Climate Modeling¶
-
Disrespect Others, Respect the Climate? Applying Social Dynamics with Inequality to Forest Climate Models¶
Understanding the role of human behavior in shaping environmental outcomes is crucial for addressing global challenges such as climate change. Environmental systems are influenced not only by natural...Understanding the role of human behavior in shaping environmental outcomes is crucial for addressing global challenges such as climate change. Environmental systems are influenced not only by natural factors like temperature, but also by human decisions regarding mitigation efforts, which are often based on forecasts or predictions about future environmental conditions. Over time, different outcomes can emerge, including scenarios where the environment deteriorates despite efforts to mitigate, or where successful mitigation leads to environmental resilience. Additionally, fluctuations in the level of human participation in mitigation can occur, reflecting shifts in collective behavior. In this study, we consider a variety of human mitigation decisions, in addition to the feedback loop that is created by changes in human behavior because of environmental changes. While these outcomes are based on simplified models, they offer important insights into the dynamics of human decision-making and the factors that influence effective action in the context of environmental sustainability. This study aims to examine key social dynamics influencing society's response to a worsening climate. While others conclude that homophily prompts greater warming unconditionally, this model finds that homophily can prevent catastrophic effects given a poor initial environmental state. Assuming that poor countries have the resources to do so, a consensus in that class group to defect from the strategy of the rich group (who are generally incentivized to continue “business as usual”) can frequently prevent the vegetation proportion from converging to 0. more
-
ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matching¶
Internal variability is a dominant contributor to the uncertainty of predictions at the interannual to decadal timescale. A typical approach to separating the internal variability from forced climate...Internal variability is a dominant contributor to the uncertainty of predictions at the interannual to decadal timescale. A typical approach to separating the internal variability from forced climate responses is to generate large ensembles of simulations under different initial conditions. Due to the complexity of Earth System Models, generating these large ensembles is computationally expensive. In this work, we present ArchesClimate, a deep learning-based climate model emulator designed to reduce the cost of exploring internal variability at timescales ranging from monthly to decadal. ArchesClimate is trained on decadal hindcasts of the IPSL-CM6A-LR climate model. We train a flow matching model following ArchesWeatherGen, which we adapt to predict near-term climate. Once trained, the model generates states at a one-month lead time from the states of the two preceding months, and can be used to auto-regressively emulate climate model simulations. We show that for up to 10 years, these generations are stable and physically consistent. We also show that for several important climate variables, ArchesClimate generates simulations that are interchangeable with the IPSL model. This work suggests that climate model emulators could reduce the cost of generating large ensembles with climate models. more
-
An Attention-Based Stochastic Simulator for Multisite Extremes to Evaluate Nonstationary, Cascading Flood Risk¶
Flood risk is correlated in space and time, challenging insurance systems that rely on diversification across assets. Financial instruments governing flood coverage are typically structured as 1 to...Flood risk is correlated in space and time, challenging insurance systems that rely on diversification across assets. Financial instruments governing flood coverage are typically structured as 1 to 5-year contracts, exposing portfolios to climate-driven risk at interannual-to-decadal scales. Yet existing tools address climate risk either through seasonal forecasts extending only months or multidecadal projections misaligned with fiscal horizons, leaving a critical gap in actionable flood risk simulation. We introduce a multisite flood simulation framework combining attention-based analog retrieval with stochastic generation of multivariate flood frequency, intensity, and duration sequences. Applied to over 100 sites in the Mississippi River Basin, the model produces spatiotemporally coherent flood portfolios conditioned on interannual climate variability. Explainable AI attribution paired with wavelet analysis links simulated clustering to large-scale climate drivers, yielding physically interpretable flood clusters for portfolio-scale loss simulation. The framework provides plausible, out-of-sample flood risk catalogs for interannual-to-decadal insurance risk assessment and financial planning. more
-
Do machine learning climate models work in changing climate dynamics?¶
Climate change is accelerating the frequency and severity of unprecedented events, deviating from established patterns. Predicting these out-of-distribution (OOD) events is critical for assessing...Climate change is accelerating the frequency and severity of unprecedented events, deviating from established patterns. Predicting these out-of-distribution (OOD) events is critical for assessing risks and guiding climate adaptation. While machine learning (ML) models have shown promise in providing precise, high-speed climate predictions, their ability to generalize under distribution shifts remains a significant limitation that has been underexplored in climate contexts. This research systematically evaluates state-of-the-art ML-based climate models in diverse OOD scenarios by adapting established OOD evaluation methodologies to climate data. Experiments on large-scale datasets reveal notable performance variability across scenarios, shedding light on the strengths and limitations of current models. These findings underscore the importance of robust evaluation frameworks and provide actionable insights to guide the reliable application of ML for climate risk forecasting. more
-
DeepSeasons: a Deep Learning scale-selecting approach to Seasonal Forecasts¶
