# Recurrent Convolutional Neural Networks help to predict location of Earthquakes

arXiv: https://arxiv.org/abs/2004.09140 · HTML: https://mlsanity.com/paper/2004.09140/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [Similarity learning for wells based on logging data](https://mlsanity.com/paper/2202.05583/) (2022)
- [Long-term drought prediction using deep neural networks based on geospatial weather data](https://mlsanity.com/paper/2309.06212/) (2023)
- [A CNN-BiLSTM Model with Attention Mechanism for Earthquake Prediction](https://mlsanity.com/paper/2112.13444/) (2021)
- [MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data](https://mlsanity.com/paper/2106.09643/) (2021)
- [Predicting spatial distribution of Palmer Drought Severity Index](https://mlsanity.com/paper/2208.14833/) (2022)
- [Usage of specific attention improves change point detection](https://mlsanity.com/paper/2204.08175/) (2022)
- [Correcting sampling biases via importance reweighting for spatial modeling](https://mlsanity.com/paper/2309.04824/) (2023)

## Abstract (arXiv)

We examine the applicability of modern neural network architectures to the midterm prediction of earthquakes. Our data-based classification model aims to predict if an earthquake with the magnitude above a threshold takes place at a given area of size 10 × 10 kilometers in 10-60 days from a given moment. Our deep neural network model has a recurrent part (LSTM) that accounts for time dependencies between earthquakes and a convolutional part that accounts for spatial dependencies. Obtained results show that neural networks-based models beat baseline feature-based models that also account for spatio-temporal dependencies between different earthquakes. For historical data on Japan earthquakes our model predicts occurrence of an earthquake in 10 to 60 days from a given moment with magnitude Mc > 5 with quality metrics ROC AUC 0.975 and PR AUC 0.0890, making 1.18 · 103 correct predictions, while missing 2.09 · 103 earthquakes and making 192 · 103 false alarms. The baseline approach has similar ROC AUC 0.992, number of correct predictions 1.19 · 103, and missing 2.07 · 103 earthquakes, but significantly worse PR AUC 0.00911, and number of false alarms 1004 · 103.