Generative artificial intelligence improves projections of climate extremes
Artificial Intelligence Innovation and Incubation Institute（人工智能创新与孵化院）；Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；Institute for Big Data（大数据研究院）；MOE Laboratory for National Development and Intelligent Governance（教育部国家发展与智能治理实验室）；Shanghai Academy of AI for Science（上海人工智能科学研究院）；FuXi Intelligent Computing Technology Co., Ltd.（复旦智能计算技术有限公司）
Ruian Tie, Xiaohui Zhong, Zhengyu Shi, Hao Li, Bin Chen, Jun Liu, Wu Libo
Climate change is amplifying extreme events, posing escalating risks to biodiversity, human health, and food security. GCMs are essential for projecting future climate, yet their coarse resolution and high computational costs constrain their ability to represent extremes. Here, we introduce FuXi-CMIPAlign, a generative deep learning framework for downscaling CMIP outputs. The model integrates Flow Matching for generative modeling with domain adaptation via MMD loss to align feature distributions between training data and inference data, thereby mitigating input discrepancies and improving accuracy, stability, and generalization across emission scenarios. FuXi-CMIPAlign performs spatial, temporal, and multivariate downscaling, enabling more realistic simulation of compound extremes such as TCs.
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Indian Institute of Tropical Meteorology, Ministry of Earth Sciences（印度热带气象研究所）；Krea University（克雷亚大学）；University of Petroleum and Energy Studies（石油与能源研究大学）；Queen Mary University of London（伦敦玛丽女王大学）
Climate change has become one of the biggest global problems increasingly compromising the Earth's habitability. Recent developments such as the extraordinary heat waves in California & Canada, and the devastating floods in Germany point to the role of climate change in the ever-increasing frequency of extreme weather. Numerical modelling of the weather and climate have seen tremendous improvements in the last five decades, yet stringent limitations remain to be overcome. Spatially and temporally localized forecasting is the need of the hour for effective adaptation measures towards minimizing…
The response of precipitation extremes to climate change is considered using results from theory, modeling, and observations, with a focus on the physical factors that control the response. Observations and simulations with climate models show that precipitation extremes intensify in response to a warming climate. However, the sensitivity of precipitation extremes to warming remains uncertain when convection is important, and it may be higher in the tropics than the extratropics. Several physical contributions govern the response of precipitation extremes. The thermodynamic contribution is rob…
The parameterization of moist convection contributes to uncertainty in climate modeling and numerical weather prediction. Machine learning (ML) can be used to learn new parameterizations directly from high-resolution model output, but it remains poorly understood how such parameterizations behave when fully coupled in a general circulation model (GCM) and whether they are useful for simulations of climate change or extreme events. Here, we focus on these issues using idealized tests in which an ML-based parameterization is trained on output from a conventional parameterization and its performa…
A climate state close to a tipping point will have a degenerate linear response to perturbations, which can be associated with extreme values of the equilibrium climate sensitivity (ECS). In this paper we contrast linearized (`instantaneous') with fully nonlinear geometric (`two-point') notions of ECS, in both presence and absence of tipping points. For a stochastic energy balance model of the global mean surface temperature with two stable regimes, we confirm that tipping events cause the appearance of extremes in both notions of ECS. Moreover, multiple regimes with different mean sensitiviti…
Understanding the dynamics of climate extreme is important in its prediction and modeling. In this study, linear trends in percentile, threshold, absolute, and duration based temperature and precipitation extremes indicator were obtained for the period 1979 - 2012 using the ETCCDI data set. The pattern of trend was compared with nonlinear measures (Entropy, Hurst Exponent, Recurrence Quantification Analysis) of temperature and precipitation. Regions which show positive trends in temperature based extremes were found to be areas with low entropy and chaotic. Complexity measures also revealed th…