Seasonal forecasting remains challenging due to the inherent chaotic nature of atmospheric dynamics. This paper introduces DeepSeasons, a novel deep learning approach designed to enhance the accuracy...Seasonal forecasting remains challenging due to the inherent chaotic nature of atmospheric dynamics. This paper introduces DeepSeasons, a novel deep learning approach designed to enhance the accuracy and reliability of seasonal forecasts. Leveraging advanced neural network architectures and extensive historical climatic datasets, DeepSeasons identifies complex, nonlinear patterns and dependencies in climate variables with similar or improved skill respcet GCM-based forecasting methods, at a significant lower cost. The framework also allow tailored application to specific regions or variables, rather than the overall problem of predicting the entire atmosphere/ocean system. The proposed methods also allow for direct predictions of anomalies and time-means, opening a new approach to long-term forecasting and highlighting its potential for operational deployment in climate-sensitive sectors. This innovative methodology promises substantial improvements in managing climate-related risks and decision-making processes. more
-
A Deep Learning Model of Lightning Stroke Density¶
Lightning plays a crucial role in the Earth's climate system, yet existing parameterizations for use in forecasting and earth system models show room for improvement in capturing spatial and temporal...Lightning plays a crucial role in the Earth's climate system, yet existing parameterizations for use in forecasting and earth system models show room for improvement in capturing spatial and temporal variations in its frequency. This study develops deep learning-based parameterizations of lightning stroke density using meteorological variables from the ERA and IMERG datasets. Convolutional neural networks (CNNs) with U-Net architectures are trained using World Wide Lightning Location Network (WWLLN) data from 2010 to 2021 and evaluated on WWLLN lightning observations from 2022 and 2023. The CNNs reduce the average domain mean bias by an order of magnitude and produce significantly higher Fractions Skill Score (FSS) values across all lightning regimes compared to the multiplicative product of CAPE and precipitation. The CNNs show skill relative to previously published parameterizations over the oceans especially, with r2 values as high as 0.93 achieved between the best performing modeled and observed lightning stroke density climatologies. The CNNs are also able to accurately capture the 12-hourly evolution of lightning spatial patterns on an event-scale with high skill. These results show the potential for deep learning to improve on lightning parameterizations in weather and earth system models. more
-
Two Stage Context Learning with Large Language Models for Multimodal Stance Detection on Climate Change¶
With the rapid proliferation of information across digital platforms, stance detection has emerged as a pivotal challenge in social media analysis. While most of the existing approaches focus solely...With the rapid proliferation of information across digital platforms, stance detection has emerged as a pivotal challenge in social media analysis. While most of the existing approaches focus solely on textual data, real-world social media content increasingly combines text with visual elements creating a need for advanced multimodal methods. To address this gap, we propose a multimodal stance detection framework that integrates textual and visual information through a hierarchical fusion approach. Our method first employs a Large Language Model to retrieve stance-relevant summaries from source text, while a domain-aware image caption generator interprets visual content in the context of the target topic. These modalities are then jointly modeled along with the reply text, through a specialized transformer module that captures interactions between the texts and images. The proposed modality fusion framework integrates diverse modalities to facilitate robust stance classification. We evaluate our approach on the MultiClimate dataset, a benchmark for climate change-related stance detection containing aligned video frames and transcripts. We achieve accuracy of 76.2%, precision of 76.3%, recall of 76.2% and F1-score of 76.2%, respectively, outperforming existing state-of-the-art approaches. more
-
Finetuning AI Foundation Models to Develop Subgrid-Scale Parameterizations: A Case Study on Atmospheric Gravity Waves¶
Global climate models parameterize a range of atmospheric-oceanic processes like gravity waves, clouds, moist convection, and turbulence that cannot be sufficiently resolved. These subgrid-scale...Global climate models parameterize a range of atmospheric-oceanic processes like gravity waves, clouds, moist convection, and turbulence that cannot be sufficiently resolved. These subgrid-scale closures for unresolved processes are a leading source of model uncertainty. Here, we present a new approach to developing machine learning parameterizations of small-scale climate processes by fine-tuning a pre-trained AI foundation model (FM). FMs are largely unexplored in climate research. A pre-trained encoder-decoder from a 2.3 billion parameter FM (NASA and IBM Research's Prithvi WxC) -- which contains a latent probabilistic representation of atmospheric evolution -- is fine-tuned (or reused) to create a deep learning parameterization for atmospheric gravity waves (GWs). The parameterization captures GW effects for a coarse-resolution climate model by learning the fluxes from an atmospheric reanalysis with 10 times finer resolution. A comparison of monthly averages and instantaneous evolution with a machine learning model baseline (an Attention U-Net) reveals superior predictive performance of the FM parameterization throughout the atmosphere, even in regions excluded from pre-training. This performance boost is quantified using the Hellinger distance, which is 0.11 for the baseline and 0.06 for the fine-tuned model. Our findings emphasize the versatility and reusability of FMs, which could be used to accomplish a range of atmosphere- and climate-related applications, leading the way for the creation of observations-driven and physically accurate parameterizations for more earth-system processes. more
-
LUCIE-3D: A three-dimensional climate emulator for forced responses¶
