We use a conditional deep convolutional generative adversarial network to predict the geopotential height of the 500 hPa pressure level, the two-meter temperature and the total precipitation for the next 24 hours over Europe. The proposed models are trained on 4 years of ERA5 reanalysis data from 2015-2018 with the goal to predict the associated meteorological fields in 2019. The forecasts show a good qualitative and quantitative agreement with the true reanalysis data for the geopotential height and two-meter temperature, while failing for total precipitation, thus indicating that weather forecasts based on data alone may be possible for specific meteorological parameters. We further use Monte-Carlo dropout to develop an ensemble weather prediction system based purely on deep learning strategies, which is computationally cheap and further improves the skill of the forecasting model, by allowing to quantify the uncertainty in the current weather forecast as learned by the model.
University Bremen（不来梅大学）；Memorial University of Newfoundland（纽芬兰纪念大学）
Ensemble prediction systems are an invaluable tool for weather forecasting. Practically, ensemble predictions are obtained by running several perturbations of the deterministic control forecast. However, ensemble prediction is associated with a high computational cost and often involves statistical post-processing steps to improve its quality. Here we propose to use deep-learning-based algorithms to learn the statistical properties of an ensemble prediction system, the ensemble spread, given only the deterministic control forecast. Thus, once trained, the costly ensemble prediction system will…
CoDiCast: Conditional Diffusion Model for Global Weather Prediction with Uncertainty Quantification
Florida International University（佛罗里达国际大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Hurricane Research Division, National Oceanic and Atmospheric Administration（国家海洋和大气管理局飓风研究 division）
Federal Office of Meteorology and Climatology MeteoSwiss（瑞士联邦气象与气候办公室）；Comerge（Comerge公司）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；ETH Zürich（苏黎世联邦理工学院）；University of Amsterdam（阿姆斯特丹大学）
Outdoor webcam images are an information-dense yet accessible visualization of past and present weather conditions, and are consulted by meteorologists and the general public alike. Weather forecasts, however, are still communicated as text, pictograms or charts. We therefore introduce a novel method that uses photographic images to also visualize future weather conditions. This is challenging, because photographic visualizations of weather forecasts should look real, be free of obvious artifacts, and should match the predicted weather conditions. The transition from observation to forecast sh…
Indian Institute of Technology, Hyderabad（印度理工学院海得拉巴分校）
Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks. However, these perturbations are largely additive and not naturally found. We turn our attention to the field of Autonomous navigation wherein adverse weather conditions such as fog have a drastic effect on the predictions of these systems. These weather conditions are capable of acting like natural adversaries that can help in testing models. To this end, we introduce a general notion of adversarial perturbations, which can be created using generative models and provide a methodology inspi…
Most current computer vision datasets are composed of disconnected sets, such as images from different classes. We prove that distributions of this type of data cannot be represented with a continuous generative network without error. They can be represented in two ways: With an ensemble of networks or with a single network with truncated latent space. We show that ensembles are more desirable than truncated distributions in practice. We construct a regularized optimization problem that establishes the relationship between a single continuous GAN, an ensemble of GANs, conditional GANs, and Gau…
Machine Learning has been applied in a wide range of tasks throughout the last years, ranging from image classification to autonomous driving and natural language processing. Restricted Boltzmann Machine (RBM) has received recent attention and relies on an energy-based structure to model data probability distributions. Notwithstanding, such a technique is susceptible to adversarial manipulation, i.e., slightly or profoundly modified data. An alternative to overcome the adversarial problem lies in the Generative Adversarial Networks (GAN), capable of modeling data distributions and generating a…
Stockholm University（斯德哥尔摩大学）；Uppsala University（乌普萨拉大学）
Ensemble weather forecasts enable a measure of uncertainty to be attached to each forecast, by computing the ensemble's spread. However, generating an ensemble with a good spread-error relationship is far from trivial, and a wide range of approaches to achieve this have been explored -- chiefly in the context of numerical weather prediction models. Here, we aim to transform a deterministic neural network weather forecasting system into an ensemble forecasting system. We test four methods to generate the ensemble: random initial perturbations, retraining of the neural network, use of random dro…
