Deep learning algorithms to forecast the magnitude of earthquakes in Peru

Zuniga J.L.B.; Llerena F.F.A. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2023)

Resumen

The research proposes the application of the algorithm. LSTM with the aim of forecasting the magnitude of earthquakes in Peru adding pink noise in its dynamics to replicate and capture the complex dynamics of magnitude, confirms a anti persistence in the increments by means of the coefficient of hurst. less than 0.5 and stable. Then a model is implemented of higher precision LSTM network in the generation of forecasts than the one-way multilayer perceptron network. By Therefore, evidence of better network performance is presented LSTM in relation to the magnitude variables of the earthquake due to the pink noise that occurs in its dynamics. The study period consists from January 1, 2020 to October 23, 2021.

Instituciones: Universidad Tecnológica del Perú