We introduce LUCIE-3D, a lightweight three-dimensional climate emulator designed to capture the vertical structure of the atmosphere, respond to climate change forcings, and maintain computational...We introduce LUCIE-3D, a lightweight three-dimensional climate emulator designed to capture the vertical structure of the atmosphere, respond to climate change forcings, and maintain computational efficiency with long-term stability. Building on the original LUCIE-2D framework, LUCIE-3D employs a Spherical Fourier Neural Operator (SFNO) backbone and is trained on 30 years of ERA5 reanalysis data spanning eight vertical σ-levels. The model incorporates atmospheric CO2 as a forcing variable and optionally integrates prescribed sea surface temperature (SST) to simulate coupled ocean--atmosphere dynamics. Results demonstrate that LUCIE-3D successfully reproduces climatological means, variability, and long-term climate change signals, including surface warming and stratospheric cooling under increasing CO2 concentrations. The model further captures key dynamical processes such as equatorial Kelvin waves, the Madden--Julian Oscillation, and annular modes, while showing credible behavior in the statistics of extreme events. Despite requiring longer training than its 2D predecessor, LUCIE-3D remains efficient, training in under five hours on four GPUs. Its combination of stability, physical consistency, and accessibility makes it a valuable tool for rapid experimentation, ablation studies, and the exploration of coupled climate dynamics, with potential applications extending to paleoclimate research and future Earth system emulation. more
-
Community-Centered Spatial Intelligence for Climate Adaptation at Nova Scotia's Eastern Shore¶
This paper presents an overview of a human-centered initiative aimed at strengthening climate resilience along Nova Scotia's Eastern Shore. This region, a collection of rural villages with deep ties...This paper presents an overview of a human-centered initiative aimed at strengthening climate resilience along Nova Scotia's Eastern Shore. This region, a collection of rural villages with deep ties to the sea, faces existential threats from climate change that endanger its way of life. Our project moves beyond a purely technical response, weaving together expertise from Computer Science, Industrial Engineering, and Coastal Geography to co-create tools with the community. By integrating generational knowledge of residents, particularly elders, through the Eastern Shore Citizen Science Coastal Monitoring Network, this project aims to collaborate in building a living digital archive. This effort is hosted under Dalhousie University's Transforming Climate Action (TCA) initiative, specifically through its Transformative Adaptations to Social-Ecological Climate Change Trajectories (TranSECT) and TCA Artificial Intelligence (TCA-AI) projects. This work is driven by a collaboration model in which student teams work directly with residents. We present a detailed project timeline and a replicable model for how technology can support traditional communities, enabling them to navigate climate transformation more effectively. more
-
Advanced Torrential Loss Function for Precipitation Forecasting¶
Accurate precipitation forecasting is becoming increasingly important in the context of climate change. In response, machine learning-based approaches have recently gained attention as an emerging...Accurate precipitation forecasting is becoming increasingly important in the context of climate change. In response, machine learning-based approaches have recently gained attention as an emerging alternative to traditional methods such as numerical weather prediction and climate models. Nonetheless, many recent approaches still rely on off-the-shelf loss functions, and even the more advanced ones merely involve optimization processes based on the critical success index (CSI). The problem, however, is that CSI may become ineffective during extended dry periods when precipitation remains below the threshold, rendering it less than ideal as a criterion for optimization. To address this limitation, we introduce a simple penalty expression and reinterpret it as a quadratic unconstrained binary optimization (QUBO) formulation. Ultimately, the resulting QUBO formulation is relaxed into a differentiable advanced torrential (AT) loss function through an approximation process. The proposed AT loss demonstrates its superiority through the Lipschitz constant, forecast performance evaluations, consistency experiments, and ablation studies with the operational model. more
-
Imputing Missing Long-Term Spatiotemporal Multivariate Atmospheric Data with CNN-Transformer Machine Learning¶
Continuous physical domains are important for scientific investigations of dynamical processes in the atmosphere. However, missing data arising from operational constraints and adverse environmental...Continuous physical domains are important for scientific investigations of dynamical processes in the atmosphere. However, missing data arising from operational constraints and adverse environmental conditions pose significant challenges to accurate analysis and modeling. To address this limitation, we propose a novel hybrid Convolutional Neural Network (CNN) Transformer machine learning model for multivariable atmospheric data imputation, termed CT-MVP. This framework integrates CNNs for local feature extraction with transformers for capturing long-range dependencies across time and altitude. The model is trained and evaluated on a testbed using the Specified Dynamics Whole Atmosphere Community Climate Model with thermosphere and ionosphere extension (SD-WACCM-X) dataset spanning 13 years, which provides continuous global coverage of atmospheric variables, including temperature and zonal and meridional winds. This setup ensures that the ML approach can be rigorously assessed under diverse data-gap conditions. The hybrid framework enables effective reconstruction of missing values in high-dimensional atmospheric datasets, with comparative evaluations against traditional methods and a simple transformer. The results demonstrate that CT-MVP achieves superior performance compared with traditional approaches, particularly in cases involving extended periods of missing data, and slightly outperforms a simple transformer with the same hyper-parameters. more
-
Towards a Climate OSSE Framework for Satellite Mission Design¶