Quantifying uncertainty in weather forecasts is critical, especially for predicting extreme weather events. This is typically accomplished with ensemble prediction systems, which consist of many perturbed numerical weather simulations, or trajectories, run in parallel. These systems are associated with a high computational cost and often involve statistical post-processing steps to inexpensively improve their raw prediction qualities. We propose a mixed model that uses only a subset of the original weather trajectories combined with a post-processing step using deep neural networks. These enab…
Post-processing ensemble prediction systems can improve the reliability of weather forecasting, especially for extreme event prediction. In recent years, different machine learning models have been developed to improve the quality of weather post-processing. However, these models require a comprehensive dataset of weather simulations to produce high-accuracy results, which comes at a high computational cost to generate. This paper introduces the ENS-10 dataset, consisting of ten ensemble members spanning 20 years (1998-2017). The ensemble members are generated by perturbing numerical weather s…
Huge Ensembles Part I: Design of Ensemble Weather Forecasts using Spherical Fourier Neural Operators
Lawrence Berkeley National Laboratory (LBNL)（劳伦斯伯克利国家实验室）；University of California, Berkeley（加州大学伯克利分校）；NVIDIA Corporation（英伟达公司）；Indiana University（印第安纳大学）；National Energy Research Scientific Computing Center (NERSC)（国家能源研究科学计算中心）；University of California, Irvine（加州大学欧文分校）
Cooperative Institute for Mesoscale Meteorological Studies（中尺度气象研究合作所）；NOAA/OAR/National Severe Storms Laboratory（美国国家海洋和大气管理局/海洋与大气研究/国家强风暴实验室）；School of Meteorology, University of Oklahoma（俄克拉荷马大学气象学院）；School of Computer Science, University of Oklahoma（俄克拉荷马大学计算机科学学院）
A primary goal of the National Oceanic and Atmospheric Administration (NOAA) Warn-on-Forecast (WoF) project is to provide rapidly updating probabilistic guidance to human forecasters for short-term (e.g., 0-3 h) severe weather forecasts. Maximizing the usefulness of probabilistic severe weather guidance from an ensemble of convection-allowing model forecasts requires calibration. In this study, we compare the skill of a simple method using updraft helicity against a series of machine learning (ML) algorithms for calibrating WoFS severe weather guidance. ML models are often used to calibrate se…
Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction
Microsoft Corporation（微软公司）；Department of Earth System Science, Ministry of Education Key Laboratory for Earth System Modeling, Institute for Global Change Studies（教育部地球系统科学部门地球系统建模重点实验室，全球变化研究机构）；Tsinghua University（清华大学）
Microsoft（微软）；Department of Atmospheric Sciences, University of Washington（华盛顿大学大气科学系）；Microsoft Research（微软研究院）
We present an ensemble prediction system using a Deep Learning Weather Prediction (DLWP) model that recursively predicts key atmospheric variables with six-hour time resolution. This model uses convolutional neural networks (CNNs) on a cubed sphere grid to produce global forecasts. The approach is computationally efficient, requiring just three minutes on a single GPU to produce a 320-member set of six-week forecasts at 1.4° resolution. Ensemble spread is primarily produced by randomizing the CNN training process to create a set of 32 DLWP models with slightly different learned weights. Althou…
On the Predictive Skill of Artificial Intelligence-based Weather Models for Extreme Events using Uncertainty Quantification
Applied Machine Learning Group（应用机器学习组）；Fraunhofer Heinrich-Hertz Institute（弗劳恩霍夫海因里希-赫兹研究所）；Signal Theory and Communications Dept.（信号理论与通信系）；Universidad Carlos III de Madrid (UC3M)（马德里卡洛斯三世大学）
FuXi-ENS: A machine learning model for medium-range ensemble weather forecasting
Artificial Intelligence Innovation and Incubation Institute, Fudan University（复旦大学人工智能创新与孵化研究院）；Shanghai Academy of Artificial Intelligence for Science（上海科学人工智能研究院）；National Meteorological Information Center, China Meteorological Administration（中国气象局国家气象信息中心）
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Heidelberg Institute for Theoretical Studies（海德堡理论研究所）
Postprocessing ensemble weather predictions to correct systematic errors has become a standard practice in research and operations. However, only few recent studies have focused on ensemble postprocessing of wind gust forecasts, despite its importance for severe weather warnings. Here, we provide a comprehensive review and systematic comparison of eight statistical and machine learning methods for probabilistic wind gust forecasting via ensemble postprocessing, that can be divided in three groups: State of the art postprocessing techniques from statistics (ensemble model output statistics (EMO…
Huge Ensembles Part II: Properties of a Huge Ensemble of Hindcasts Generated with Spherical Fourier Neural Operators
Lawrence Berkeley National Laboratory (LBNL)（劳伦斯伯克利国家实验室）；University of California, Berkeley（加州大学伯克利分校）；NVIDIA Corporation（英伟达公司）；National Energy Research Scientific Computing Center (NERSC)（国家能源研究科学计算中心）；Indiana University（印第安纳大学）；University of California, Irvine（加州大学欧文分校）
Results of direct numerical simulations have been used to show that intensive thermal convection in a horizontal layer and on a hemisphere can be described by the distributed chaos approach. The vorticity and helicity dominated distributed chaos were considered for this purpose. Results of numerical simulations of the Weather Research and Forecast Model (with the moist convection and with the Coriolis effect) and of the Coupled Ocean-Atmosphere Mesoscale Prediction System (COAMPS) were also analysed to demonstrate applicability of this approach to the atmospheric processes. The ensemble foreca…
