Other¶
-
High-resolution weather-guided surrogate modeling for data-efficient cross-location building energy prediction¶
Building design optimization often depends on physics-based simulation tools such as EnergyPlus, which, although accurate, are computationally expensive and slow. Surrogate models provide a faster...Building design optimization often depends on physics-based simulation tools such as EnergyPlus, which, although accurate, are computationally expensive and slow. Surrogate models provide a faster alternative, yet most are location-specific, and even weather-informed variants require simulations from many sites to generalize to unseen locations. This limitation arises because existing methods do not fully exploit the short-term weather-driven energy patterns shared across regions, restricting their scalability and reusability. This study introduces a high-resolution (weekly) weather-informed surrogate modeling approach that enhances model reusability across locations. By capturing recurring short-term weather-energy demand patterns common to multiple regions, the proposed method produces a generalized surrogate that performs well beyond the training location. Unlike previous weather-informed approaches, it does not require extensive simulations from multiple sites to achieve strong generalization. Experimental results show that when trained on a single location, the model maintains high predictive accuracy for other sites within the same climate zone, with no noticeable performance loss, and exhibits only minimal degradation when applied across different climate zones. These findings demonstrate the potential of climate-informed generalization for developing scalable and reusable surrogate models, supporting more sustainable and optimized building design practices. more
-
Data-Driven Integration Kernels for Interpretable Nonlocal Operator Learning¶
Machine learning models can represent climate processes that are nonlocal in horizontal space, height, and time, often by combining information across these dimensions in highly nonlinear ways. While...Machine learning models can represent climate processes that are nonlocal in horizontal space, height, and time, often by combining information across these dimensions in highly nonlinear ways. While this can improve predictive skill, it makes learned relationships difficult to interpret and prone to overfitting as the extent of nonlocal information grows. We address this challenge by introducing data-driven integration kernels, a framework that adds structure to nonlocal operator learning by explicitly separating nonlocal information aggregation from local nonlinear prediction. Each spatiotemporal predictor field is first integrated using learnable kernels (defined as continuous weighting functions over horizontal space, height, and/or time), after which a local nonlinear mapping is applied only to the resulting kernel-integrated features and optional local inputs. This design confines nonlinear interactions to a small set of integrated features and makes each kernel directly interpretable as a weighting pattern that reveals which horizontal locations, vertical levels, and past timesteps contribute most to the prediction. We demonstrate the framework for South Asian monsoon precipitation using a hierarchy of neural network models with increasing structure, including baseline, nonparametric kernel, and parametric kernel models. Across this hierarchy, kernel models achieve near-baseline performance with far fewer trainable parameters, indicating that much of the relevant nonlocal information can be captured through a small set of interpretable integrations when appropriate structural constraints are imposed. more
-
Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes¶
Accurately upscaling terrestrial carbon fluxes is central to estimating the global carbon budget, yet remains challenging due to the sparse and regionally biased distribution of ground measurements....Accurately upscaling terrestrial carbon fluxes is central to estimating the global carbon budget, yet remains challenging due to the sparse and regionally biased distribution of ground measurements. Existing data-driven upscaling products often fail to generalize beyond observed domains, leading to systematic regional biases and high predictive uncertainty. We introduce Task-Aware Modulation with Representation Learning (TAM-RL), a framework that couples spatio-temporal representation learning with knowledge-guided encoder-decoder architecture and loss function derived from the carbon balance equation. Across 150+ flux tower sites representing diverse biomes and climate regimes, TAM-RL improves predictive performance relative to existing state-of-the-art datasets, reducing RMSE by 8-9.6% and increasing explained variance (R2) from 19.4% to 43.8%, depending on the target flux. These results demonstrate that integrating physically grounded constraints with adaptive representation learning can substantially enhance the robustness and transferability of global carbon flux estimates. more
