Abstract

Predicting the earthquake is an important problem in the earth science community. Several models have been proposed to predict the time for next earthquake. However, all those methods are based on traditional machine learning algorithms. Recently, deep learning based models have obtained breakthrough achievements over traditional machine learning models in various data processing tasks. Hence, in this paper, we propose and analyze different deep learning based models to predict the time to the next earthquake. From our knowledge, this is the first work in which deep learning is used to predict earthquakes. We perform several experiments on the proposed models and compare them in terms of the mean absolute error (MAE) measurement. From the different experiments, we found that the GRU-Conv1D model obtains better MAE value than that of other models.

1. 1. This material content is developed to serve as a GUIDE for students to conduct academic research work
2. 2. As a source for additional understanding of the subject.
3. 3. As a source for ideas for your own research work (if properly referenced).
4. 4. For PROPER paraphrasing (see your university definition of plagiarism and acceptable paraphrase)
5. 5. Direct citing (if referenced properly)
Thank you so much for your respect to the authors copyright.