Ludwig-Maximilians-Universität（路德维希-马克西米利安大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Heidelberg Institute for Theoretical Studies（海德堡理论研究所）
Ensemble weather predictions require statistical post-processing of systematic errors to obtain reliable and accurate probabilistic forecasts. Traditionally, this is accomplished with distributional regression models in which the parameters of a predictive distribution are estimated from a training period. We propose a flexible alternative based on neural networks that can incorporate nonlinear relationships between arbitrary predictor variables and forecast distribution parameters that are automatically learned in a data-driven way rather than requiring pre-specified link functions. In a case…
The space weather community has begun to use frontier methods such as data assimilation, machine learning, and ensemble modeling to advance current operational forecasting efforts. This was highlighted by a multi-disciplinary session at the 2017 American Geophysical Union Meeting, 'Frontier Solar-Terrestrial Science Enabled by the Combination of Data-Driven Techniques and Physics-Based Understanding', with considerable discussion surrounding ensemble techniques. Here ensemble methods are described in detail; using a set of predictions to improve on a single-model output, for example taking a s…
Modern weather forecast models perform uncertainty quantification using ensemble prediction systems, which collect nonparametric statistics based on multiple perturbed simulations. To provide accurate estimation, dozens of such computationally intensive simulations must be run. We show that deep neural networks can be used on a small set of numerical weather simulations to estimate the spread of a weather forecast, significantly reducing computational cost. To train the system, we both modify the 3D U-Net architecture and explore models that incorporate temporal data. Our models serve as a sta…
This chapter proposes and provides an in-depth discussion of a scalable solution for running ensemble simulation for solar energy production. Generating a forecast ensemble is computationally expensive. But with the help of Analog Ensemble, forecast ensembles can be generated with a single deterministic run of a weather forecast model. Weather ensembles are then used to simulate 11 10 KW photovoltaic solar power systems to study the simulation uncertainty under a wide range of panel configuration and weather conditions. This computational workflow has been deployed onto the NCAR supercomputer,…
Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior
Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；University of Amsterdam（阿姆斯特丹大学）；Delft University of Technology（代尔夫特理工大学）；Centrum Wiskunde & Informatica（数学与计算机科学中心）
Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions
Fraunhofer Heinrich-Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所（BIFOLD））
The spread of ensemble weather forecasts contains information about the spread of possible future weather scenarios. But how much information does it contain, and how useful is that information in predicting the probabilities of future temperatures? One traditional answer to this question is to calculate the spread-skill correlation. We discuss the spread-skill correlation and how it interacts with some simple calibration schemes. We then point out why it is not, in fact, a useful measure for the amount of information in the ensemble spread, and discuss a number of other measures that are more…
Historical observations of severe weather and simulated severe weather environments (i.e., features) from the Global Ensemble Forecast System v12 (GEFSv12) Reforecast Dataset (GEFS/R) are used in conjunction to train and test random forest (RF) machine learning (ML) models to probabilistically forecast severe weather out to days 4--8. RFs are trained with 9 years of the GEFS/R and severe weather reports to establish statistical relationships. Feature engineering is briefly explored to examine alternative methods for gathering features around observed events, including simplifying features usin…
Neural General Circulation Models for Weather and Climate
Google Research（谷歌研究院）；Massachusetts Institute of Technology（麻省理工学院）；European Centre for Medium-Range Weather Forecasts（欧洲中期天气预报中心）；Google DeepMind（谷歌DeepMind）；Harvard University（哈佛大学）
NVIDIA Corporation（英伟达公司）；University of Michigan（密歇根大学）；Rice University（莱斯大学）；California Institute of Technology（加州理工学院）；Purdue University（普渡大学）
FourCastNet, short for Fourier Forecasting Neural Network, is a global data-driven weather forecasting model that provides accurate short to medium-range global predictions at $0.25^{\circ}$ resolution. FourCastNet accurately forecasts high-resolution, fast-timescale variables such as the surface wind speed, precipitation, and atmospheric water vapor. It has important implications for planning wind energy resources, predicting extreme weather events such as tropical cyclones, extra-tropical cyclones, and atmospheric rivers. FourCastNet matches the forecasting accuracy of the ECMWF Integrated F…
Potential Paradigm Shift in Hazard Risk Management: AI-Based Weather Forecast for Tropical Cyclone Hazards
Tongji University（同济大学）；Princeton University（普林斯顿大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Wollongong（伍伦贡大学）；Nanjing University（南京大学）；Shanghai Jiao Tong University（上海交通大学）
