Varda-single-1.0：瑞士复杂地形上空1公里分辨率下的确定性数据驱动天气预报
Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography
- Federal Office of Meteorology and Climatology MeteoSwiss（瑞士联邦气象与气候办公室（MeteoSwiss））
- Swiss Data Science Center (SDSC), ETH Zürich（苏黎世联邦理工学院瑞士数据科学中心（SDSC））
- Center for Climate Systems Modeling (C2SM), ETH Zürich（苏黎世联邦理工学院气候系统建模中心（C2SM））
- European Centre for Medium-Range Weather Forecasts (ECMWF)（欧洲中期天气预报中心（ECMWF））
- Norwegian Meteorological Institute (MET Norway)（挪威气象研究所（MET Norway））
- Royal Netherlands Meteorological Institute (KNMI)（荷兰皇家气象研究所（KNMI））
- Institute for Atmospheric and Climate Science (IAC), ETH Zürich（苏黎世联邦理工学院大气与气候科学研究所（IAC））
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
Varda-single-1.0是面向阿尔卑斯山区的1公里分辨率数据驱动天气预报系统，采用拉伸网格图变换器，在多数指标上媲美或超越业务数值预报，但局部风表示存在弱点。
中文摘要 AI 辅助
我们提出了Varda-single-1.0，一个为阿尔卑斯山区域构建的中期数据驱动天气预报系统。该系统在1公里分辨率的网格上提供每小时确定性的区域预报，并在31公里网格上提供全球预报。该系统包含两个独立训练的、采用编码器-处理器-解码器架构的拉伸网格图变换器模型，开发于Anemoi框架中：一个6小时自回归预报器和一个时间降尺度器，用于在预报器步骤之间重建每小时预报。其训练课程包括在ERA5再分析数据上进行预训练，随后在20年公里级区域再分析数据上进行训练，最后在业务公里级分析数据上进行微调。经过一年与业务分析和地面站点观测的验证，Varda-single在大多数主要评分和变量上与MeteoSwiss的业务数值天气预报基线相比具有竞争力或有所改进。在提前时间长达+33小时时，它大致与高分辨率1公里ICON-CH1-EPS控制预报的技能相匹配，并且在提前时间长达+120小时时通常优于2公里ICON-CH2-EPS控制预报。尽管总体评分具有竞争力，Varda-single低估了某些局部风速最大值，并产生了过于平滑的对流降水场，这与平方误差训练相关的平滑效应一致。为了深入了解模型行为，我们研究了总体评分之外的三个案例，并发现Varda-single在复杂地形上对局部风的表示存在特定弱点。Varda-single代表了在复杂地形上开发高分辨率机器学习预报的重要一步，它补充了MeteoSwiss的业务区域数值天气预报模型，并为研究人员和特定用户应用提供了预训练模型。
英文摘要
We present Varda-single-1.0, a medium-range data-driven weather prediction system built for the Alpine domain. It provides hourly deterministic regional forecasts on a mesh of 1 km resolution and global forecasts on a 31 km mesh. The system comprises two independently trained stretched-grid Graph Transformer models with encoder-processor-decoder architecture, developed in the Anemoi framework: a 6-hourly autoregressive forecaster and a temporal downscaler reconstructing hourly forecasts between the forecaster's steps. Its training curriculum includes pre-training on ERA5 reanalysis data, followed by training on a 20-year kilometre-scale regional reanalysis, and finally fine-tuning on operational kilometre-scale analyses. Verified over one year against operational analyses and surface station observations, Varda-single is competitive with or improves on MeteoSwiss' operational numerical weather prediction baselines for most headline scores and variables. It broadly matches the skill of the high-resolution 1 km ICON-CH1-EPS control at lead times up to +33 h and generally outperforms the 2 km ICON-CH2-EPS control at lead times up to +120 h. Despite competitive aggregate scores, Varda-single underestimates some local wind maxima and produces overly smooth convective precipitation fields, consistent with the smoothing associated with squared-error training. To gain insight into the model's behaviour, we investigate three case studies beyond the aggregated headline scores, and find particular weaknesses in Varda-single's representation of local winds over complex terrain. Varda-single represents an important step in the development of high-resolution ML forecasting over complex terrain, in complementing the operational regional numerical weather prediction models of MeteoSwiss with data-driven models and in providing a pretrained model for researchers and user-specific applications.
