Impact of seismic wave length to detect high-magnitude earthquakes via deep learning

Impact of seismic wave length to detect high-magnitude earthquakes via deep learning

Georgiev, Gancho (TU Delft Electrical Engineering, Mathematics and Computer Science)

Sabbaqi, M. (mentor)
Isufi, E. (mentor)
Brinkman, W.P. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2022-06-22

Earthquakes are one of the most destructive natural phenomena, both in terms of human lives, and property damage. Although they are treated as a random phenomenon, the ability to predict them, even few seconds before they occur, could be of great benefit to society. Lots of research has been done on this topic but without any significant results. With the increase of seismic wave measurements data and since in recent years deep learning has solved many difficult problems, this paper aims to answer the impact of the seismic wave length in detecting high-magnitude earthquakes via Long Short-Term Memory (LSTM) neural network. Although the performance of the model was unsatisfactory, given the complex task of predicting earthquakes, as well as the resulting metrics not indicating any significant data in order to extrapolate a certain conclusion, it is worth further researching a duration of seismic waveform recordings of length 30 seconds, with sampling rate between 10 and 20 HZ, as these seismic waves seem to perform relatively best in our research.

Earthquake Prediction
Long Short-term Memory
Neural network

http://resolver.tudelft.nl/uuid:a3305121-f074-4f8b-a18d-e512c484733a

Student theses

bachelor thesis

© 2022 Gancho Georgiev