Localization of microseismic events using physics-informed neural networks for traveltime computation

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

The paper demonstrates an algorithm for using physics-informed neural networks in the workflow of microseismic data processing and more specifically the problem of localization of microseismic events. The proposed algorithm involves the use of a physics-informed neural network solution to the eikonal equation to calculate the traveltimes of the first arrivals. As a result, the network solution is compared with the observed arrival times to solve the inverse kinematic problem to determine the coordinates of the event locations. Using a synthetic 3D example, it was shown that the average absolute error of the arrival time misfit was less than 0.25 ms, and the average localization error did not exceed 4.5 meters.

Original languageEnglish
Title of host publication82nd EAGE Conference and Exhibition 2021
PublisherEuropean Association of Geoscientists and Engineers, EAGE
Pages5228-5232
Number of pages5
ISBN (Electronic)978-171384144-9
Publication statusPublished - 2021
Event82nd EAGE Conference and Exhibition 2021 - Amsterdam, Virtual, Netherlands
Duration: 18 Oct 202121 Oct 2021

Publication series

Name82nd EAGE Conference and Exhibition 2021
Volume7

Conference

Conference82nd EAGE Conference and Exhibition 2021
CountryNetherlands
CityAmsterdam, Virtual
Period18.10.202121.10.2021

OECD FOS+WOS

  • 1.05 EARTH AND RELATED ENVIRONMENTAL SCIENCES

Fingerprint

Dive into the research topics of 'Localization of microseismic events using physics-informed neural networks for traveltime computation'. Together they form a unique fingerprint.

Cite this