The rich history of observing system simulation experiments (OSSEs) does not yet include a well-established framework for using climate models. The need for a climate OSSE is triggered by the need to...The rich history of observing system simulation experiments (OSSEs) does not yet include a well-established framework for using climate models. The need for a climate OSSE is triggered by the need to quantify the value of a particular measurement for reducing the uncertainty in climate predictions, which differ from numerical weather predictions in that they depend on future atmospheric composition rather than the current state of the weather. However, both weather and climate modeling communities share a need for motivating major observing system investments. Here we outline a new framework for climate OSSEs that leverages the use of machine-learning to calibrate climate model physics against existing satellite data. We demonstrate its application using NASA's GISS-E3 model to objectively quantify the value of potential future improvements in spaceborne measurements of Earth's planetary boundary layer. A mature climate OSSE framework should be able to quantitatively compare the ability of proposed observing system architectures to answer a climate-related question, thus offering added value throughout the mission design process, which is subject to increasingly rapid advances in instrument and satellite technology. Technical considerations include selection of observational benchmarks and climate projection metrics, approaches to pinpoint the sources of model physics uncertainty that dominate uncertainty in projections, and the use of instrument simulators. Community and policy-making considerations include the potential to interface with an established culture of model intercomparison projects and a growing need to economically assess the value-driven efficiency of social spending on Earth observations. more
-
GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes¶
Accurately quantifying the increased risks of climate extremes requires generating large ensembles of climate realization across a wide range of emissions scenarios, which is computationally...Accurately quantifying the increased risks of climate extremes requires generating large ensembles of climate realization across a wide range of emissions scenarios, which is computationally challenging for conventional Earth System Models. We propose GEN2, a generative prediction-correction framework for an efficient and accurate forecast of the extreme event statistics. The prediction step is constructed as a conditional Gaussian emulator, followed by a non-Gaussian machine-learning (ML) correction step. The ML model is trained on pairs of the reference data and the emulated fields nudged towards the reference, to ensure the training is robust to chaos. We first validate the accuracy of our model on historical ERA5 data and then demonstrate the extrapolation capabilities on various future climate change scenarios. When trained on a single realization of one warming scenario, our model accurately predicts the statistics of extreme events in different scenarios, successfully extrapolating beyond the distribution of training data. more
-
FedRAIN-Lite: Federated Reinforcement Algorithms for Improving Idealised Numerical Weather and Climate Models¶
Sub-grid parameterisations in climate models are traditionally static and tuned offline, limiting adaptability to evolving states. This work introduces FedRAIN-Lite, a federated reinforcement...Sub-grid parameterisations in climate models are traditionally static and tuned offline, limiting adaptability to evolving states. This work introduces FedRAIN-Lite, a federated reinforcement learning (FedRL) framework that mirrors the spatial decomposition used in general circulation models (GCMs) by assigning agents to latitude bands, enabling local parameter learning with periodic global aggregation. Using a hierarchy of simplified energy-balance climate models, from a single-agent baseline (ebm-v1) to multi-agent ensemble (ebm-v2) and GCM-like (ebm-v3) setups, we benchmark three RL algorithms under different FedRL configurations. Results show that Deep Deterministic Policy Gradient (DDPG) consistently outperforms both static and single-agent baselines, with faster convergence and lower area-weighted RMSE in tropical and mid-latitude zones across both ebm-v2 and ebm-v3 setups. DDPG's ability to transfer across hyperparameters and low computational cost make it well-suited for geographically adaptive parameter learning. This capability offers a scalable pathway towards high-complexity GCMs and provides a prototype for physically aligned, online-learning climate models that can evolve with a changing climate. Code accessible at https://github.com/p3jitnath/climate-rl-fedrl. more
-
Data-driven global ocean model resolving ocean-atmosphere coupling dynamics¶
Artificial intelligence has advanced global weather forecasting, outperforming traditional numerical models in both accuracy and computational efficiency. Nevertheless, extending predictions beyond...Artificial intelligence has advanced global weather forecasting, outperforming traditional numerical models in both accuracy and computational efficiency. Nevertheless, extending predictions beyond subseasonal timescales requires the development of deep learning (DL)-based ocean-atmosphere coupled models that can realistically simulate complex oceanic responses to atmospheric forcing. This study presents KIST-Ocean, a DL-based global three-dimensional ocean general circulation model using a U-shaped visual attention adversarial network architecture. KIST-Ocean integrates partial convolution, adversarial training, and transfer learning to address coastal complexity and predictive distribution drift in auto-regressive models. Comprehensive evaluations confirmed the model's robust ocean predictive skill and efficiency. Moreover, it accurately captures realistic ocean response, such as Kelvin and Rossby wave propagation in the tropical Pacific, and vertical motions induced by cyclonic and anticyclonic wind stress, demonstrating its ability to represent key ocean-atmosphere coupling mechanisms underlying climate phenomena, including the El Nino-Southern Oscillation. These findings reinforce confidence in DL-based global weather and climate models and their extending DL-based approaches to broader Earth system modeling, offering potential for enhancing climate prediction capabilities. more
