CLARA：仅用站点观测数据学习联合概率天气预测
Learning joint probabilistic weather forecasts from station observations alone
一个只有 2.8 万参数的小模型，不靠数值预报，纯站点数据就能做联合概率天气预测，CPU 就能跑，做气象的可以看看。
arXiv 论文提出 CLARA（Calibrated Advection-Routing Attention），仅从站点观测数据学习五个地面变量的联合高斯预测分布，不依赖数值天气预报或再分析数据。模型约 28,000 参数，可在 CPU 上训练和预测。在 96 个站点的六组多年折验证中，其平均 lead 能量分数比同输入的对比模型低 4.9%，比统计基线低 11-65%。模型在六大洲十个区域重训后，60 组区域-lead 对比中全部优于 persistence，57 组优于同等规模的对比模型。
Learning joint probabilistic weather forecasts from station observations alone
Assessing compound weather risks requires forecasts representing dependence between variables. CLARA (Calibrated Advection-Routing Attention) learns joint Gaussian predictive distributions of five surface variables from station observations alone, without numerical weather prediction or reanalysis; the approximately 28,000-parameter model supports CPU training and prediction. Across six multi-year folds on 96 stations, its lead-mean energy score is 4.9% lower than that of a learned comparator with matched temporal inputs (4.7% with a similar parameter count) and 11-65% lower than those of statistical baselines. Holding marginal variances fixed, removing learned correlations worsens joint negative log-likelihood by 1.0-2.8 nats per station. A covariance-scale estimator, proved consistent under stated assumptions, improves short-lead calibration but over-corrects at long leads. Synthetic interventions show an attention-bias coefficient alone does not measure forecast influence. Retrained in ten regions on six continents, CLARA outperforms persistence in all 60 multi-year region-lead comparisons and a similarly sized learned model in 57 of 60.
