{"type":"ScholarlyArticle","title":"REAVER: Real-time Earthquake Prediction with Attention-based Sliding-Window Spectrograms","authors":[{"name":"Lotfy Abdel Khaliq","slug":"lotfy-abdel-khaliq","given":"Lotfy","family":"Abdel Khaliq","affiliation":"German Research Center for Artificial Intelligence (DFKI) , Germany"},{"name":"Sabine Janzen","slug":"sabine-janzen","given":"Sabine","family":"Janzen","affiliation":"German Research Center for Artificial Intelligence (DFKI) , Germany"},{"name":"Wolfgang Maass","slug":"wolfgang-maass","given":"Wolfgang","family":"Maass","affiliation":"German Research Center for Artificial Intelligence (DFKI) , Germany; Saarland University , Germany"}],"abstract":"Predicting earthquakes with precision remains an ongoing challenge in earthquake early warning systems (EEWS), that struggle with accuracy and fail to provide timely warnings for impending earthquakes. Recent efforts employing deep learning techniques have shown promise in overcoming these limitations. However, current methods lack the ability to capture subtle frequency changes indicative of seismic activity in real-time, limiting their effectiveness in EEWS. To address this gap, we propose REAVER, a novel approach for real-time prediction of P- and S-waves of earthquakes using attention-based sliding-window spectrograms. REAVER leverages Mel-Spectrogram signal representations to capture temporal frequency changes in seismic signals effectively. By employing an encoder-decoder architecture with attention mechanisms, REAVER accurately predicts the onset of P- and S-waves moments when an earthquake occurs. We benchmark the effectiveness of REAVER, showing its performance in terms of both accuracy and real-time prediction capabilities compared to existing methods. Additionally, we provide a web-based implementation of REAVER, allowing users to monitor seismic activity in real-time and analyze historical earthquake waveforms.","doi":"10.24963/ijcai.2024/988","url":"https://ijcai.org/proceedings/2024/988","pdf":"https://ijcai.org/proceedings/2024/0988.pdf","markdown":"https://ijcai.org/proceedings/2024/988.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/988","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Demo Track","track":"Demo Track","number":988,"pages":{"first":8596,"last":8600},"keywords":["Machine Learning: ML: Applications","Multidisciplinary Topics and Applications: MDA: Real-time systems"],"videos":[],"references":[{"position":1,"raw":"[Choubik et al., 2020] Youness Choubik, Abdelhak Mah- moudi, Mohammed Majid Himmi, and Lahcen El Moud- nib. Sta/lta trigger algorithm implementation on a seismo- logical dataset using hadoop mapreduce. IAES Interna- tional Journal of Artificial Intelligence, 9(2):269, 2020.","title":"Sta/lta trigger algorithm implementation on a seismological dataset using hadoop mapreduce","authors":"Youness Choubik, Abdelhak Mahmoudi, Mohammed Majid Himmi, Lahcen El Moudnib","year":"2020","venue":"IAES International Journal of Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Fauvel et al., 2020] Kevin Fauvel, Daniel Balouek- Thomert, Diego Melgar, Pedro Silva, Anthony Simonet, Gabriel Antoniu, Alexandru Costan, Véronique Masson, Manish Parashar, Ivan Rodero, et al. A distributed multi-sensor machine learning approach to earthquake early warning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 403-411, 2020.","title":"A distributed multi-sensor machine learning approach to earthquake early warning","authors":"Kevin Fauvel, Daniel Balouek-Thomert, Diego Melgar, Pedro Silva, Anthony Simonet, Gabriel Antoniu, Alexandru Costan, Véronique Masson, Manish Parashar, Ivan Rodero","year":"2020","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Gaol et al., 2021] YH Lumban Gaol, RK Lobo, SS Angkasa, A Abdullah, I Madrinovella, S Widyanti, A Priyono, SK Suhardja, AD Nugraha, Z Zulfakriza, et al. Preliminary results of automatic p-wave regional earthquake arrival time picking using machine learning with sta/lta as the input parameters. In IOP conference series: earth and environmental science, volume 873, page 012060. IOP Publishing, 2021.","title":"Preliminary results of automatic p-wave regional earthquake arrival time picking using machine learning with sta/lta as the input parameters","authors":"Gaol","year":"2021","venue":"IOP conference series: earth and environmental science","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gong et al., 2022] Yuan Gong, Cheng-I Lai, Yu-An Chung, and James Glass. Ssast: Self-supervised audio spectro- gram transformer. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 10699-10709, 2022.","title":"Ssast: Self-supervised audio spectrogram transformer","authors":"Yuan Gong, -I Cheng, Yu-An Lai, James Chung, Glass","year":"2022","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Huang et al., 2020] Xin Huang, Jangsoo Lee, Young-Woo Kwon, and Chul-Ho Lee. Crowdquake: A networked sys- tem of low-cost sensors for earthquake detection via deep learning. In Proceedings of the 26th ACM SIGKDD In- ternational Conference on Knowledge Discovery & Data Mining, pages 3261-3271, 2020.","title":"Crowdquake: A networked system of low-cost sensors for earthquake detection via deep learning","authors":"Xin Huang, Jangsoo Lee, Young-Woo Kwon, Chul-Ho Lee","year":"2020","venue":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kohler et al., 2020] Monica D Kohler, Deborah E Smith, Jennifer Andrews, Angela I Chung, Renate Hartog, Ivan Henson, Douglas D Given, Robert de Groot, and Stephen Guiwits. Earthquake early warning shakealert 2.0: Public rollout. Seismological Research Letters, 91(3):1763-1775, 2020.","title":"Earthquake early warning shakealert 2.0: Public rollout","authors":"Monica D Kohler, Deborah E Smith, Jennifer Andrews, Angela I Chung, Renate Hartog, Ivan Henson, Robert Douglas D Given, Stephen De Groot, Guiwits","year":"2020","venue":"Seismological Research Letters","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ku et al., 2020] Bonhwa Ku, Gwantae Kim, JaeKwang Ahn, Jimin Lee, and Hanseok Ko. Attention-based con- volutional neural network for earthquake event classifi- cation. IEEE Geoscience and Remote Sensing Letters, 18(12):2057-2061, 2020.","title":"Attention-based convolutional neural network for earthquake event classification","authors":"Ku","year":"2020","venue":"IEEE Geoscience and Remote Sensing Letters","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kwiatek et al., 2023] G Kwiatek, P Martínez-Garzón, Dirk Becker, Georg Dresen, Fabrice Cotton, Gregory C Beroza, D Acarel, S Ergintav, and Marco Bohnhoff. Months- long seismicity transients preceding the 2023 mw 7.8 kahramanmaras ¸earthquake, türkiye. Nature Communica- tions, 14(1):7534, 2023.","title":"Monthslong seismicity transients preceding the 2023 mw 7.8 kahramanmaras ¸earthquake, türkiye","authors":"P Kwiatek, Dirk Martínez-Garzón, Georg Becker, Fabrice Dresen, Gregory C Cotton, D Beroza, S Acarel, Marco Ergintav, Bohnhoff","year":"2023","venue":"Nature Communications","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lara et al., 2023] Pablo Lara, Quentin Bletery, Jean-Paul Ampuero, Adolfo Inza, and Hernando Tavera. Earthquake early warning starting from 3 s of records on a single sta- tion with machine learning. Journal of Geophysical Re- search: Solid Earth, 128:e2023JB026575, 2023.","title":"Earthquake early warning starting from 3 s of records on a single station with machine learning","authors":"Lara","year":"2023","venue":"Journal of Geophysical Research: Solid Earth","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Mallouhy et al., 2019] Roxane Mallouhy, Chady Abou Jaoude, Christophe Guyeux, and Abdallah Makhoul. Major earthquake event prediction using various machine learning algorithms. In 2019 Interna- tional Conference on Information and Communication Technologies for Disaster Management (ICT-DM), pages 1-7. IEEE, 2019.","title":"Major earthquake event prediction using various machine learning algorithms","authors":"Roxane Mallouhy, Chady Abou Jaoude, Christophe Guyeux, Abdallah Makhoul","year":"2019","venue":"2019 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[McBride et al., 2022] Sara K McBride, Hollie Smith, Meredith Morgoch, Danielle Sumy, Mariah Jenkins, Lori Peek, Ann Bostrom, Dare Baldwin, Elizabeth Reddy, Robert de Groot, et al. Evidence-based guidelines for protective actions and earthquake early warning systems. Geophysics, 87(1):WA77-WA102, 2022.","title":"Evidence-based guidelines for protective actions and earthquake early warning systems","authors":"Hollie Sara K Mcbride, Meredith Smith, Danielle Morgoch, Mariah Sumy, Lori Jenkins, Ann Peek, Dare Bostrom, Elizabeth Baldwin, Robert Reddy, De