-
Idealized Impacts of Mountainous Terrain on the Energetics of Hurricane Melissa (2025)¶
This study examines the decay of Hurricane Melissa (2025) as the storm crossed the mountainous terrain of Jamaica, focusing on changes in inner-core energetics. Using NOAA P-3 reconnaissance...This study examines the decay of Hurricane Melissa (2025) as the storm crossed the mountainous terrain of Jamaica, focusing on changes in inner-core energetics. Using NOAA P-3 reconnaissance observations near the 700 hPa level, integrated kinetic energy within 100 km of the storm center was computed before and after land interaction to quantify vortex weakening. During the approximately four hour period in which the center remained over Jamaica, the storm experienced rapid degradation, including a 48 percent reduction in peak tangential wind, a 58 hPa rise in central pressure, and a 41 percent decrease in integrated kinetic energy. To investigate the mechanisms responsible for this decay, the observations were compared with results from an idealized axisymmetric tangential momentum diffusion model that isolates the effects of vertical turbulent mixing and enhanced surface drag. Despite its simplified physics, the model reproduces many leading order features of the observed weakening, including substantial reductions in tangential wind and a 36 percent decline in integrated kinetic energy. These results indicate that enhanced friction and turbulent mixing associated with extremely rough mountainous terrain can account for a large fraction of the rapid spin down observed during land interaction. Differences between the model and observations suggest that additional processes such as asymmetric dynamics, terrain induced flow distortion, and thermodynamic feedbacks further amplify the weakening of intense tropical cyclones over land. more
-
Data-driven, non-Markovian modelling of weather in the presence of non-stationary, non-Gaussian, and heteroskedastic climate dynamics¶
While the generalized Langevin equation (GLE) is a powerful tool to understand the behavior of complex dissipative systems, driving by external fields renders standard GLE construction workflows...While the generalized Langevin equation (GLE) is a powerful tool to understand the behavior of complex dissipative systems, driving by external fields renders standard GLE construction workflows invalid. Filtering approaches that separate fluctuations from the non-equilibrium response can sometimes circumvent the need for a non-equilibrium formalism when the residual fluctuations are homoskedastic, stationary, and preferably Gaussian. Here, we introduce the temperature time series from Boulder, Colorado, as representative of the more general and complex case where the filtered time series remains non-Gaussian, non-stationary, and heteroskedastic. With this example, we develop a protocol to build an accurate and efficient low-dimensional description of the weather fluctuations. Our protocol classifies the weather data based on the position in the annual cycle, and introduces local homoskedasticity as a metric to identify seasons of likely stationarity. Within these seasons, we build pseudo-equilibrium models. Leveraging state-based generalized master equation modelling as an alternative to the GLE, we resolve difficulties like non-Gaussianity and position dependence of the memory (friction) kernel. Our data-driven approach accurately reproduces the evolving fluctuations of the Boulder temperature time series, illustrating the feasibility of our method as a general tool to describe driven, dissipative systems. more
-
Deep Learning Based Monthly Temperature Prediction for Jilin Province: A Multi Model Comparative Study 2000 2026¶
Jilin Province, a core commercial grain production base in China with a mid-temperate continental monsoon climate and significant temperature fluctuations, relies heavily on temperature for...Jilin Province, a core commercial grain production base in China with a mid-temperate continental monsoon climate and significant temperature fluctuations, relies heavily on temperature for agricultural production and ecological security. Existing temperature prediction studies focus mostly on national/southeastern coastal regions, with few targeting Jilin's specific climatic characteristics, and most models fail to integrate local temperature's spatiotemporal differentiation and seasonal periodicity, limiting prediction accuracy. Using 1 km \(\times\) 1 km monthly mean temperature raster data (2000--2024) of Jilin Province, we analyzed regional temperature's spatiotemporal variation and constructed a multi-model comparison system including four deep learning models (LSTM, GRU, BiLSTM, Transformer) and five traditional machine learning models (Ridge/Lasso Regression, SVR, Random Forest, Gradient Boosting). Model performance was evaluated via RMSE, MAE, and \(R^2\). Results show Jilin's temperature has obvious latitudinal zonal distribution, significant warming trend, strong seasonal periodicity, and high temporal autocorrelation. The LSTM model achieved optimal performance (test set RMSE=2.26 \(^\circ\)C, MAE=1.83 \(^\circ\)C, \(R^2\)=0.9655), outperforming traditional models and Transformer. Predictions for 2025--2026 indicate stable seasonal temperature fluctuations with an annual mean of ~4.9 \(^\circ\)C. This study enriches mid-latitude cold region temperature prediction research, verifies LSTM's applicability for Jilin's monthly temperature prediction, and provides scientific support for agricultural planning, frost disaster warning, and extreme temperature risk prevention. more
-
Distillation and Interpretability of Ensemble Forecasts of ENSO Phase using Entropic Learning¶
This paper introduces a distillation framework for an ensemble of entropy-optimal Sparse Probabilistic Approximation (eSPA) models, trained exclusively on satellite-era observational and reanalysis...This paper introduces a distillation framework for an ensemble of entropy-optimal Sparse Probabilistic Approximation (eSPA) models, trained exclusively on satellite-era observational and reanalysis data to predict ENSO phase up to 24 months in advance. While eSPA ensembles yield state-of-the-art forecast skill, they are harder to interpret than individual eSPA models. We show how to compress the ensemble into a compact set of "distilled" models by aggregating the structure of only those ensemble members that make correct predictions. This process yields a single, diagnostically tractable model for each forecast lead time that preserves forecast performance while also enabling diagnostics that are impractical to implement on the full ensemble. An analysis of the regime persistence of the distilled model "superclusters", as well as cross-lead clustering consistency, shows that the discretised system accurately captures the spatiotemporal dynamics of ENSO. By considering the effective dimension of the feature importance vectors, the complexity of the input space required for correct ENSO phase prediction is shown to peak when forecasts must cross the boreal spring predictability barrier. Spatial importance maps derived from the feature importance vectors are introduced to identify where predictive information resides in each field and are shown to include known physical precursors at certain lead times. Case studies of key events are also presented, showing how fields reconstructed from distilled model centroids trace the evolution from extratropical and inter-basin precursors to the mature ENSO state. Overall, the distillation framework enables a rigorous investigation of long-range ENSO predictability that complements real-time data-driven operational forecasts. more
-
Winter forecasting of September/October rainfall¶
We formulate seasonal rainfall prediction as a reduced-order nonlinear forecasting problem, embedding coupled Indian-Pacific Ocean variability into a low-dimensional state space and projecting it...We formulate seasonal rainfall prediction as a reduced-order nonlinear forecasting problem, embedding coupled Indian-Pacific Ocean variability into a low-dimensional state space and projecting it forward using deep neural networks. Variables include Nino 3.4, the Indian Ocean Dipole (IOD), the Indian Ocean meridional SST gradient, and selected empirical orthogonal functions. Monthly time series of the variables then form the input into deep neural networks which project rainfall further into the future. Forecasts for the 2025 austral spring were generated and archived in the Mendeley database during the winter. Subsequent rainfall data demonstrated a high level of agreement with the forecasts, providing a validation of the method and supporting the hypothesis that chaotic yet conditionally predictable dynamics underpin spring rainfall variability in southeastern Australia. more
-
KAN-FIF: Spline-Parameterized Lightweight Physics-based Tropical Cyclone Estimation on Meteorological Satellite¶