One of the goals of climate science is to characterize the statistics of extreme and potentially dangerous events in the present and future climate. Extreme events like heat waves, droughts, or floods due to persisting rains are characterized by large anomalies of the time average of an observable over a long time. The framework of Donsker-Varadhan large deviation theory could therefore be useful for their analysis. In this paper we discuss how concepts and numerical algorithms developed in relation with large deviation theory can be applied to study extreme, rare fluctuations of time averages…
Climate projection uncertainty can be partitioned into model uncertainty, scenario uncertainty and internal variability. Here, we investigate the different sources of uncertainty in the projected frequencies of daily maximum temperature and precipitation extremes, which are defined as events that exceed the 99.97th percentile. This is done globally using initial-condition large ensembles. For maximum temperature extremes, internal variability dominates in the next two decades. Around the middle of the 21st century model and scenario uncertainty become the dominant contribution in the tropics b…
Helmholtz Centre Potsdam, German Research Centre for Geosciences GFZ（亥姆霍兹波茨坦中心，德国地球科学研究中心GFZ）；Free University of Berlin（柏林自由大学）；Potsdam Institute for Climate Impact Research（波茨坦气候影响研究所）；University of Exeter（埃克塞特大学）；Princeton University（普林斯顿大学）；NOAA/OAR Geophysical Fluid Dynamics Laboratory（美国国家海洋和大气管理局/海洋与大气研究办公室地球物理流体动力学实验室）；University of Washington（华盛顿大学）；Colorado State University（科罗拉多州立大学）；German Climate Computing Center DKRZ（德国气候计算中心DKRZ）；Helmholtz-Zentrum Geesthacht, Center for Material and Coastal Research HZG（亥姆霍兹盖斯特哈赫特中心，材料与海岸研究中心HZG）
We outline a perspective of an entirely new research branch in Earth and climate sciences, where deep neural networks and Earth system models are dismantled as individual methodological approaches and reassembled as learning, self-validating, and interpretable Earth system model-network hybrids. Following this path, we coin the term "Neural Earth System Modelling" (NESYM) and highlight the necessity of a transdisciplinary discussion platform, bringing together Earth and climate scientists, big data analysts, and AI experts. We examine the concurrent potential and pitfalls of Neural Earth Syste…
Tongji University（同济大学）；College of Civil Engineering, Tongji University（同济大学土木工程学院）
An extreme wind speed estimation method that considers wind hazard climate types is critical for design wind load calculation for building structures affected by mixed climates. However, it is very difficult to obtain wind hazard climate types from meteorological data records, because they restrict the application of extreme wind speed estimation in mixed climates. This paper first proposes a wind hazard type identification algorithm based on a numerical pattern recognition method that utilizes feature extraction and generalization. Next, it compares six commonly used machine learning models u…
Studying extreme events and how they evolve in a changing climate is one of the most important current scientific challenges. Starting from complex climate models, a key difficulty is to be able to run long enough simulations in order to observe those extremely rare events. In physics, chemistry, and biology, rare event algorithms have recently been developed to compute probabilities of events that cannot be observed in direct numerical simulations. Here we propose such an algorithm, specifically designed for extreme heat or cold waves, based on statistical physics approaches. This gives an im…
Rapid changes in climatic conditions threaten both socioeconomic and ecological systems, as these might not be able to adapt or to migrate at the same pace as that of global warming. In particular, an increase of weather and climate extremes can lead to increased stress on human and natural systems, and a tendency for serious adverse effects. We rely on the EURO-CORDEX simulations and focus on the the screen-level daily mean temperature (T2m). We compare the shifting velocities of the cold and hot extremes with these of the associated central trends, i.e., the arithmetical mean or median. We d…
Natural climate variability, captured through multiple initial condition ensembles, may be comparable to the variability caused by knowledge gaps in future emissions trajectories and in the physical science basis, especially at adaptation-relevant scales and projection horizons. The relations to chaos theory, including sensitivity to initial conditions, have caused the resulting variability in projections to be viewed as the irreducible uncertainty component of climate. The multiplier effect of ensembles from emissions-trajectories, multiple-models and initial-conditions contribute to the chal…
