A Machine-Learning Approach for Earthquake Magnitude Estimation
This provides a fast and reliable method for earthquake monitoring and early warning systems, though it is incremental as it builds on existing deep-learning techniques for seismic data.
The study tackled earthquake magnitude estimation by developing a single-station deep-learning approach that predicts magnitudes directly from raw waveforms, achieving an average error near zero and a standard deviation of ~0.2 without instrument correction.
In this study we develop a single-station deep-learning approach for fast and reliable estimation of earthquake magnitude directly from raw waveforms. We design a regressor composed of convolutional and recurrent neural networks that is not sensitive to the data normalization, hence waveform amplitude information can be utilized during the training. Our network can predict earthquake magnitudes with an average error close to zero and standard deviation of ~0.2 based on single-station waveforms without instrument response correction. We test the network for both local and duration magnitude scales and show a station-based learning can be an effective approach for improving the performance. The proposed approach has a variety of potential applications from routine earthquake monitoring to early warning systems.