Tropical cyclones (TC) are among the most destructive natural disasters, causing catastrophic damage to coastal regions through extreme winds, heavy rainfall, and storm surges. Timely monitoring of...Tropical cyclones (TC) are among the most destructive natural disasters, causing catastrophic damage to coastal regions through extreme winds, heavy rainfall, and storm surges. Timely monitoring of tropical cyclones is crucial for reducing loss of life and property, yet it is hindered by the computational inefficiency and high parameter counts of existing methods on resource-constrained edge devices. Current physics-guided models suffer from linear feature interactions that fail to capture high-order polynomial relationships between TC attributes, leading to inflated model sizes and hardware incompatibility. To overcome these challenges, this study introduces the Kolmogorov-Arnold Network-based Feature Interaction Framework (KAN-FIF), a lightweight multimodal architecture that integrates MLP and CNN layers with spline-parameterized KAN layers. For Maximum Sustained Wind (MSW) prediction, experiments demonstrate that the KAN-FIF framework achieves a \(94.8\%\) reduction in parameters (0.99MB vs 19MB) and \(68.7\%\) faster inference per sample (2.3ms vs 7.35ms) compared to baseline model Phy-CoCo, while maintaining superior accuracy with \(32.5\%\) lower MAE. The offline deployment experiment of the FY-4 series meteorological satellite processor on the Qingyun-1000 development board achieved a 14.41ms per-sample inference latency with the KAN-FIF framework, demonstrating promising feasibility for operational TC monitoring and extending deployability to edge-device AI applications. The code is released at https://github.com/Jinglin-Zhang/KAN-FIF. more
-
Urban Spatio-Temporal Foundation Models for Climate-Resilient Housing: Scaling Diffusion Transformers for Disaster Risk Prediction¶
Climate hazards increasingly disrupt urban transportation and emergency-response operations by damaging housing stock, degrading infrastructure, and reducing network accessibility. This paper...Climate hazards increasingly disrupt urban transportation and emergency-response operations by damaging housing stock, degrading infrastructure, and reducing network accessibility. This paper presents Skjold-DiT, a diffusion-transformer framework that integrates heterogeneous spatio-temporal urban data to forecast building-level climate-risk indicators while explicitly incorporating transportation-network structure and accessibility signals relevant to intelligent vehicles (e.g., emergency reachability and evacuation-route constraints). Concretely, Skjold-DiT enables hazard-conditioned routing constraints by producing calibrated, uncertainty-aware accessibility layers (reachability, travel-time inflation, and route redundancy) that can be consumed by intelligent-vehicle routing and emergency dispatch systems. Skjold-DiT combines: (1) Fjell-Prompt, a prompt-based conditioning interface designed to support cross-city transfer; (2) Norrland-Fusion, a cross-modal attention mechanism unifying hazard maps/imagery, building attributes, demographics, and transportation infrastructure into a shared latent representation; and (3) Valkyrie-Forecast, a counterfactual simulator for generating probabilistic risk trajectories under intervention prompts. We introduce the Baltic-Caspian Urban Resilience (BCUR) dataset with 847,392 building-level observations across six cities, including multi-hazard annotations (e.g., flood and heat indicators) and transportation accessibility features. Experiments evaluate prediction quality, cross-city generalization, calibration, and downstream transportation-relevant outcomes, including reachability and hazard-conditioned travel times under counterfactual interventions. more
-
MSWEP V3: Machine Learning-Powered Global Precipitation Estimates at 0.1\(^\circ\) Hourly Resolution (1979-Present)¶
We introduce Version 3 (V3) of the gridded near real-time Multi-Source Weighted-Ensemble Precipitation (MSWEP) product -- the first fully global, historical machine learning powered precipitation (P)...We introduce Version 3 (V3) of the gridded near real-time Multi-Source Weighted-Ensemble Precipitation (MSWEP) product -- the first fully global, historical machine learning powered precipitation (P) dataset, developed to meet the growing demand for timely and accurate P estimates amid escalating climate challenges. MSWEP V3 provides hourly data at 0.1\(^\circ\) resolution from 1979 to the present, continuously updated with a latency of approximately two hours. Development follows a two-stage process. First, baseline P fields are generated using machine learning model stacks that integrate satellite- and (re)analysis-based P and air-temperature products, along with static variables. The models are trained using hourly and daily observations from 15,959 P gauges worldwide. Second, these baseline P fields are corrected using daily and monthly gauge observations from 57,666 and 86,000 stations globally. To assess MSWEP V3's baseline performance, we evaluated 19 (quasi-) global gridded P products -- including both