Artificial intelligence pathways from weather to climate
University of California, Los Angeles（加州大学洛杉矶分校）；Hong Kong University of Science and Technology（香港科技大学）；University of Lausanne（洛桑大学）；Allen Institute for AI（艾伦人工智能研究所）；University of Colorado Boulder（科罗拉多大学博尔德分校）；California Institute of Technology（加州理工学院）；NOAA/Geophysical Fluid Dynamics Laboratory（NOAA地球物理流体动力学实验室）；Google Research（谷歌研究院）；New York University（纽约大学）
"Climate dice", describing the chance of unusually warm or cool seasons relative to climatology, have become progressively "loaded" in the past 30 years, coincident with rapid global warming. The distribution of seasonal mean temperature anomalies has shifted toward higher temperatures and the range of anomalies has increased. An important change is the emergence of a category of summertime extremely hot outliers, more than three standard deviations (3σ) warmer than climatology. This hot extreme, which covered much less than 1% of Earth's surface in the period of climatology, now typically cov…
Precipitation extremes intensify in most regions in climate-model projections. Changes in vertical velocities contribute to the changes in intensity of precipitation extremes but remain poorly understood. Here, we find that mid-tropospheric vertical velocities in extratropical precipitation extremes strengthen overall in simulations of 21st-century climate change. For each extreme event, we solve the quasi-geostrophic omega equation to decompose this strengthening into different physical contributions. We first consider a dry decomposition in which latent heating is treated as an external forc…
Constructing Extreme Heatwave Storylines with Differentiable Climate Models
Centre Étude et simulation du climat à l’échelle régionale (ESCER), Département des Sciences de la Terre et de l’Atmosphère, Université du Québec à Montréal（区域气候研究与模拟中心（ESCER）、地球科学与大气科学系、魁北克蒙特利尔大学）
Harnessing AI data-driven global weather models for climate attribution: An analysis of the 2017 Oroville Dam extreme atmospheric river
Center for Western Weather and Water Extremes, Scripps Institution of Oceanography, University of California San Diego（加州大学圣迭戈分校斯克里普斯海洋研究所西部极端天气与极端水情中心）；Northern Illinois University（北伊利诺伊大学）；Halıcıoğlu Data Science Institute, University of California San Diego（加州大学圣迭戈分校哈利哲奥卢数据科学研究所）
Tackling extreme urban heat: a machine learning approach to assess the impacts of climate change and the efficacy of climate adaptation strategies in urban microclimates
The analysis of extremes in climate models is hindered by the lack of statistics due to the computational costs required to run simulations long enough to sample rare events. We demonstrate how rare event algorithms can improve the statistics of extreme events in state-of-the-art climate models. We study extreme warm summers and heatwaves over France and Scandinavia with CESM1.2.2 in present-day climate. The algorithm concentrates the simulations on events of importance, and shifts the probability distributions of regional temperatures such that warm summers become common. We estimate return t…
Investigating the Robustness of Extreme Precipitation Super-Resolution Across Climates
Expertise Center for Climate Extremes, University of Lausanne（极端气候专家中心，洛桑大学）；Faculty of Geosciences and Environment, University of Lausanne（地球科学与环境学院，洛桑大学）；Faculty of Business and Economics (HEC), University of Lausanne（商业经济学院（HEC），洛桑大学）
Univ Lyon, Ens de Lyon, Univ Claude Bernard, CNRS, Laboratoire de Physique（里昂大学、里昂高等师范学院、克洛德·贝尔纳大学、法国国家科学研究中心、物理实验室）；Royal Meteorological Institute（皇家气象研究所）
Because of the impact of extreme heat waves and heat domes on society and biodiversity, their study is a key challenge. We specifically study long-lasting extreme heat waves, which are among the most important for climate impacts. Physics driven weather forecast systems or climate models can be used to forecast their occurrence or predict their probability. The present work explores the use of deep learning architectures, trained using outputs of a climate model, as an alternative strategy to forecast the occurrence of extreme long-lasting heatwaves. This new approach will be useful for severa…
