Seismological Research Letters 0895-0695 1938-2057 12 19 2018 03 2019 90 2A Marius Kriegerowski University of Potsdam, Institut für Erd‐ und Umweltwissenschaften, Karl‐Liebknecht‐Str. 24‐25, 14476 Potsdam, Germany, kriegero@uni-potsdam.de, hvasbath@uni-potsdam.de, mao@geo.uni-potsdam.de Gesa M. Petersen Helmholtz Centre Potsdam German Research Centre for Geosciences ‐ GFZ, Telegrafenberg, 14473 Potsdam, Germany, gesap@gfz-potsdam.de Also at University of Potsdam, Institut für Erd‐ und Umweltwissenschaften, Karl‐Liebknecht‐Str. 24‐25, 14476 Potsdam, Germany. Hannes Vasyura‐Bathke University of Potsdam, Institut für Erd‐ und Umweltwissenschaften, Karl‐Liebknecht‐Str. 24‐25, 14476 Potsdam, Germany, kriegero@uni-potsdam.de, hvasbath@uni-potsdam.de, mao@geo.uni-potsdam.de Matthias Ohrnberger University of Potsdam, Institut für Erd‐ und Umweltwissenschaften, Karl‐Liebknecht‐Str. 24‐25, 14476 Potsdam, Germany, kriegero@uni-potsdam.de, hvasbath@uni-potsdam.de, mao@geo.uni-potsdam.de 12 19 2018 03 2019 510 516 10.1785/0220180320 https://pubs.geoscienceworld.org/ssa/srl/article/90/2A/510/567690/A-Deep-Convolutional-Neural-Network-for https://pubs.geoscienceworld.org/ssa/srl/article-pdf/90/2A/510/4655307/srl-2018320.1.pdf Abadi M. Agarwal A. Barham P. Brevdo E. Chen Z. Citro C. Corrado G. S. Davis A. Dean J. , and DevinM. 2015. TensorFlow: Large‐Scale Machine Learning on Heterogeneous Systems, available at tensorflow.org (last accessed September 2018). IEEE Trans. Neural Networks Bengio 2 157 1994 10.1109/72.279181 Learning long‐term dependencies with gradient descent is difficult Bull. Seismol. Soc. Am. Böse 1 366 2008 10.1785/0120070002 PreSEIS: A neural network‐based approach to earthquake early warning for finite faults Bull. Seismol. Soc. Am. Del Pezzo 1 215 2003 10.1785/0120020005 Discrimination of earthquakes and underwater explosions using neural networks Rev. Geophys. Farr 2005 1 2007 The shuttle radar topography mission Tectonophysics Fischer 1 2014 10.1016/j.tecto.2013.11.001 Intra‐continental earthquake swarms in West‐Bohemia and Vogtland: A review J. Seismol. Fischer 665 2010 10.1007/s10950-010-9189-4 The 2008 West Bohemia earthquake swarm in the light of the WEBNET network Goodfellow I. Bengio Y. , and CourvilleA. 2016. Deep Learning, MIT Press, Cambridge, Massachusetts, available at http://www.deeplearningbook.org (last accessed September 2018). Seismol. Res. Lett. Grigoli 4 666 2013 10.1785/0220120191 Automated seismic event location by travel‐time stacking: An application to mining induced seismicity New Manual of Seismological Observatory Practice (NMSOP‐2) Havskov 2012 Information sheet IS 11.1: Seismic source location GFZ Data Services Heimann 2017 Pyrocko ‐ An open‐source seismology toolbox and library International Federation of Digital Seismograph Networks. Other/Seismic Network Institute of Geophysics, Academy of Sciences of the Czech Republic 1991 West Bohemia local seismic network Keskar N. S. Mudigere D. Nocedal J. Smelyanskiy M. , and TangP. T. P. 2016. On Large‐Batch Training for Deep Learning: Generalization Gap and Sharp Minima, available at http://arxiv.org/abs/1609.04836 (last accessed September 2018). Kingma D. P. , and BaJ. 2014. Adam: A Method for Stochastic Optimization, available at http://arxiv.org/abs/1412.6980 (last accessed November 2018). Geophys. J. Int. Köhler 3 1619 2010 10.1111/j.1365-246X.2010.04709.x Unsupervised pattern recognition in continuous seismic wavefield records using self‐organizing maps Nature LeCun 7553 2015 10.1038/nature14539 Deep learning Bull. Seismol. Soc. Am. Musil 4 1077 1996 10.1785/BSSA0860041077 Discrimination between local microearthquakes and quarry blasts by multi‐layer perceptrons and Kohonen maps Pascanu R. Mikolov T. , and BengioY. 2012. On the difficulty of training Recurrent Neural Networks, CoRR, available at http://arxiv.org/abs/1211.5063 (last accessed November 2018). Sci. Adv. Perol 2 2018 10.1126/sciadv.1700578 Convolutional neural network for earthquake detection and location J. Geophys. Res. Ross 5120 2018 10.1029/2017JB015251 P‐wave arrival picking and first‐motion polarity determination with deep learning Ross Z. E. Meier M.‐A. Hauksson E. , and HeatonT. H. 2018. Generalized Seismic Phase Detection with Deep Learning, available at http://arxiv.org/abs/1805.01075 (last accessed September 2018). Springenberg J. T. Dosovitskiy A. Brox T. , and RiedmillerM. 2014. Striving for Simplicity: The All Convolutional Net, available at http://arxiv.org/abs/1412.6806 (last accessed September 2018). J. Machine Learn. Res. Srivastava 1 1929 2014 Dropout: A simple way to prevent neural networks from overfitting Comput. Geosci. Tiira 8 929 1999 10.1016/S0098-3004(99)00056-4 Detecting teleseismic events using artificial neural networks Bull. Seismol. Soc. Am. Wang 1 308 1995 10.1785/BSSA0850010308 Artificial neural network‐based seismic detector Bull. Seismol. Soc. Am. Wang 5 1140 1997 10.1785/BSSA0870051140 Identification and picking of S phase using an artificial neural network Eos Trans. AGU Wessel 409 2013 10.1002/2013EO450001 Generic mapping tools: Improved version released Bull. Seismol. Soc. Am. Zhao 3 670 1999 10.1785/BSSA0890030670 An artificial neural network approach for broadband seismic phase picking 10.1093/gji/ggy423 Zhu W. , and BerozaG. C. 2018. PhaseNet: A Deep‐Neural‐Network‐Based Seismic Arrival Time Picking Method, available at http://arxiv.org/abs/1803.03211 (last accessed September 2018).