|Title||Winning with Simple Models: Detecting Earthquakes in Groningen, the Netherlands|
|Publication Type||Conference Proceedings|
|Year of Conference||2020|
|Authors||bin Wahid, U, Afify, A, Fehler, M, Fulcher, B|
|Conference Name||EAGE Annual|
Deep learning is fast emerging as a potential disruptive tool to tackle longstanding research problems across the sciences. Notwithstanding its success across scientific disciplines, the recent trend of the overuse of deep learning is concerning to many machine learning practitioners. Recently, seismologists have also demonstrated the efficacy of deep learning algorithms in detecting low magnitude earthquakes. Here, we revisit the problem of seismic event detection but using a logistic regression model with feature extraction. We select well-discriminating features from a huge database of time-series operations collected from interdisciplinary timeseries analysis methods. With a simple learning model, we detect several low-magnitude induced earthquakes from the Groningen gas field that are not present in the catalog. The added advantage of simpler models is that the selected features add to our understanding of the noise and event classes present in the dataset. Since simpler models are easy to maintain, debug, understand, and train, through this study we underscore that it might be a dangerous pursuit to use deep learning without carefully weighing simpler alternatives.