Abstract
If only we could anticipate an earthquake, even if it were only one day in advance, many lives and properties could be saved. But to date, the ability to forecast earthquakes has eluded us. This paper draws its inspiration from the success in recent decades in weather forecasts. This paper applies recent developments in mathematical theories and advancements in machine learning tools to simulate the erratic behaviour of earthquakes. In particular, this paper shows that the application of the deep learning tool, LSTM, could effectively forecast the future outcomes of chaotic systems.



![Author ORCID: We display the ORCID iD icon alongside authors names on our website to acknowledge that the ORCiD has been authenticated when entered by the user. To view the users ORCiD record click the icon. [opens in a new tab]](https://www.cambridge.org/engage/assets/public/coe/logo/orcid.png)