Groot","year":"2022","venue":"Geophysics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Meier et al., 2019] Men-Andrin Meier, Zachary E Ross, Anshul Ramachandran, Ashwin Balakrishna, Suraj Nair, Peter Kundzicz, Zefeng Li, Jennifer Andrews, Egill Hauksson, and Yisong Yue. Reliable real-time seismic sig- nal/noise discrimination with machine learning. Journal of Geophysical Research: Solid Earth, 124(1):788-800, 2019.","title":"Reliable real-time seismic signal/noise discrimination with machine learning","authors":"Meier","year":"2019","venue":"Journal of Geophysical Research: Solid Earth","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Meng et al., 2019] Hao Meng, Tianhao Yan, Fei Yuan, and Hongwei Wei. Speech emotion recognition from 3d log- mel spectrograms with deep learning network. IEEE ac- cess, 7:125868-125881, 2019.","title":"Speech emotion recognition from 3d logmel spectrograms with deep learning network","authors":"Tianhao Hao Meng, Fei Yan, Hongwei Yuan, Wei","year":"2019","venue":"IEEE access","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mousavi et al., 2019] S Mostafa Mousavi, Yixiao Sheng, Weiqiang Zhu, and Gregory C Beroza. Stanford earth- quake dataset (stead): A global data set of seismic signals for ai. IEEE Access, 7:179464-179476, 2019.","title":"Stanford earthquake dataset (stead): A global data set of seismic signals for ai","authors":"Yixiao Mostafa Mousavi, Weiqiang Sheng, Gregory C Zhu, Beroza","year":"2019","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mousavi et al., 2020] S Mostafa Mousavi, William L Ellsworth, Weiqiang Zhu, Lindsay Y Chuang, and Gre- gory C Beroza. Earthquake transformer-an attentive deep-learning model for simultaneous earthquake de- tection and phase picking. Nature communications, 11(1):3952, 2020.","title":"Earthquake transformer-an attentive deep-learning model for simultaneous earthquake detection and phase picking","authors":"William L Mostafa Mousavi, Weiqiang Ellsworth, Lindsay Y Zhu, Gregory C Chuang, Beroza","year":"2020","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mukherjee et al., 2021] Tonumoy Mukherjee, Chandrani Singh, and Prabir Kumar Biswas. A novel approach for earthquake early warning system design using deep learn- ing techniques. ArXiv, abs/2101.06517, 2021.","title":"A novel approach for earthquake early warning system design using deep learning techniques","authors":"Tonumoy Mukherjee, Chandrani Singh, Prabir Kumar, Biswas","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Munchmeyer et al., 2021] Jannes Munchmeyer, Dino Bindi, Ulf Leser, and Frederik Tilmann. Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network. Geophysical Journal International, 226(2):1086-1104, 2021.","title":"Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network","authors":"Jannes Munchmeyer, Dino Bindi, Ulf Leser, Frederik Tilmann","year":"2021","venue":"Geophysical Journal International","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ochoa et al., 2018] Luis H. Ochoa, Luis F. Niño, and Car- los A. Vargas. Fast magnitude determination using a single seismological station record implementing machine learn- ing techniques. Geodesy and Geodynamics, 9(1):34-41, 2018. Seismological advances in Latin America.","title":"Fast magnitude determination using a single seismological station record implementing machine learning techniques","authors":"H Luis, Luis F Ochoa, Carlos A Niño, Vargas","year":"2018","venue":"Geodesy and Geodynamics","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shakeel et al., 2021] Muhammad Shakeel, Katsutoshi Itoyama, Kenji Nishida, and Kazuhiro Nakadai. Detecting earthquakes: a novel deep learning-based approach for effective disaster response. Applied Intelligence, 51(11):8305-8315, 2021.","title":"Detecting earthquakes: a novel deep learning-based approach for effective disaster response","authors":"Shakeel","year":"2021","venue":"Applied Intelligence","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zhu and Beroza, 2019] Weiqiang Zhu and Gregory C Beroza. Phasenet: A deep-neural-network-based seismic arrival-time picking method. Geophysical Journal Inter- national, 216(1):261-273, 2019.","title":"Phasenet: A deep-neural-network-based seismic arrival-time picking method","authors":"Weiqiang Zhu, Gregory C Beroza","year":"2019","venue":"Geophysical Journal International","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}