-
Setting the Standard: Recommended Practices for Data Preprocessing in Data-Driven Climate Prediction¶
Artificial intelligence (AI) - and specifically machine learning (ML) - applications for climate prediction across timescales are proliferating quickly. The emergence of these methods prompts a...Artificial intelligence (AI) - and specifically machine learning (ML) - applications for climate prediction across timescales are proliferating quickly. The emergence of these methods prompts a revisit to the impact of data preprocessing, a topic familiar to the climate community, as more traditional statistical models work with relatively small sample sizes. Indeed, the skill and confidence in the forecasts produced by data-driven models are directly influenced by the quality of the datasets and how they are treated during model development, thus yielding the colloquialism, "garbage in, garbage out." As such, this article establishes protocols for the proper preprocessing of input data for AI/ML models designed for climate prediction (i.e., subseasonal to decadal and longer). The three aims are to: (1) educate researchers, developers, and end users on the effects that preprocessing has on climate predictions; (2) provide recommended practices for data preprocessing for such applications; and (3) empower end users to decipher whether the models they are using are properly designed for their objectives. Specific topics covered in this article include the creation of (standardized) anomalies, dealing with non-stationarity and the spatiotemporally correlated nature of climate data, and handling of extreme values and variables with potentially complex distributions. Case studies will illustrate how using different preprocessing techniques can produce different predictions from the same model, which can create confusion and decrease confidence in the overall process. Ultimately, implementing the recommended practices set forth in this article will enhance the robustness and transparency of AI/ML in climate prediction studies. more
-
A Machine Learning Framework for Predicting Microphysical Properties of Ice Crystals from Cloud Particle Imagery¶
The microphysical properties of ice crystals are important because they significantly alter the radiative properties and spatiotemporal distributions of clouds, which in turn strongly affect Earth's...The microphysical properties of ice crystals are important because they significantly alter the radiative properties and spatiotemporal distributions of clouds, which in turn strongly affect Earth's climate. However, it is challenging to measure key properties of ice crystals, such as mass or morphological features. Here, we present a framework for predicting three-dimensional (3D) microphysical properties of ice crystals from in situ two-dimensional (2D) imagery. First, we computationally generate synthetic ice crystals using 3D modeling software along with geometric parameters estimated from the 2021 Ice Cryo-Encapsulation Balloon (ICEBall) field campaign. Then, we use synthetic crystals to train machine learning (ML) models to predict effective density (\(ρ_{e}\)), effective surface area (\(A_e\)), and number of bullets (\(N_b\)) from synthetic rosette imagery. When tested on unseen synthetic images, we find that our ML models can predict microphysical properties with high accuracy. For \(ρ_{e}\) and \(A_e\), respectively, our best-performing single view models achieved \(R^2\) values of 0.99 and 0.98. For \(N_b\), our best single view model achieved a balanced accuracy and F1 score of 0.91. We also quantify the marginal prediction improvements from incorporating a second view. A stereo view ResNet-18 model reduced RMSE by 40% for both \(ρ_e\) and \(A_e\), relative to a single view ResNet-18 model. For \(N_b\), we find that a stereo view ResNet-18 model improved the F1 score by 8%. This work provides a novel ML-driven framework for estimating ice microphysical properties from in situ imagery, which will allow for downstream constraints on microphysical parameterizations, such as the mass-size relationship. more
-
A Self-Evolving AI Agent System for Climate Science¶
Scientific progress in Earth science depends on integrating data across the planet's interconnected spheres. However, the accelerating volume and fragmentation of multi-sphere knowledge and data have...Scientific progress in Earth science depends on integrating data across the planet's interconnected spheres. However, the accelerating volume and fragmentation of multi-sphere knowledge and data have surpassed human analytical capacity. This creates a major bottleneck for discovery, especially in climate science. To address this challenge, we introduce EarthLink, the first self-evolving AI agent system designed as an interactive "copilot" for Earth scientists. Through natural language interaction, EarthLink automates the entire research workflow by integrating planning, code execution, data analysis, and physical reasoning into a unified process that directly addresses this limitation. Beyond efficiency, it exhibits human-like cross-disciplinary analytical ability and achieves proficiency comparable to a junior researcher in expert evaluations on core large-scale climate tasks, including model-observation comparison and climate change understanding. When tasked with an open scientific problem, specifically the discovery of precursors of the Atlantic Niño, EarthLink autonomously developed a research strategy, identified sources of predictability, verified its hypotheses with available data, and proposed a physically consistent mechanism. These emerging capabilities enable a new human-AI research paradigm. Scientists can focus on value and result judgments, while AI systems handle complex data analysis and knowledge integration. This accelerates the pace and breadth of discovery in Earth sciences. The system is accessible at our website https://earthlink.intern-ai.org.cn. more
-
Met\(^2\)Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems¶
