S020
Uncertainty Quantification in AI/ML applications for seismic monitoring
Session ID#: 251430
Session Description:
Recent advances in Artificial Intelligence/Machine Learning (AI/ML) have transformed the field of seismology and particularly seismic monitoring by decreasing detection thresholds and improving the accuracy and efficiency of source characteristics estimation. However, there remains critical need for systematic uncertainty quantification (UQ) of AI/ML models to assess their reliability and build confidence in their predictions. This session focuses on addressing some of the challenges inherent in estimating uncertainties in AI/ML models and aims to foster conversations within the seismic community. We welcome contributions demonstrating recent progress in UQ approaches and their integration into AI/ML models for seismic monitoring. Topics of interest include the incorporation of UQ techniques such as Monte-Carlo Dropout, Deep Ensembles, Bayesian inferences in seismic signal detection, phase association, and event location and characterization. Efforts that evaluate the strengths/limitations of different UQ techniques and the generalizability of uncertainty estimates in the face of domain shift are of particular interest.
Index Terms:
0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
3275 Uncertainty quantification [MATHEMATICAL GEOPHYSICS]
7219 Seismic monitoring and test-ban treaty verification [SEISMOLOGY]
7290 Computational seismology [SEISMOLOGY]
Primary Convener: Maeva Pourpoint, Air Force Research Laboratory Albuquerque, Albuquerque, NM, United States
Conveners: Ian W. McBrearty, Stanford University, Department of Geophysics, Stanford, United States, Jesse Williams, GTC Analytics, Atlanta, United States and Weiqiang Zhu, University of California, Berkeley, Department of Earth and Planetary Science, Berkeley, United States
Empirical Rules for Quality Control of Deep Learning Enhanced Earthquake Catalogs (1876229)
Albert Aguilar Suarez1, Yongsoo Park2, William L Ellsworth1 and Gregory C Beroza1, (1)Stanford University, Department of Geophysics, Stanford, CA, United States, (2)Los Alamos National Laboratory, Los Alamos, United States
Optimizing Seismological Objective Functions with Machine Learning: A Case Study with Focal Mechanism Determination (1907495)
Xiaohan Song1, Men-Andrin Meier2, William L Ellsworth3 and Gregory C Beroza3, (1)Stanford University, Department of Geophysics, Stanford, United States, (2)ETH Zurich, Institute of Geophysics, Zurich, Switzerland, (3)Stanford University, Department of Geophysics, Stanford, CA, United States
Machine Learning-Based Event Detection And Earthquake Relocation For The Seismic Catalog Of The Gargano Promontory (Southern Italy) (1910559)
Andrea Tallarico1,2, Andrea Pio Ferreri2, Serena Panebianco3, Claudio Satriano4, Marilena Filippucci1,2, Tony Alfredo Stabile3, Gianpaolo Cecere5, Vincenzo Serlenga3 and Giulio Selvaggi1, (1)Istituto Nazionale di Geofisica e Vulcanologia, Roma, Italy, (2)University of Bari Aldo Moro, Dipartimento di Scienze della Terra e Geoambientali, Bari, Italy, (3)CNR Institute of Methodologies for Environmental Analysis, Potenza, Italy, (4)Institut de Physique du Globe, Paris, France, (5)Istituto Nazionale di Geofisica e Vulcanologia, Sezione Irpina, Grottaminarda (AV), Italy
Real-Time Classification of Induced Seismicity Events Using an Attention-Based U-Net Architecture (1926139)
Avigyan Chatterjee1, Qingkai Kong1, Kayla Kroll2, Chengping Chai3, Alex Dzubay4, Jeffrey M Leifer5, Scott Fertig6, Paul A Friberg6 and Josh Stachnik7, (1)Lawrence Livermore National Laboratory, Livermore, CA, United States, (2)UC Riverside, Riverside, United States, (3)Oak Ridge National Laboratory, Oak Ridge, TN, United States, (4)University of Utah, Geology and Geophysics, Salt Lake City, United States, (5)Instrumental Software Tech Inc, Saratoga Springs, NY, United States, (6)Instrumental Software Technologies, Inc., Saratoga Springs, United States, (7)Instrumental Software Technologies, Inc., Saratoga Springs, NY, United States
Seismic detection based on unsupervised station-wise phase picks using deep learning and its application (1933837)
Tomoki Tokuda1, Shutaro Sekine2, Shintaro Abe2, Naoshi Hirata1 and Hiromichi Nagao1, (1)Earthquake Research Institute, University of Tokyo, Tokyo, Japan, (2)Association for the Development of Earthquake Prediction, Tokyo, Japan
Benchmarking a Deep Learning Seismic Associator Across Synthetic and Real Global Datasets (1951615)
Hiba Kunwer1, Chang Ding2, Jesse Williams3, John Pace3, Zhigang Peng2 and Andrew Vern Newman4, (1)Georgia Institute of Technology, School of Earth and Atmospheric Sciences, Geophysics, Atlanta, United States, (2)Georgia Institute of Technology, School of Earth and Atmospheric Sciences, Atlanta, United States, (3)GTC Analytics, Atlanta, United States, (4)Georgia Institute of Technology, Atlanta, United States
A Comparative Analysis & Benchmarking between Seismic Phase Associators using the TexNet portable Seismic Station of the West Delaware Basin. (1952703)
Oluwaseyifunmi Adeboboye1, Chengping Chai2, Monica Maceira2, Qingkai Kong3, Avigyan Chatterjee3, Kayla Kroll3, Alex Dzubay4, Jeff Leifer4, Scott Fertig4, Paul A Friberg4, Josh Stachnik5, Zhigang Peng6 and Chengping Chai, (1)Georgia Institute of Technology Main Campus, Earth and Atmospheric Sciences, Atlanta, United States, (2)Oak Ridge National Laboratory, Oak Ridge, TN, United States, (3)Lawrence Livermore National Laboratory, Livermore, CA, United States, (4)Instrumental Software Technologies, Inc., Saratoga Springs, United States, (5)Instrumental Software Technologies, Inc., Saratoga Springs, NY, United States, (6)Georgia Institute of Technology, School of Earth and Atmospheric Sciences, Atlanta, United States
