The state of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis. To address the large resolution ratio, different physics involved at different scales and prediction of channels beyond those in the input data, we employ a two-step approach where a UNet predicts the mean and a corrector diffusion (CorrDiff) model predicts the residual. CorrDiff exhibits encouraging skill in bulk MAE and CRPS scores. The predicted spectra and distributions from CorrDiff faithfully recover important power law relationships in the target data. Case studies of coherent weather phenomena show that CorrDiff can help sharpen wind and temperature gradients that co-locate with intense rainfall in cold front, and can help intensify typhoons and synthesize rain band structures. Calibration of model uncertainty remains challenging. The prospect of unifying methods like CorrDiff with coarser resolution global weather models implies a potential for global-to-regional multi-scale machine learning simulation.
China Regional 3km Downscaling Based on Residual Corrective Diffusion Model
State Key Laboratory of Severe Weather Meteorological Science and Technology（severe weather meteorological science and technology state key laboratory）；CMA Earth System Modeling and Prediction Centre；NVIDIA；Tsinghua University
Statistical Downscaling of Daily Precipitation from ERA5 Atmospheric Fields to IMERG over West Africa
Laboratoire d’Océanographie et des Sciences de l’Environnement et du Climat (LOSEC)Université Assane Seck de Ziguinchor（西古尔省阿萨内·塞克大学海洋与环境气候学实验室）；Institut Pierre-Simon Laplace (IPSL), Sorbonne Université, IRD（皮埃尔-西蒙·拉普拉斯研究所，索邦大学，法国国家科学研究中心）
École polytechnique fédérale de Lausanne（洛桑联邦理工学院）；Federal Office of Meteorology and Climatology MeteoSwiss（联邦气象和气候学办公室 MeteoSwiss）
Generative adversarial networks (GANs) have been recently adopted for super-resolution, an application closely related to what is referred to as "downscaling" in the atmospheric sciences: improving the spatial resolution of low-resolution images. The ability of conditional GANs to generate an ensemble of solutions for a given input lends itself naturally to stochastic downscaling, but the stochastic nature of GANs is not usually considered in super-resolution applications. Here, we introduce a recurrent, stochastic super-resolution GAN that can generate ensembles of time-evolving high-resoluti…
Kumamoto University（熊本大学）；University of California, Davis（加州大学戴维斯分校）；Sun Yat-Sen University（中山大学）
Deep learning has been utilized for the statistical downscaling of climate data. Specifically, a two-dimensional (2D) convolutional neural network (CNN) has been successfully applied to precipitation estimation. This study implements a three-dimensional (3D) CNN to estimate watershed-scale daily precipitation from 3D atmospheric data and compares the results with those for a 2D CNN. The 2D CNN is extended along the time direction (3D-CNN-Time) and the vertical direction (3D-CNN-Vert). The precipitation estimates of these extended CNNs are compared with those of the 2D CNN in terms of the root-…
Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Department of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程系）；School of Computer and Information Sciences, University of Newcastle（纽卡斯尔大学计算机与信息科学学院）；School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University（西北工业大学人工智能、光学与电子学学院（iOPEN））
Refining low-resolution (LR) spatial fields with high-resolution (HR) information, often known as statistical downscaling, is challenging as the diversity of spatial datasets often prevents direct matching of observations. Yet, when LR samples are modeled as aggregate conditional means of HR samples with respect to a mediating variable that is globally observed, the recovery of the underlying fine-grained field can be framed as taking an "inverse" of the conditional expectation, namely a deconditioning problem. In this work, we propose a Bayesian formulation of deconditioning which naturally r…
Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscaling
University of Florida（佛罗里达大学）；Stony Brook University（石溪大学）；University of Maryland（马里兰大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）；Pacific Northwest National Laboratory（太平洋西北国家实验室）
Time-aware UNet and super-resolution deep residual networks for spatial downscaling
Department of Mathematics and Statistics（数学与统计学系）；University of Jyväskylä（于韦斯屈莱大学）；Department of Economic Sciences（经济科学系）；University of Salento（萨伦托大学）；National Centre for HPC, Big Data and Quantum Computing（高性能计算、大数据与量子计算国家中心）；National Biodiversity Future Center（国家生物多样性未来中心）；University of Helsinki（赫尔辛基大学）
Representation learning has proven to be a powerful methodology in a wide variety of machine learning applications. For atmospheric dynamics, however, it has so far not been considered, arguably due to the lack of large-scale, labeled datasets that could be used for training. In this work, we show that the difficulty is benign and introduce a self-supervised learning task that defines a categorical loss for a wide variety of unlabeled atmospheric datasets. Specifically, we train a neural network on the simple yet intricate task of predicting the temporal distance between atmospheric fields fro…
Transformer based super-resolution downscaling for regional reanalysis: Full domain vs tiling approaches
Predictia Intelligent Data Solutions S.L.（普雷迪西亚智能数据解决方案有限公司）；Instituto de Física de Cantabria (IFCA), CSIC-Universidad de Cantabria（坎塔布里亚物理研究所（IFCA），西班牙国家研究委员会-坎塔布里亚大学）
University of Oxford（牛津大学）；European Centre for Medium-Range Weather Forecasts（欧洲中期天气预报中心）
Despite continuous improvements, precipitation forecasts are still not as accurate and reliable as those of other meteorological variables. A major contributing factor to this is that several key processes affecting precipitation distribution and intensity occur below the resolved scale of global weather models. Generative adversarial networks (GANs) have been demonstrated by the computer vision community to be successful at super-resolution problems, i.e., learning to add fine-scale structure to coarse images. Leinonen et al. (2020) previously applied a GAN to produce ensembles of reconstruct…
Quantile Regression, Variational Autoencoders, and Diffusion Models for Uncertainty Quantification: A Spatial Analysis of Sub-seasonal Wind Speed Prediction
WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric Modeling
Munich Climate Center（慕尼黑气候中心）；Earth System Modelling Group, TUM School of Engineering（地球系统建模组，技术大学工程学院）；Design, Technical University of Munich, Germany（设计，慕尼黑技术大学，德国）；ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz, Austria（ELLIS单元，LIT人工智能实验室，机器学习研究所，JKU林茨，奥地利）；Emmi AI GmbH, Linz, Austria（Emmi AI GmbH，林茨，奥地利）；Potsdam Institute for Climate Impact Research, Potsdam, Germany（波茨坦气候影响研究所，波茨坦，德国）；Department of Mathematics, University of Exeter, Exeter, United Kingdom（数学系，埃克塞特大学，埃克塞特，英国）
Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution
Fudan University（复旦大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Beihang University（北京航空航天大学）；Columbia University（哥伦比亚大学）；Nanjing University of Information Science and Technology（南京信息工程大学）
