Adapting vision foundation models with LoRA and kurtosis-guided unsupervised test-time adaptation matches or exceeds domain-specific models for seismic denoising across multiple sites and unseen data.
Geophysical Journal International , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
physics.geo-ph 2years
2026 2representative citing papers
Introduces a staged pretrain-to-alignment workflow for geophysical AI that improves relative geologic time estimation across global field surveys despite limited labels and domain gaps.
citing papers explorer
-
Parameter-Efficient Adaptation of Pre-Trained Vision Foundation Models for Active and Passive Seismic Data Denoising
Adapting vision foundation models with LoRA and kurtosis-guided unsupervised test-time adaptation matches or exceeds domain-specific models for seismic denoising across multiple sites and unseen data.
-
Pretrain-to-alignment learning paradigm to improve geophysical AI applicability under scarce field labels and synthetic-to-field gaps: A case study of relative geologic time estimation in global shelf-edge clinothems
Introduces a staged pretrain-to-alignment workflow for geophysical AI that improves relative geologic time estimation across global field surveys despite limited labels and domain gaps.