Planets that revolve around a binary pair of stars are known as circumbinary planets. The orbital motion of the stars around their center of mass causes a periodic variation in the total instellation incident upon a circumbinary planet. This study uses both an analytic and numerical energy balance model to calculate the extent to which this effect can drive changes in surface temperature on circumbinary terrestrial planets. We show that the amplitude of the temperature variation is largely constrained by the effective heat capacity, which corresponds to the ocean-to-land ratio on the planet. P…
Verisk Analytics（韦里斯克分析公司）；Otto-von-Guericke Universität（奥托·冯·格里克大学）；Massachusetts Institute of Technology（麻省理工学院）
Weather extremes are a major societal and economic hazard, claiming thousands of lives and causing billions of dollars in damage every year. Under climate change, their impact and intensity are expected to worsen significantly. Unfortunately, general circulation models (GCMs), which are currently the primary tool for climate projections, cannot characterize weather extremes accurately. To address this, we present a multi-resolution deep-learning framework that, firstly, corrects a GCM's biases by matching low-order and tail statistics of its output with observations at coarse scales; and secon…
Modeling the risk of extreme weather events in a changing climate is essential for developing effective adaptation and mitigation strategies. Although the available low-resolution climate models capture different scenarios, accurate risk assessment for mitigation and adaption often demands detail that they typically cannot resolve. Here, we develop a dynamic data-driven downscaling (super-resolution) method that incorporates physics and statistics in a generative framework to learn the fine-scale spatial details of rainfall. Our method transforms coarse-resolution ($0.25^{\circ} \times 0.25^{\…
The East Asian summer monsoon (EASM) is important for bringing rainfall to large areas of China. Historically, variations in the EASM have had major impacts including flooding and drought. We present an analysis of the impact of anthropogenic climate change on EASM rainfall in Eastern China using a newly updated attribution system. Our results suggest that anthropogenic climate change has led to an overall decrease in total monsoon rainfall over the past 65 years, and an increased number of dry days. However the model also predicts that anthropogenic forcings have caused the most extreme heavy…
The frequency and magnitude of weather extreme events have increased significantly during the past few years in response to anthropogenic climate change. However, global statistical characteristics and underlying physical mechanisms are still not fully understood. Here, we adopt a statistical physics and probability theory based method to investigate the nature of extreme weather events, particularly the statistics of the day-to-day air temperature differences. These statistical measurements reveal that the distributions of the magnitudes of the extreme events satisfy a universal \textit{Gumbe…
Water vapor is not only Earth's dominant greenhouse gas. Through the release of latent heat when it condenses, it also plays an active role in dynamic processes that shape the global circulation of the atmosphere and thus climate. Here we present an overview of how latent heat release affects atmosphere dynamics in a broad range of climates, ranging from extremely cold to extremely warm. Contrary to widely held beliefs, atmospheric circulation statistics can change non-monotonically with global-mean surface temperature, in part because of dynamic effects of water vapor. For example, the streng…
If climate stationarity is dead, how should engineering design standards be modified to account for potential changes in extreme precipitation? Many standards rely on precipitation intensity-duration-frequency (IDF) curves provided in NOAA's Atlas 14. General Circulation Models (GCMs) predict increases in average temperature throughout the US, but are less clear on changes in precipitation. In many areas GCMs predict relatively small changes in total precipitation volume, but also suggest increased magnitude of extreme events as warmer air can hold more water. Unfortunately, GCMs have limited …
Over recent decades, the Arctic Ocean has experienced dramatic changes due to climate change. Retreating sea ice has opened up large areas of ocean, resulting in an enhanced wave climate. Taking into account the intense seasonality and the rapid changes to the Arctic climate, a non-stationary approach is applied to time-varying statistical properties to investigate historical trends of extreme values. The analysis is based on a 28-year wave hindcast (from 1991 to 2018) carried out with the WAVEWATCH III wave model forced by ERA5 wind speed. The results show notable seasonal differences and rob…
