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 reconstructed high-resolution atmospheric fields, given coarsened input data. In this paper, we demonstrate this approach can be extended to the more challenging problem of increasing the accuracy and resolution of comparatively low-resolution input from a weather forecasting model, using high-resolution radar measurements as a "ground truth". The neural network must learn to add resolution and structure whilst accounting for non-negligible forecast error. We show that GANs and VAE-GANs can match the statistical properties of state-of-the-art pointwise post-processing methods whilst creating high-resolution, spatially coherent precipitation maps. Our model compares favourably to the best existing downscaling methods in both pixel-wise and pooled CRPS scores, power spectrum information and rank histograms (used to assess calibration). We test our models and show that they perform in a range of scenarios, including heavy rainfall.
Jackson School of Geosciences（杰克逊地球科学学院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；CIRES, University of Colorado Boulder（科罗拉多大学博尔德分校环境科学研究合作研究所）；NOAA/Physical Sciences Laboratory（美国国家海洋和大气管理局物理科学实验室）；Purdue University（普渡大学）；Cockrell School of Engineering（科克雷尔工程学院）
Urban downscaling is a link to transfer the knowledge from coarser climate information to city scale assessments. These high-resolution assessments need multiyear climatology of past data and future projections, which are complex and computationally expensive to generate using traditional numerical weather prediction models. The city of Austin, Texas, USA has seen tremendous growth in the past decade. Systematic planning for the future requires the availability of fine resolution city-scale datasets. In this study, we demonstrate a novel approach generating a general purpose operator using dee…
Indian Institute of Tropical Meteorology（印度热带气象研究所）；Indian Institute of Science Education and Research（印度科学教育与研究学院）；Indian Meteorological Department（印度气象局）；CIRES（环境科学合作研究所）；University of Colorado Boulder（科罗拉多大学博尔德分校）；NOAA/Physical Sciences Laboratory（美国国家海洋和大气管理局物理科学实验室）；Center for Atmospheric and Ocean Sciences, Indian Institute of Science（印度科学学院大气与海洋科学中心）
Deep Learning (DL) based downscaling has become a popular tool in earth sciences recently. Increasingly, different DL approaches are being adopted to downscale coarser precipitation data and generate more accurate and reliable estimates at local (~few km or even smaller) scales. Despite several studies adopting dynamical or statistical downscaling of precipitation, the accuracy is limited by the availability of ground truth. A key challenge to gauge the accuracy of such methods is to compare the downscaled data to point-scale observations which are often unavailable at such small scales. In th…
RainScaleGAN: a Conditional Generative Adversarial Network for Rainfall Downscaling
Institute for Applied Mathematics and Information Technologies, CNR（意大利国家研究委员会应用数学与信息技术研究所）；Institute of Atmospheric Sciences and Climate, CNR（意大利国家研究委员会大气科学与气候研究所）；Politecnico di Torino（都灵理工大学）
Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model
School of Computing, KAIST（韩国科学技术院计算机学院）；Data Science Group, IBS（基础科学研究院数据科学组）；Department of Climate System, PNU（釜山大学气候系统系）；Center for Climate Physics, IBS（基础科学研究院气候物理中心）
University of Cambridge（剑桥大学）；British Antarctic Survey（英国南极调查局）；The Alan Turing Institute（艾伦·图灵研究所）
A new model is presented for multisite statistical downscaling of temperature and precipitation using convolutional conditional neural processes (convCNPs). ConvCNPs are a recently developed class of models that allow deep learning techniques to be applied to off-the-grid spatio-temporal data. This model has a substantial advantage over existing downscaling methods in that the trained model can be used to generate multisite predictions at an arbitrary set of locations, regardless of the availability of training data. The convCNP model is shown to outperform an ensemble of existing downscaling …
Conditional diffusion models for downscaling and bias correction of Earth system model precipitation
Technical University of Munich（慕尼黑技术大学）；Munich Climate Center（慕尼黑气候中心）；TUM School of Engineering and Design（慕尼黑技术大学工程与设计学院）；Potsdam Institute for Climate Impact Research（波茨坦气候影响研究所）；Institute of Atmospheric Physics（大气物理研究所）；University of Exeter（埃克塞特大学）
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）
Argonne National Laboratory（阿贡国家实验室）；University of Cincinnati（辛辛那提大学）
This study develops a neural network-based approach for emulating high-resolution modeled precipitation data with comparable statistical properties but at greatly reduced computational cost. The key idea is to use combination of low- and high- resolution simulations to train a neural network to map from the former to the latter. Specifically, we define two types of CNNs, one that stacks variables directly and one that encodes each variable before stacking, and we train each CNN type both with a conventional loss function, such as mean square error (MSE), and with a conditional generative adver…
