Japan Geoscience Union Meeting 2025

Presentation information

Print

[J] Oral

S (Solid Earth Sciences ) » S-CG Complex & General

[S-CG60] Driving Solid Earth Science through Machine Learning

Mon. May 26, 2025 3:30 PM - 5:00 PM 105 (International Conference Hall, Makuhari Messe)

convener:Hisahiko Kubo(National Research Institute for Earth Science and Disaster Resilience), Makoto Naoi(Hokkaido University), Keisuke Yano(The Institute of Statistical Mathematics), Yusuke Tanaka(Geospatial Information Authority of Japan), Chairperson:Yutaro Okada(International Research Institute of Disaster Science), Makoto Naoi(Hokkaido University)

3:30 PM - 4:00 PM

[SCG60-06] Fast and large-scale similar waveform search

★Invited Papers

*Yusuke Matsui1 (1.The University of Tokyo)

Keywords:similar waveform search, approximate nearest neighbor search

In fields such as computer vision, machine learning, and natural language processing, research on Approximate Nearest Neighbor Search (ANNS) has been actively conducted. ANNS algorithm finds vectors similar to a query vector from a large number of vectors. State-of-the-art methods enable approximate searches on a standard computer in milliseconds for 1 million to 1 billion 100-dimensional vectors. On the other hand, in seismology, a similar waveform search is a crucial problem. Applying ANNS techniques to similar waveform searches could provide new insights. This talk provides an overview of modern ANNS techniques and discusses their potential applications in seismology.