Tectonic tremor in Taiwan is known for its short duration and weak amplitude. Recent observations from the mountain area (Central Range) allows us to document such type of tectonic tremor recorded at a close distance and to investigate a single station technique for a minute-long tremor. To effectively distinguish tremor from earthquakes and noise, we applied the Fisher's class separability criterion to automatically select the optimal feature subset from a set of commonly adopted feature candidates. During the study period of 1 January to 16 September 2016 when a local seismic array was deployed, we successfully differentiated tremor from local earthquakes and noise with high accuracy of 86.6% to 98.9% from three stations using a k-nearest neighbors classifier. Other than the maximum amplitude, number of peaks, and energy of the 2- to 8-Hz passband, the spikiness of discrete Fourier transforms median in time is also found to be important to separate tremor from noise.
- Fisher's class separability
- k-nearest neighbor
- machine learning
- single-station classification
- tectonic tremor