Usage of multiple RTL features for Earthquake prediction
This work addresses earthquake prediction for disaster management, but it is incremental as it builds on existing RTL-based methods with machine learning enhancements.
The paper tackles earthquake prediction by constructing a classification model that forecasts earthquakes above a certain magnitude within 30-180 days at specific locations, using machine learning on multiple RTL features to improve accuracy, achieving precision up to ~0.95 and recall up to ~0.98 on historical Japan data from 1992-2005.
We construct a classification model that predicts if an earthquake with the magnitude above a threshold will take place at a given location in a time range 30-180 days from a given moment of time. A common approach is to use expert forecasts based on features like Region-Time-Length (RTL) characteristics. The proposed approach uses machine learning on top of multiple RTL features to take into account effects at various scales and to improve prediction accuracy. For historical data about Japan earthquakes 1992-2005 and predictions at locations given in this database the best model has precision up to ~ 0.95 and recall up to ~ 0.98.