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）
UC Berkeley（加州大学伯克利分校）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
Forecasting global precipitation patterns and, in particular, extreme precipitation events is of critical importance to preparing for and adapting to climate change. Making accurate high-resolution precipitation forecasts using traditional physical models remains a major challenge in operational weather forecasting as they incur substantial computational costs and struggle to achieve sufficient forecast skill. Recently, deep-learning-based models have shown great promise in closing the gap with numerical weather prediction (NWP) models in terms of precipitation forecast skill, opening up excit…
RainShift: A Benchmark for Precipitation Downscaling Across Geographies
Mila Quebec AI Institute（魁北克AI研究所）；European Centre for Medium Range Weather Forecasts（欧洲中期天气预报中心）；Cluster of Excellence Machine Learning（卓越机器学习集群）；University of Tübingen（图宾根大学）；McGill University（麦吉尔大学）
本文提出 RainShift 数据集与基准，系统评估 GAN 和扩散模型等降尺度方法在跨地理分布偏移下的泛化能力，揭示分布外区域性能显著下降，并证明数据对齐可改善空间泛化，推动高分辨率气候信息的全球公平获取。
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
University of Colorado, Boulder（科罗拉多大学博尔德分校）；Jupiter Intelligence Inc.（木星智能公司）
Downscaling is a landmark task in climate science and meteorology in which the goal is to use coarse scale, spatio-temporal data to infer values at finer scales. Statistical downscaling aims to approximate this task using statistical patterns gleaned from an existing dataset of downscaled values, often obtained from observations or physical models. In this work, we investigate the application of deep latent variable learning to the task of statistical downscaling. We present ClimAlign, a novel method for unsupervised, generative downscaling using adaptations of recent work in normalizing flows…
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…
An impact of climate change is the increase in frequency and intensity of extreme precipitation events. However, confidently predicting the likelihood of extreme precipitation at seasonal scales remains an outstanding challenge. Here, we present an approach to forecasting the quantiles of the maximum daily precipitation in each week up to six months ahead using the temporal fusion transformer (TFT) model. Through experiments in two regions, we compare TFT predictions with those of two baselines: climatology and a calibrated ECMWF SEAS5 ensemble forecast (S5). Our results show that, in terms of…
Indian Institute of Tropical Meteorology, Ministry of Earth Sciences（印度热带气象研究所，地球科学部）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；Ramrao Adik Institute of Technology（拉姆劳·阿迪克技术学院）；Defence Institute of Advanced Technology（国防高级技术研究所）
Downscaling is necessary to generate high-resolution observation data to validate the climate model forecast or monitor rainfall at the micro-regional level operationally. Dynamical and statistical downscaling models are often used to get information at high-resolution gridded data over larger domains. As rainfall variability is dependent on the complex Spatio-temporal process leading to non-linear or chaotic Spatio-temporal variations, no single downscaling method can be considered efficient enough. In data with complex topographies, quasi-periodicities, and non-linearities, deep Learning (DL…
Jackson School of Geosciences（杰克逊地球科学学院）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Indian Institute of Tropical Meteorology（印度热带气象研究所）；Ministry of Earth Sciences（地球科学部）；CIRES, University of Colorado Boulder（科罗拉多大学博尔德分校环境科学研究合作研究所）；NOAA/Physical Sciences Laboratory（美国国家海洋和大气管理局物理科学实验室）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Precipitation governs Earth's hydroclimate, and its daily spatiotemporal fluctuations have major socioeconomic effects. Advances in Numerical weather prediction (NWP) have been measured by the improvement of forecasts for various physical fields such as temperature and pressure; however, large biases exist in precipitation prediction. We augment the output of the well-known NWP model CFSv2 with deep learning to create a hybrid model that improves short-range global precipitation at 1-, 2-, and 3-day lead times. To hybridise, we address the sphericity of the global data by using modified DLWP-C…
Compressing high-resolution data through latent representation encoding for downscaling large-scale AI weather forecast model