The increasing frequency of extreme weather events due to global climate change urges accurate weather prediction. Recently, great advances have been made by the end-to-end methods, thanks to deep...The increasing frequency of extreme weather events due to global climate change urges accurate weather prediction. Recently, great advances have been made by the end-to-end methods, thanks to deep learning techniques, but they face limitations of representation inconsistency in multivariable integration and struggle to effectively capture the dependency between variables, which is required in complex weather systems. Treating different variables as distinct modalities and applying a two-stage training approach from multimodal models can partially alleviate this issue, but due to the inconformity in training tasks between the two stages, the results are often suboptimal. To address these challenges, we propose an implicit two-stage training method, configuring separate encoders and decoders for each variable. In detailed, in the first stage, the Translator is frozen while the Encoders and Decoders learn a shared latent space, in the second stage, the Encoders and Decoders are frozen, and the Translator captures inter-variable interactions for prediction. Besides, by introducing a self-attention mechanism for multivariable fusion in the latent space, the performance achieves further improvements. Empirically, extensive experiments show the state-of-the-art performance of our method. Specifically, it reduces the MSE for near-surface air temperature and relative humidity predictions by 28.82% and 23.39%, respectively. The source code is available at https://github.com/ShremG/Met2Net. more
-
Linear stability of an oceanic front at finite Rossby number¶
Submesoscale currents in the ocean's mixed layer (ML), consisting of fronts, eddies, and filaments, are characterized by order one Rossby (Ro) and Richardson (Ri) numbers. These currents play a...Submesoscale currents in the ocean's mixed layer (ML), consisting of fronts, eddies, and filaments, are characterized by order one Rossby (Ro) and Richardson (Ri) numbers. These currents play a crucial role in mediating vertical exchange between the surface and ocean interior and in facilitating cross-scale energy transfers. Despite a growing understanding of their generation mechanisms and energy pathways, two fundamental questions remain unresolved - how does a finite Ro modify the dynamics of ML instabilities, and what mechanisms are responsible for ML frontal arrest when Ro is order one. In this study, we address these questions through a linear stability analysis of a two-dimensional, geostrophically adjusted oceanic front based on the analytical model of Ou(1984), which allows systematic exploration across a range of Ro. In the low Ro, order one Ri regime, the most unstable mode is that of baroclinic instability, with the buoyancy flux serving as the primary source of perturbation kinetic energy. As Ro increases, the dominant instability becomes an inertia-critical layer type, characterized by a resonant interaction between a Rossby wave and an inertia-gravity wave. In the order one Ro regime, the shear production terms become comparable to the buoyancy flux term and even dominate in the region where the adjusted front is strongest. Our results suggest that shear production should be included in parameterizations of ML instabilities.minate in the region where the adjusted front is strongest. Our results suggest that shear production should be included in parameterizations of ML instabilities. more
-
Capturing Unseen Spatial Heat Extremes Through Dependence-Aware Generative Modeling¶
Observed records of climate extremes provide an incomplete view of risk, missing "unseen" events beyond historical experience. Ignoring spatial dependence further underestimates hazards striking...Observed records of climate extremes provide an incomplete view of risk, missing "unseen" events beyond historical experience. Ignoring spatial dependence further underestimates hazards striking multiple locations simultaneously. We introduce DeepX-GAN (Dependence-Enhanced Embedding for Physical eXtremes - Generative Adversarial Network), a deep generative model that explicitly captures the spatial structure of rare extremes. Its zero-shot generalizability enables simulation of statistically plausible extremes beyond the observed record, validated against long climate model large-ensemble simulations. We define two unseen types: direct-hit extremes that affect the target and near-miss extremes that narrowly miss. These unrealized events reveal hidden risks and can either prompt proactive adaptation or reinforce a sense of false resilience. Applying DeepX-GAN to the Middle East and North Africa shows that unseen heat extremes disproportionately threaten countries with high vulnerability and low socioeconomic readiness. Future warming is projected to expand and shift these extremes, creating persistent hotspots in Northwest Africa and the Arabian Peninsula, and new hotspots in Central Africa, necessitating spatially adaptive risk planning. more
-
Site-Specific Parameterization of Ocean Spectra for Power Estimates of Wave Energy Converters¶
Estimating the mean annual power of a wave energy converter (WEC) through the method of bins relies on a parametric representation of all possible sea states. In practice, two-parameter spectra based...Estimating the mean annual power of a wave energy converter (WEC) through the method of bins relies on a parametric representation of all possible sea states. In practice, two-parameter spectra based on significant wave height and energy period are ubiquitous. Two-parameter spectra have been shown insufficient in capturing the range of spectral shapes that can occur in an actual ocean environment. Furthermore, through sensitivity analysis, these two-parameters have been shown to be insufficient for predicting power performance of WECs. Four parameter spectra, which expand the parameter space to include two additional shape parameters have been shown sufficient in capturing sea state variance, but their effect on mean power estimates has not been presented. This work directly looks at the effects of incorporating 4-parameter spectra into annual power estimates compared to using the traditional 2-parameter spectra. We use two different 4-parameter spectra: one from the literature and a novel machine learning-based autoencoder, presented here. Both are shown to improve the information retained when parameterizing spectra. The site-specific autoencoder performs consistently the best across two case studies of mean annual power prediction, achieving an error around 1% in each instance. The 2-parameter spectra resulted in less consistent predictive performance, with errors of -8% and 1% in the two case studies. For the case study where all three models performed well, it is shown that the low error in the 2-parameter model is attributable to a symmetrical distribution of large errors whereas both 4-parameter spectra result in relatively low errors throughout the parametric space. These results highlight the need for more sophisticated resource characterization methods for estimating the power performance of WECs and suggest site-specific machine learning-based spectra are an adequate option. more
