用扩散模型快速生成地震波场神经网络初值，训练速度提升明显。
DiffPINN: Generative diffusion-initialized physics-informed neural networks for accelerating seismic wavefield representation
- 用扩散模型生成新速度模型对应的神经网络初始参数
- 训练时间大幅缩短，对分布内/外模型均保持高精度
- 适合需快速建模多地质条件的地震模拟场景
物理信息神经网络（PINNs）在地震波场建模中表现强大，但针对不同速度模型需重复训练，且收敛缓慢。为此，本文提出基于潜在扩散模型的PINN快速初始化方法：先训练多个针对不同速度模型的频率域散射波场PINNs，将各网络参数展平为向量，构建参数数据集；再通过自编码器学习这些参数向量的潜在表示，捕捉跨模型的共性模式；最后训练一个以速度模型为条件的扩散模型，存储潜向量分布。模型训练完成后，可为新速度模型生成对应潜向量，并通过自编码器解码为完整PINN参数。实验表明，该方法显著加速训练过程，在分布内与分布外速度模型下均保持高精度。
原文摘要 · Abstract (English)
Physics-informed neural networks (PINNs) offer a powerful framework for seismic wavefield modeling, yet they typically require time-consuming retraining when applied to different velocity models. Moreover, their training can suffer from slow convergence due to the complexity of of the wavefield solution. To address these challenges, we introduce a latent diffusion-based strategy for rapid and effective PINN initialization. First, we train multiple PINNs to represent frequency-domain scattered wavefields for various velocity models, then flatten each trained network's parameters into a one-dimensional vector, creating a comprehensive parameter dataset. Next, we employ an autoencoder to learn latent representations of these parameter vectors, capturing essential patterns across diverse PINN's parameters. We then train a conditional diffusion model to store the distribution of these latent vectors, with the corresponding velocity models serving as conditions. Once trained, this diffusion model can generate latent vectors corresponding to new velocity models, which are subsequently decoded by the autoencoder into complete PINN parameters. Experimental results indicate that our method significantly accelerates training and maintains high accuracy across in-distribution and out-of-distribution velocity scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。