Shanghai Academy of Artificial Intelligence for Science（上海科学人工智能研究院）；Shanghai Normal University（上海师范大学）；Jiangsu Meteorological Observatory（江苏省气象台）；Artificial Intelligence Innovation and Incubation Institute, Fudan University（复旦大学人工智能创新与孵化研究院）；Nanjing Meteorological Observatory（南京市气象台）
University of Oxford（牛津大学）；The Alan Turing Institute（艾伦·图灵研究所）；ClimateAI
Accurately forecasting extreme rainfall is notoriously difficult, but is also ever more crucial for society as climate change increases the frequency of such extremes. Global numerical weather prediction models often fail to capture extremes, and are produced at too low a resolution to be actionable, while regional, high-resolution models are hugely expensive both in computation and labour. In this paper we explore the use of deep generative models to simultaneously correct and downscale (super-resolve) global ensemble forecasts over the Continental US. Specifically, using fine-grained radar o…
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-…
High-resolution climatic data are essential to many applications in environmental research. Here we develop a new semi-mechanistic downscaling approach for daily precipitation that incorporates high resolution (30 arc sec) satellite-derived cloud frequency. The downscaling algorithm incorporates orographic predictors such as wind fields, valley exposition, and boundary layer height, with a subsequent bias correction. We apply the method to the ERA5 precipitation archive and MODIS monthly cloud cover frequency to develop a daily gridded precipitation time series in 1km resolution for the years …
Global spatio-temporal downscaling of ERA5 precipitation through generative AI
Institute of Meteorology and Climate Research - Atmospheric Environmental Research (IMK-IFU)（气象与气候研究所——大气环境研究（IMK-IFU））；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Institute of Meteorology and Climate Research - Atmospheric Trace Gases and Remote Sensing (IMK-ASF)（气象与气候研究所——大气痕量气体与遥感（IMK-ASF））；University of Augsburg（奥格斯堡大学）
In an effort to provide optimal inputs to downstream modeling systems (e.g., a hydrodynamics model that simulates the water circulation of a lake), we hereby strive to enhance resolution of precipitation fields from a weather model by up to 9x. We test two super-resolution models: the enhanced super-resolution generative adversarial networks (ESRGAN) proposed in 2017, and the content adaptive resampler (CAR) proposed in 2020. Both models outperform simple bicubic interpolation, with the ESRGAN exceeding expectations for accuracy. We make several proposals for extending the work to ensure it ca…
Predicting future climatic conditions at high spatial resolution is essential for many applications and impact studies in science. Here, we present monthly time series data on precipitation, minimum- and maximum temperature for four downscaled global circulation models. We used model output statistics in combination with mechanistic downscaling (the CHELSa algorithm) to calculate mean monthly maximum and minimum temperatures, as well as monthly precipitation at 5 km spatial resolution globally for the years 2006-2100. We validated the performance of the downscaling algorithm by comparing model…
An intercomparison of generative machine learning methods for downscaling precipitation at fine spatial scales
Earth Sciences New Zealand（新西兰地球科学）；School of Computer Science, University of Auckland（奥克兰大学计算机科学学院）；NVIDIA AI Technology Centre, NVIDIA Corporation（英伟达人工智能技术中心，英伟达公司）；ARC Centre of Excellence for Weather of the 21st Century & Climate Change Research Centre, University of New South Wales（新南威尔士大学21世纪天气卓越研究中心及气候变化研究中心）；Commonwealth Scientific and Industrial Research Organisation (CSIRO)（联邦科学与工业研究组织（CSIRO））；Laboratory for Turbulence Research in Aerospace and Combustion, Department of Mechanical and Aerospace Engineering, Monash University（莫纳什大学机械与航空航天工程系航空与燃烧湍流研究实验室）
Downscaling with AI reveals the large role of internal variability in fine-scale projections of climate extremes
National Institute of Water and Atmospheric Research (NIWA)（国家水气和大气研究所）；ARC Centre of Excellence for Weather of the 21st Century（21世纪天气卓越研究中心）；University of New South Wales（新南威尔士大学）；Climate Change Research Centre, University of New South Wales（新南威尔士大学气候变化研究中心）；Te Aka Mātuatua School of Science, University of Waikato（怀卡托大学理学院）
Projection of changes in extreme indices of climate variables such as temperature and precipitation are critical to assess the potential impacts of climate change on human-made and natural systems, including critical infrastructures and ecosystems. While impact assessment and adaptation planning rely on high-resolution projections (typically in the order of a few kilometers), state-of-the-art Earth System Models (ESMs) are available at spatial resolutions of few hundreds of kilometers. Current solutions to obtain high-resolution projections of ESMs include downscaling approaches that consider …
