TY - JOUR A1 - Kriegerowski, Marius A1 - Petersen, Gesa Maria A1 - Vasyura-Bathke, Hannes A1 - Ohrnberger, Matthias T1 - A Deep Convolutional Neural Network for Localization of Clustered Earthquakes Based on Multistation Full Waveforms JF - Seismological research letters N2 - Earthquake localization is both a necessity within the field of seismology, and a prerequisite for further analysis such as source studies and hazard assessment. Traditional localization methods often rely on manually picked phases. We present an alternative approach using deep learning that once trained can predict hypocenter locations efficiently. In seismology, neural networks have typically been trained with either single-station records or based on features that have been extracted previously from the waveforms. We use three-component full-waveform records of multiple stations directly. This means no information is lost during preprocessing and preparation of the data does not require expert knowledge. The first convolutional layer of our deep convolutional neural network (CNN) becomes sensitive to features that characterize the waveforms it is trained on. We show that this layer can therefore additionally be used as an event detector. As a test case, we trained our CNN using more than 2000 earthquake swarm events from West Bohemia, recorded by nine local three-component stations. The CNN successfully located 908 validation events with standard deviations of 56.4 m in east-west, 123.8 m in north-south, and 136.3 m in vertical direction compared to a double-difference relocated reference catalog. The detector is sensitive to events with magnitudes down to M-L = -0.8 with 3.5% false positive detections. Y1 - 2018 U6 - https://doi.org/10.1785/0220180320 SN - 0895-0695 SN - 1938-2057 VL - 90 IS - 2 SP - 510 EP - 516 PB - Seismological Society of America CY - Albany ER - TY - JOUR A1 - Woith, Heiko A1 - Petersen, Gesa Maria A1 - Hainzl, Sebastian A1 - Dahm, Torsten T1 - Review: Can Animals Predict Earthquakes? JF - Bulletin of the Seismological Society of America N2 - In public perception, abnormal animal behavior is widely assumed to be a potential earthquake precursor, in strong contrast to the viewpoint in natural sciences. Proponents of earthquake prediction via animals claim that animals feel and react abnormally to small changes in environmental and physico-chemical parameters related to the earthquake preparation process. In seismology, however, observational evidence for changes of physical parameters before earthquakes is very weak. In this study, we reviewed 180 publications regarding abnormal animal behavior before earthquakes and analyze and discuss them with respect to (1) magnitude-distance relations, (2) foreshock activity, and (3) the quality and length of the published observations. More than 700 records of claimed animal precursors related to 160 earthquakes are reviewed with unusual behavior of more than 130 species. The precursor time ranges from months to seconds prior to the earthquakes, and the distances from a few to hundreds of kilometers. However, only 14 time series were published, whereas all other records are single observations. The time series are often short (the longest is 1 yr), or only small excerpts of the full data set are shown. The probability density of foreshocks and the occurrence of animal precursors are strikingly similar, suggesting that at least parts of the reported animal precursors are in fact related to foreshocks. Another major difficulty for a systematic and statistical analysis is the high diversity of data, which are often only anecdotal and retrospective. The study clearly demonstrates strong weaknesses or even deficits in many of the published reports on possible abnormal animal behavior. To improve the research on precursors, we suggest a scheme of yes and no questions to be assessed to ensure the quality of such claims. Y1 - 2018 U6 - https://doi.org/10.1785/0120170313 SN - 0037-1106 SN - 1943-3573 VL - 108 IS - 3A SP - 1031 EP - 1045 PB - Seismological Society of America CY - Albany ER -