Prototype-driven contrastive learning enables transferable seismic representation
Authors:
- Fanchun MengFMFanchun Meng
- Tao RenTRTao Ren
- Hengwei ZhangHZHengwei Zhang
- Xinyue WangXWXinyue Wang
- 10 June 2026
- journal article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 181
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62276058)
- National Natural Science Foundation of China (41774063)
- National University's Basic Research Foundation of China
- Fundamental Research Funds for the Central Universities (N2217003)
- Fundamental Research Funds for the Central Universities (N25LPY049)
This publication has 33 references indexed in Scilit:
- Seismic denoising diffusion restoration model for seismic data processingEngineering Applications of Artificial Intelligence, 2025
- Self-similar spectral reasoning network for efficient anti-aliasing seismic data reconstructionEngineering Applications of Artificial Intelligence, 2025
- DFTQuake: Tripartite Fourier attention and dendrite network for real-time early prediction of earthquake magnitude and peak ground accelerationEngineering Applications of Artificial Intelligence, 2025
- Multi-scale convolution networks for seismic event classification with windowed self-attentionJournal of Seismology, 2024
- Earthquake magnitude estimation using a two-step convolutional neural networkJournal of Seismology, 2024
- Estimation of ground motion parameters via multi-task deep neural networksNatural Hazards, 2024
- Automated Seismic Source Characterization Using Deep Graph Neural NetworksGeophysical Research Letters, 2020
- A Machine‐Learning Approach for Earthquake Magnitude EstimationGeophysical Research Letters, 2020
- Classification of Tectonic and Nontectonic Earthquakes by an Integrated Learning AlgorithmPure and Applied Geophysics, 2019
- The nature of noise wavefield and its applications for site effects studiesEarth-Science Reviews, 2006