A Novel Diffusion Model for Pairwise Geoscience Data Generation with Unbalanced Training Dataset
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21965-21973
Abstract
Recently, the advent of generative AI technologies has made transformational impacts on our daily lives, yet its application in scientific applications remains in its early stages. Data scarcity is a major, well-known barrier in data-driven scientific computing, so physics-guided generative AI holds significant promise. In scientific computing, most tasks study the conversion of multiple data modalities to describe physical phenomena, for example, spatial and waveform in seismic imaging, time and frequency in signal processing, and temporal and spectral in climate modeling; as such, multi-modal pairwise data generation is highly required instead of single-modal data generation, which is usually used in natural images (e.g., faces, scenery). Moreover, in real-world applications, the unbalance of available data in terms of modalities commonly exists; for example, the spatial data (i.e., velocity maps) in seismic imaging can be easily simulated, but real-world seismic waveform is largely lacking. While the most recent efforts enable the powerful diffusion model to generate multi-modal data, how to leverage the unbalanced available data is still unclear. In this work, we use seismic imaging in subsurface geophysics as a vehicle to present "UB-Diff", a novel diffusion model for multi-modal paired scientific data generation. One major innovation is a one-in-two-out encoder-decoder network structure, which can ensure pairwise data is obtained from a co-latent representation. Then, the co-latent representation will be used by the diffusion process for pairwise data generation. Experimental results on the OpenFWI dataset show that UB-Diff significantly outperforms existing techniques in terms of Fréchet Inception Distance (FID) score and pairwise evaluation, indicating the generation of reliable and useful multi-modal pairwise data.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Using diffusion models to generate synthetic labeled data for medical image segmentationInternational Journal of Computer Assisted Radiology and Surgery, 2024
- Generative artificial intelligence, human creativity, and artPNAS Nexus, 2024
- Denoising diffusion probabilistic models for 3D medical image generationScientific Reports, 2023
- CodeFusion: A Pre-trained Diffusion Model for Code Generation2023
- Photorealistic Text-To-Image Diffusion Models with Deep Language Understanding2022
- Diffusion-LM Improves Controllable Text Generation2022
- InversionNet3D: Efficient and Scalable Learning for 3-D Full-Waveform InversionIEEE Transactions on Geoscience and Remote Sensing, 2021
- Data-Driven Seismic Waveform Inversion: A Study on the Robustness and GeneralizationIEEE Transactions on Geoscience and Remote Sensing, 2020
- InversionNet: An Efficient and Accurate Data-Driven Full Waveform InversionIEEE Transactions on Computational Imaging, 2019
- Fault interpretation in seismic reflection data: an experiment analysing the impact of conceptual model anchoring and vertical exaggerationSolid Earth, 2019