Search

We introduce deep generative diffusion for multivariate and regional surrogate modeling learned from sea‐ice simulations. Given initial conditions and atmospheric forcings, the model is trained to generate forecasts for a 12‐hr lead time from simulations by the state‐of‐the‐art sea‐ice model neXtSIM. For our regional model setup, the diffusion model outperforms as ensemble forecast all other tested models, including a free‐drift model and a stochastic extension of a deterministic data‐driven surrogate model. The diffusion model additionally retains information at all scales, resolving smoothing issues of deterministic models. Furthermore, by generating physically consistent forecasts, previously unseen for such kind of completely data‐driven surrogates, the model can almost match the scaling properties of neXtSIM, as similarly deduced from sea‐ice observations. With these results, we provide a strong indication that diffusion models can achieve similar results as traditional geophysical models with the significant advantage of being orders of magnitude faster and solely learned from data. Plain Language Summary: Thanks to generative deep learning, computers can generate images that are almost indistinguishable from real images. We use this technology to forecast the sea‐ice with models that are solely learned from data, here from simulation data. Doing so for a region North of Svalbard, we enhance the accuracy of the model and maintain their sharpness. The learned model further depicts physical processes as similarly observed for the targeted physical‐driven model. Therefore, this technology could provide us with the necessary tools to learn faster models from data that have similar properties to those based on physical equations. Key Points: We introduce the first denoising diffusion model designed for sea‐ice physicsGenerative diffusion outperforms deterministic surrogates and retains the sharpness in the forecasts as observed in the targeted simulationsOur model generates forecasts that exhibit physical consistency between variables in space and time [ABSTRACT FROM AUTHOR]

Deep neural networks have significantly advanced the field of medical image analysis, yet their full potential is often limited by relatively small dataset sizes. Generative modeling, particularly through diffusion models, has unlocked remarkable capabilities in synthesizing photorealistic images, thereby broadening the scope of their application in medical imaging. This study specifically investigates the use of diffusion models to generate high-quality brain MRI scans, including those depicting low-grade gliomas, as well as contrast-enhanced spectral mammography (CESM) and chest and lung X-ray images. By leveraging the DreamBooth platform, we have successfully trained stable diffusion models utilizing text prompts alongside class and instance images to generate diverse medical images. This approach not only preserves patient anonymity but also substantially mitigates the risk of patient re-identification during data exchange for research purposes. To evaluate the quality of our synthesized images, we used the Fréchet inception distance metric, demonstrating high fidelity between the synthesized and real images. Our application of diffusion models effectively captures oncology-specific attributes across different imaging modalities, establishing a robust framework that integrates artificial intelligence in the generation of oncological medical imagery. [ABSTRACT FROM AUTHOR]