-
Deep Learning Atmospheric Models Reliably Simulate Out-of-Sample Land Heat and Cold Wave Frequencies¶
Deep learning (DL)-based general circulation models (GCMs) are emerging as fast simulators, yet their ability to replicate extreme events outside their training range remains unknown. Here, we...Deep learning (DL)-based general circulation models (GCMs) are emerging as fast simulators, yet their ability to replicate extreme events outside their training range remains unknown. Here, we evaluate two such models -- the hybrid Neural General Circulation Model (NGCM) and purely data-driven Deep Learning Earth System Model (DLESyM) -- against a conventional high-resolution land-atmosphere model (HiRAM) in simulating land heatwaves and coldwaves. All models are forced with observed sea surface temperatures and sea ice over 1900-2020, focusing on the out-of-sample early-20th-century period (1900-1960). Both DL models generalize successfully to unseen climate conditions, broadly reproducing the frequency and spatial patterns of heatwave and cold wave events during 1900-1960 with skill comparable to HiRAM. An exception is over portions of North Asia and North America, where all models perform poorly during 1940-1960. Due to excessive temperature autocorrelation, DLESyM tends to overestimate heatwave and cold wave frequencies, whereas the physics-DL hybrid NGCM exhibits persistence more similar to HiRAM. more
-
Probing forced responses and causality in data-driven climate emulators: conceptual limitations and the role of reduced-order models¶
A central challenge in climate science and applied mathematics is developing data-driven models of multiscale systems that capture both stationary statistics and responses to external perturbations....A central challenge in climate science and applied mathematics is developing data-driven models of multiscale systems that capture both stationary statistics and responses to external perturbations. Current neural climate emulators aim to resolve the atmosphere-ocean system in all its complexity but often struggle to reproduce forced responses, limiting their use in causal studies such as Green's function experiments. To explore the origin of these limitations, we first examine a simplified dynamical system that retains key features of climate variability. We interpret the results through linear response theory, providing a rigorous framework to evaluate neural models beyond stationary statistics and to probe causal mechanisms. We argue that the ability of emulators of multiscale systems to reproduce perturbed statistics depends critically on (i) the choice of an appropriate coarse-grained representation and (ii) careful parameterizations of unresolved processes. These insights highlight reduced-order models, tailored to specific goals, processes, and scales, as valuable alternatives to general-purpose emulators. We next consider a real-world application by developing a neural model to investigate the joint variability of the surface temperature field and radiative fluxes. The model infers a multiplicative noise process directly from data, largely reproduces the system's probability distribution, and enables causal studies through forced responses. We discuss its limitations and outline directions for future work. Overall, these results expose key challenges in data-driven modeling of multiscale physical systems and underscore the value of coarse-grained, stochastic approaches, with response theory providing a principled framework to guide model design and enhance causal understanding. more
-
Artificial Intelligence for Atmospheric Sciences: A Research Roadmap¶
Atmospheric sciences are crucial for understanding environmental phenomena ranging from air quality to extreme weather events, and climate change. Recent breakthroughs in sensing, communication,...Atmospheric sciences are crucial for understanding environmental phenomena ranging from air quality to extreme weather events, and climate change. Recent breakthroughs in sensing, communication, computing, and Artificial Intelligence (AI) have significantly advanced atmospheric sciences, enabling the generation of vast amounts of data through long-term Earth observations and providing powerful tools for analyzing atmospheric phenomena and predicting natural disasters. This paper contributes a critical interdisciplinary overview that bridges the fields of atmospheric science and computer science, highlighting the transformative potential of AI in atmospheric research. We identify key challenges associated with integrating AI into atmospheric research, including issues related to big data and infrastructure, and provide a detailed research roadmap that addresses both current and emerging challenges. more
-
Blended parameterization in an atmospheric model: Improving severestorm ensemble prediction by considering uncertainties in model physics¶
Physics parameterizations are often needed for numerical weather prediction (NWP) of precipitation forecast. This is mainly because the resolutions of most computational atmospheric models are not...Physics parameterizations are often needed for numerical weather prediction (NWP) of precipitation forecast. This is mainly because the resolutions of most computational atmospheric models are not fine enough to explicitly resolve sub-grid scale processes associated with precipitation systems. The various options in each physical parameterization scheme introduce model physics uncertainty, leading to variations in simulated precipitation due to differing representations of physical processes. We aim to quantify and reduce uncertainties in severe storm prediction arising from selecting physics parameterization schemes. In this study, we introduced a method called "blended parameterization" in an atmospheric model. This method parameterizes the selection of physical parameterization schemes using weighting parameters. This approach reduces the model selection problem to the optimization of these weighting parameters. The Markov Chain Monte Carlo (MCMC) method was used to estimate the posterior probability distribution of the weighting parameters. The large computational cost of MCMC was resolved by a surrogate model that efficiently mimics the relationship between weighting parameters and likelihood. Subsequently, the weighting parameters were sampled from the posterior distribution, followed by conducting an ensemble simulation to predict rainfall in Vietnam. Our optimized "blended parameterized" ensemble prediction system outperformed a conventional physical ensemble prediction system similar to that operationally used in Vietnam. more