uncorrected and gauge-based products -- using observations from an independent set of 15,958 gauges excluded from the first training stage. The MSWEP V3 baseline achieved a median daily Kling-Gupta Efficiency (KGE) of 0.69, outperforming all evaluated products. Other uncorrected products achieved median daily KGE values of 0.61 (ERA5), 0.46 (IMERG-L V7), 0.38 (GSMaP V8), and 0.31 (CHIRP). Using leave-one-out cross-validation, the daily gauge correction was found to improve the median daily correlation by 0.09, constrained by the already strong baseline performance. We anticipate that MSWEP V3 -- accessible at www.gloh2o.org/mswep -- will enable more reliable monitoring, forecasting, and management of water-related risks in a variable and changing climate. more
-
WED-Net: A Weather-Effect Disentanglement Network with Causal Augmentation for Urban Flow Prediction¶
Urban spatio-temporal prediction under extreme conditions (e.g., heavy rain) is challenging due to event rarity and dynamics. Existing data-driven approaches that incorporate weather as auxiliary...Urban spatio-temporal prediction under extreme conditions (e.g., heavy rain) is challenging due to event rarity and dynamics. Existing data-driven approaches that incorporate weather as auxiliary input often rely on coarse-grained descriptors and lack dedicated mechanisms to capture fine-grained spatio-temporal effects. Although recent methods adopt causal techniques to improve out-of-distribution generalization, they typically overlook temporal dynamics or depend on fixed confounder stratification. To address these limitations, we propose WED-Net (Weather-Effect Disentanglement Network), a dual-branch Transformer architecture that separates intrinsic and weather-induced traffic patterns via self- and cross-attention, enhanced with memory banks and fused through adaptive gating. To further promote disentanglement, we introduce a discriminator that explicitly distinguishes weather conditions. Additionally, we design a causal data augmentation strategy that perturbs non-causal parts while preserving causal structures, enabling improved generalization under rare scenarios. Experiments on taxi-flow datasets from three cities demonstrate that WED-Net delivers robust performance under extreme weather conditions, highlighting its potential to support safer mobility, highlighting its potential to support safer mobility, disaster preparedness, and urban resilience in real-world settings. The code is publicly available at https://github.com/HQ-LV/WED-Net. more
-
AI Decodes Historical Chinese Archives to Reveal Lost Climate History¶
Historical archives contain qualitative descriptions of climate events, yet converting these into quantitative records has remained a fundamental challenge. Here we introduce a paradigm shift: a...Historical archives contain qualitative descriptions of climate events, yet converting these into quantitative records has remained a fundamental challenge. Here we introduce a paradigm shift: a generative AI framework that inverts the logic of historical chroniclers by inferring the quantitative climate patterns associated with documented events. Applied to historical Chinese archives, it produces the sub-annual precipitation reconstruction for southeastern China over the period 1368-1911 AD. Our reconstruction not only quantifies iconic extremes like the Ming Dynasty's Great Drought but also, crucially, maps the full spatial and seasonal structure of El Ni\(ñ\)o influence on precipitation in this region over five centuries, revealing dynamics inaccessible in shorter modern records. Our methodology and high-resolution climate dataset are directly applicable to climate science and have broader implications for the historical and social sciences. more
-
Conformal Prediction for Generative Models via Adaptive Cluster-Based Density Estimation¶
Conditional generative models map input variables to complex, high-dimensional distributions, enabling realistic sample generation in a diverse set of domains. A critical challenge with these models...Conditional generative models map input variables to complex, high-dimensional distributions, enabling realistic sample generation in a diverse set of domains. A critical challenge with these models is the absence of calibrated uncertainty, which undermines trust in individual outputs for high-stakes applications. To address this issue, we propose a systematic conformal prediction approach tailored to conditional generative models, leveraging density estimation on model-generated samples. We introduce a novel method called CP4Gen, which utilizes clustering-based density estimation to construct prediction sets that are less sensitive to outliers, more interpretable, and of lower structural complexity than existing methods. Extensive experiments on synthetic datasets and real-world applications, including climate emulation tasks, demonstrate that CP4Gen consistently achieves superior performance in terms of prediction set volume and structural simplicity. Our approach offers practitioners a powerful tool for uncertainty estimation associated with conditional generative models, particularly in scenarios demanding rigorous and interpretable prediction sets. more
