用条件扩散模型修复卫星降水数据缺失，提升时空一致性。
Conditional Diffusion Models for Global Precipitation Map Inpainting
- 基于3D U-Net与条件编码器，融合红外图、经纬网格和时间信息
- 在2024年评估中，生成结果比传统方法更连续稳定
- 适合气象监测、遥感数据修复等需要高精度降水图的研究者
基于卫星的降水观测存在显著缺失问题，例如日本宇宙航空研究开发机构（JAXA）的全球卫星降水映射（GSMaP）因微波传感器轨道特性导致大片区域缺失，现有插值方法常引发空间不连续。本研究将降水图修复视为视频修复任务，提出基于条件扩散模型的机器学习方法。采用3D U-Net结合3D条件编码器，利用红外图像、经纬度网格和物理时间输入，重建完整降水图。训练基于2020至2023年ERA5每小时降水数据，通过随机应用GSMaP掩码生成伪GSMaP数据集。2024年评估结果显示，该方法生成的修复降水图在时空上更一致，表明条件扩散模型在提升全球降水监测方面的潜力。
原文摘要 · Abstract (English)
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.
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。