-
AI-informed model-analogs for understanding subseasonal-to-seasonal jet stream and North American temperature predictability¶
Subseasonal-to-seasonal forecasting is crucial for public health, disaster preparedness, and agriculture, and yet it remains a particularly challenging timescale to predict. We explore the use of an...Subseasonal-to-seasonal forecasting is crucial for public health, disaster preparedness, and agriculture, and yet it remains a particularly challenging timescale to predict. We explore the use of an interpretable AI-informed model analog forecasting approach, previously employed on longer timescales, to improve S2S predictions. Using an artificial neural network, we learn a mask of weights to optimize analog selection and showcase its versatility across three varied prediction tasks: 1) classification of Week 3-4 Southern California summer temperatures; 2) regional regression of Month 1 midwestern U.S. summer temperatures; and 3) classification of Month 1-2 North Atlantic wintertime upper atmospheric winds. The AI-informed analogs outperform traditional analog forecasting approaches, as well as climatology and persistence baselines, for deterministic and probabilistic skill metrics on both climate model and reanalysis data. We find the analog ensembles built using the AI-informed approach also produce better predictions of temperature extremes and improve representation of forecast uncertainty. Finally, by using an interpretable-AI framework, we analyze the learned masks of weights to better understand S2S sources of predictability. more
-
ClimateChat: Designing Data and Methods for Instruction Tuning LLMs to Answer Climate Change Queries¶
As the issue of global climate change becomes increasingly severe, the demand for research in climate science continues to grow. Natural language processing technologies, represented by Large...As the issue of global climate change becomes increasingly severe, the demand for research in climate science continues to grow. Natural language processing technologies, represented by Large Language Models (LLMs), have been widely applied to climate change-specific research, providing essential information support for decision-makers and the public. Some studies have improved model performance on relevant tasks by constructing climate change-related instruction data and instruction-tuning LLMs. However, current research remains inadequate in efficiently producing large volumes of high-precision instruction data for climate change, which limits further development of climate change LLMs. This study introduces an automated method for constructing instruction data. The method generates instructions using facts and background knowledge from documents and enhances the diversity of the instruction data through web scraping and the collection of seed instructions. Using this method, we constructed a climate change instruction dataset, named ClimateChat-Corpus, which was used to fine-tune open-source LLMs, resulting in an LLM named ClimateChat. Evaluation results show that ClimateChat significantly improves performance on climate change question-and-answer tasks. Additionally, we evaluated the impact of different base models and instruction data on LLM performance and demonstrated its capability to adapt to a wide range of climate change scientific discovery tasks, emphasizing the importance of selecting an appropriate base model for instruction tuning. This research provides valuable references and empirical support for constructing climate change instruction data and training climate change-specific LLMs. more
-
AI reconstruction of European weather from the Euro-Atlantic regimes¶
We present a non-linear AI-model designed to reconstruct monthly mean anomalies of the European temperature and precipitation based on the Euro-Atlantic Weather regimes (WR) indices. WR represent...We present a non-linear AI-model designed to reconstruct monthly mean anomalies of the European temperature and precipitation based on the Euro-Atlantic Weather regimes (WR) indices. WR represent recurrent, quasi-stationary, and persistent states of the atmospheric circulation that exert considerable influence over the European weather, therefore offering an opportunity for sub-seasonal to seasonal forecasting. While much research has focused on studying the correlation and impacts of the WR on European weather, the estimation of ground-level climate variables, such as temperature and precipitation, from Euro-Atlantic WR remains largely unexplored and is currently limited to linear methods. The presented AI model can capture and introduce complex non-linearities in the relation between the WR indices, describing the state of the Euro-Atlantic atmospheric circulation and the corresponding surface temperature and precipitation anomalies in Europe. We discuss the AI-model performance in reconstructing the monthly mean two-meter temperature and total precipitation anomalies in the European winter and summer, also varying the number of WR used to describe the monthly atmospheric circulation. We assess the impact of errors on the WR indices in the reconstruction and show that a mean absolute relative error below 80% yields improved seasonal reconstruction compared to the ECMWF operational seasonal forecast system, SEAS5. As a demonstration of practical applicability, we evaluate the model using WR indices predicted by SEAS5, finding slightly better or comparable skill relative to the SEAS5 forecast itself. Our findings demonstrate that WR-based anomaly reconstruction, powered by AI tools, offers a promising pathway for sub-seasonal and seasonal forecasting. more