Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
DYNA
Print version ISSN 0012-7353
Abstract
OCHOA, Luis H.; NINO, Luis F. and VARGAS, Carlos A.. Fast estimation of earthquake epicenter distance using a single seismological station with machine learning techniques. Dyna rev.fac.nac.minas [online]. 2018, vol.85, n.204, pp.161-168. ISSN 0012-7353. https://doi.org/10.15446/dyna.v85n204.68408.
A Support Vector Machine Regression (SVMR) algorithm was applied to calculate the epicenter distance using a ten seconds signal, after primary waves arrive at a seismological station near to Bogota - Colombia. This algorithm was tested with 863 records of earthquakes, where the input parameters were an exponential function of waveform envelope estimated by least squares and maximum value of recorded waveforms for each component of the seismic station. Cross validation was applied to normalized polynomial kernel functions, obtaining mean absolute error for different exponents and complexity parameters. The epicenter distance was estimated with 10.3 kilometers of absolute error, improving the results previously obtained for this hypocentral parameter. The proposed algorithm is easy to implement in hardware and can be employed directly in the field, generating fast decisions at seismological control centers increasing the possibilities of effective reactions.
Keywords : earthquake early warning; support vector machine regression; earthquake; rapid response; epicenter distance; seismic event; seismology; Bogota - Colombia.