using recurrent neural network algorithms
TL;DR: In this article , a location-dependent earthquake prediction based on recurrent neural network algorithms is proposed, which consists of clustering the seismic dataset based on its geographical parameters (longitude and latitude) using the K-means algorithm.
23
Modified-Fibonacci-Dual-Lucas method for earthquake prediction
Anthony C. Boucouvalas,M. Gkasios,Nikos Tselikas,G. Drakatos +3 more
- 19 Jun 2015
TL;DR: In this article, an improvement modification to the reported FDL method, the MFDL method is presented, which performs better than the FDL, with the important difference that the starting seed date is a trigger planetary aspect prior to the earthquake.
14
Exploration on coal mining-induced rockburst prediction using Internet of things and deep neural network
TL;DR: The proposed CM-induced rockburst-oriented dynamic pressure prediction system provides some ideas for applying IoT and deep neural network technology in the CM industry.
9
Earthquake probability prediction in Sumatra Island using Poisson Hidden Markov Model (HMM)
Marisa,Ukur Arianto Sembiring,Helena Margaretha +2 more
- 19 Dec 2019
TL;DR: In this article, the authors used the Autocorrelation Function (ACF) of earthquake data in Sumatera to estimate the probability of an earthquake occurring in Sumatra Island.
8