用稀疏气象站数据实现气象变量任意分辨率下采样，精度显著提升。
Sparse Local Implicit Image Function for sub-km Weather Downscaling
- 基于稀疏观测点与地形数据构建隐式神经表示模型
- 温度下采样精度比现有方法最高提升50%，风速提升10-20%
- 适用于日本区域气象精细化建模，尤其适合数据稀疏场景
我们提出SpLIIF，用于生成隐式神经表示，并实现气象变量的任意下采样。模型在覆盖日本的稀疏气象站和地形数据上训练，评估了对温度和风速的分布内与分布外预测性能，分别与插值基准和CorrDiff方法进行对比。结果表明，该模型在温度下采样上相比CorrDiff和基线方法最高提升50%，在风速下采样上提升约10-20%。
原文摘要 · Abstract (English)
We introduce SpLIIF to generate implicit neural representations and enable arbitrary downscaling of weather variables. We train a model from sparse weather stations and topography over Japan and evaluate in- and out-of-distribution accuracy predicting temperature and wind, comparing it to both an interpolation baseline and CorrDiff. We find the model to be up to 50% better than both CorrDiff and the baseline at downscaling temperature, and around 10-20% better for wind.
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。