#
Earthquake Magnitude Prediction Using Recurrent Neural Networks^{ †}

^{1}

^{2}

^{*}

^{†}

## Abstract

**:**

## 1. Introduction

## 2. Methods

#### 2.1. Time Series Modeling with the LSTM Recurrent Neural Networks

#### 2.2. Earthquake Magnitude Prediction as a Time Series Modeling Problem

## 3. Results and Discussion

## 4. Conclusions

## Acknowledgments

## References

- Kagan, Y.Y. Are earthquakes predictable? Geophys. J. Int.
**1997**, 131, 505–525. [Google Scholar] [CrossRef] - Rikitake, T. Classification of earthquake precursors. Tectonophys.
**1979**, 54, 293–309. [Google Scholar] [CrossRef] - Ghaedi, K.; Ibrahim, Z. Earthquake prediction. Earthquakes-Tectonics. Hazard Risk Mitigat.
**2017**, 10, 205–227. [Google Scholar] - Wang, Q.; Guo, Y.; Yu, L.; Li, P. Earthquake prediction based on spatio-temporal data mining: an LSTM network approach. IEEE Trans. Emerg. Top. Comput.
**2017**, 1, 1–10. [Google Scholar] [CrossRef] - Asim, K.M.; Martínez-Álvarez, F.; Basit, A.; Iqbal, T. Earthquake magnitude prediction in Hindukush region using machine learning techniques. Nat. Hazards.
**2017**, 85, 471–486. [Google Scholar] [CrossRef] - Narayanakumar, S.; Raja, K. A BP artificial neural network model for earthquake magnitude prediction in himalayas, india. Circuits Syst.
**2016**, 7, 3456–3468. [Google Scholar] [CrossRef] - Jordan, T.H.; Chen, Y.T.; Gasparini, P.; Madariaga, R.; Main, I.; Marzocchi, W.; Papadopoulos, G.; Sobolev, G.; Yamaoka, K.; Zschau, J. Operational earthquake forecasting. State of knowledge and guidelines for utilization. Ann. Geophys.
**2011**, 54, 270–276. [Google Scholar] - Gonzalez, J.; Yu, W. Non-linear system modeling using LSTM neural networks. IFAC-PapersOnLine
**2018**, 51, 485–489. [Google Scholar] [CrossRef]

**Figure 3.**(

**a**) Hourly maximum earthquake magnitude time series; (

**b**) training of hourly maximum earthquake magnitude time series.

**Figure 4.**Hourly maximum earthquake magnitude time series, where all the zero values are filled by a value equal to the last non-zero magnitude value.

**Figure 5.**Hourly maximum earthquake magnitude time series without zero values: (

**a**) training, (

**b**) prediction.

**Figure 6.**Prediction (red) versus original (blue) time series: (

**a**) with non-zero values, (

**b**) after removing all the non-zero values that were used to fill the zeros in the original series.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

González, J.; Yu, W.; Telesca, L.
Earthquake Magnitude Prediction Using Recurrent Neural Networks. *Proceedings* **2019**, *24*, 22.
https://doi.org/10.3390/IECG2019-06213

**AMA Style**

González J, Yu W, Telesca L.
Earthquake Magnitude Prediction Using Recurrent Neural Networks. *Proceedings*. 2019; 24(1):22.
https://doi.org/10.3390/IECG2019-06213

**Chicago/Turabian Style**

González, Jesús, Wen Yu, and Luciano Telesca.
2019. "Earthquake Magnitude Prediction Using Recurrent Neural Networks" *Proceedings* 24, no. 1: 22.
https://doi.org/10.3390/IECG2019-06213