Conditional Diffusion Models for Global Precipitation Map Inpainting
This addresses the challenge of missing data in global precipitation monitoring for applications like weather forecasting, though it is incremental as it builds on existing diffusion models.
The study tackled the problem of incomplete satellite-based precipitation maps by formulating it as a video inpainting task and using a conditional diffusion model with a 3D U-Net, resulting in more spatio-temporally consistent inpainted maps compared to conventional methods.
Incomplete satellite-based precipitation presents a significant challenge in global monitoring. For example, the Global Satellite Mapping of Precipitation (GSMaP) from JAXA suffers from substantial missing regions due to the orbital characteristics of satellites that have microwave sensors, and its current interpolation methods often result in spatial discontinuities. In this study, we formulate the completion of the precipitation map as a video inpainting task and propose a machine learning approach based on conditional diffusion models. Our method employs a 3D U-Net with a 3D condition encoder to reconstruct complete precipitation maps by leveraging spatio-temporal information from infrared images, latitude-longitude grids, and physical time inputs. Training was carried out on ERA5 hourly precipitation data from 2020 to 2023. We generated a pseudo-GSMaP dataset by randomly applying GSMaP masks to ERA maps. Performance was evaluated for the calendar year 2024, and our approach produces more spatio-temporally consistent inpainted precipitation maps compared to conventional methods. These results indicate the potential to improve global precipitation monitoring using the conditional diffusion models.