通过可组合接口从异构原位观测进行生成式大气超分辨率重建
Generative Atmospheric Super-Resolution from Heterogeneous In Situ Observations through Composable Interfaces
浏览论文内容
中文总结 AI 辅助
针对大气观测稀疏异构的问题，提出可组合观测接口，使预训练扩散模型融合无线电探空仪、飞机和地面站数据，实现生成式超分辨率重建，显著降低RMSE和CRPS，无需重新训练模型。
中文摘要 AI 辅助
大气观测是稀疏、异构且分布不均的，而许多生成式大气模型学习的是规则网格化多变量状态上的分布。一旦预训练完成，扩散模型可以提供大气先验，这些先验可以在贝叶斯框架中与观测导出的似然因子相结合。然而，这些观测源在几何形状和采样密度上差异很大，使得在共同的推理框架内一致使用它们的观测变得复杂。在此，我们将这一重建问题表述为生成式大气超分辨率，并引入可组合观测接口，用于对单个预训练的13变量大气扩散模型进行条件约束。这些接口将稀疏的无线电探空仪（R）、聚集的飞机（A）和密集的不规则地面站（S）观测转换为特定源的似然因子，这些因子指定了观测在何处约束网格状态、在不均匀采样下残差如何计算，以及每个源对后验采样的引导强度。我们使用2019年的观测数据开发了飞机和地面站观测接口，并在2020年全年评估了所选接口，无需进一步调整。与仅以无线电探空仪观测为条件的重建相比，由R+A+S组合接口在CONUS域内所有13个状态变量上，相对于ERA5评估的RMSE降低了9.24%。飞机和地面站因子在上层大气和地面变量方面提供了互补的改进。R+A+S组合还降低了连续排名概率分数（CRPS），而在保留的飞机和地面站观测上的评估显示预测误差减少。这些结果共同展示了一种模块化途径，可以在不重新训练底层模型的情况下，将预训练的大气生成先验条件于异构原位观测。
英文摘要
Atmospheric observations are sparse, heterogeneous, and unevenly distributed, whereas many generative atmospheric models learn distributions over regularly gridded multivariate states. Once pretrained, diffusion models can supply atmospheric priors that can be combined with observation-derived likelihood factors in a Bayesian formulation. However, these observation sources differ substantially in geometry and sampling density, complicating the consistent use of their observations within a common inference framework. Here, we formulate this reconstruction problem as generative atmospheric super-resolution and introduce composable observation interfaces for conditioning a single pretrained 13-variable atmospheric diffusion model. The interfaces convert sparse radiosonde (R), clustered aircraft (A), and dense irregular surface-station (S) observations into source-specific likelihood factors that specify where observations constrain the gridded state, how residuals are counted under uneven sampling, and how strongly each source guides posterior sampling. We developed the aircraft and surface observation interfaces using 2019 observations and evaluated the selected interfaces throughout 2020 without further tuning. Compared with reconstructions conditioned only on radiosonde observations, the composed R+A+S interface reduces RMSE evaluated against ERA5 by $9.24\%$ across all 13 state variables over the CONUS domain. The aircraft and surface factors provide complementary improvements in upper-air and surface variables. The R+A+S combination also lowers the Continuous Ranked Probability Score (CRPS), while evaluations at held-out aircraft and surface-station observations show reduced prediction errors. Together, these results demonstrate a modular route for conditioning a pretrained atmospheric generative prior on heterogeneous in situ observations without retraining the underlying model.
发表机构
- Purdue University（普渡大学）
- The Pennsylvania State University（宾夕法尼亚州立大学）
机构由 AI 辅助整理，请以论文原文为准。
