Keywords: generative modeling, material microstructures, diffusion, organic photovoltaics, design
TL;DR: Using diffusion models to generate the two-phase microstructures in organic solar cells.
Abstract: Score-based methods, particularly denoising diffusion probabilistic models (DDPMs), have demonstrated impressive improvements to state-of-the-art generative modeling. Due to their impressive ability to sample from complex distributions, DDPM models and related variants, all broadly categorized under diffusion models, apply to various applications. In this work, we compare the performance of a diffusion model with a Wasserstein Generative Adversarial Network in generating two-phase microstructures of photovoltaic cells. We demonstrate the diffusion model's performance improvements in generating realistic-looking microstructures and its ability to cover several modes of the target distribution.
Paper Track: Papers
Submission Category: AI-Guided Design