-
Cross-Domain Offshore Wind Power Forecasting: Transfer Learning Through Meteorological Clusters¶
Ambitious decarbonisation targets are rapidly increasing the commission of new offshore wind farms. For these newly commissioned plants to run, accurate power forecasts are needed from the onset....Ambitious decarbonisation targets are rapidly increasing the commission of new offshore wind farms. For these newly commissioned plants to run, accurate power forecasts are needed from the onset. These allow grid stability, good reserve management and efficient energy trading. Despite machine learning models having strong performances, they tend to require large volumes of site-specific data that new farms do not yet have. To overcome this data scarcity, we propose a novel transfer learning framework that clusters power output according to covariate meteorological features. Rather than training a single, general-purpose model, we thus forecast with an ensemble of expert models, each trained on a cluster. As these pre-trained models each specialise in a distinct weather pattern, they adapt efficiently to new sites and capture transferable, climate-dependent dynamics. Our contributions are two-fold - we propose this novel framework and comprehensively evaluate it on eight offshore wind farms, achieving accurate cross-domain forecasting with under five months of site-specific data. Our experiments achieve a MAE of 3.52%, providing empirical verification that reliable forecasts do not require a full annual cycle. Beyond power forecasting, this climate-aware transfer learning method opens new opportunities for offshore wind applications such as early-stage wind resource assessment, where reducing data requirements can significantly accelerate project development whilst effectively mitigating its inherent risks. more
-
Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models¶
Large language models (LLMs) have progressed rapidly; however, most state-of-the-art models are trained and evaluated primarily in high-resource languages such as English and Chinese, and are often...Large language models (LLMs) have progressed rapidly; however, most state-of-the-art models are trained and evaluated primarily in high-resource languages such as English and Chinese, and are often developed by a small number of organizations with access to large-scale compute and data. This gatekeeping creates a practical barrier for sovereign settings in which a regional- or national-scale institution or domain owner must retain control and understanding of model weights, training data, and deployment while operating under limited resources and strict transparency constraints. To this end, we identify two core requirements: (1) adoptability, the ability to transform a base model into a general-purpose assistant, and (2) sovereign capability, the ability to perform high-stakes, region-specific tasks (e.g., legal reasoning in local languages and cultural knowledge). We investigate whether these requirements can be achieved without scaling massive instruction corpora or relying on complex preference tuning pipelines and large-scale reinforcement fine-tuning (RFT). We present Typhoon S, a minimal and open post-training recipe that combines supervised fine-tuning, on-policy distillation, and small-scale RFT. Using Thai as a representative case study, we demonstrate that our approach transforms both sovereign-adapted and general-purpose base models into instruction-tuned models with strong general performance. We further show that small-scale RFT with InK-GRPO -- an extension of GRPO that augments the GRPO loss with a next-word prediction loss -- improves Thai legal reasoning and Thai-specific knowledge while preserving general capabilities. Our results suggest that a carefully designed post-training strategy can reduce the required scale of instruction data and computation, providing a practical path toward high-quality sovereign LLMs under academic-scale resources. more
-
Weather Estimation for Integrated Sensing and Communication¶
One of the key features of sixth-generation (6G) mobile communications will be integrated sensing and communication (ISAC). While the main goal of ISAC in standardization efforts is to detect...One of the key features of sixth-generation (6G) mobile communications will be integrated sensing and communication (ISAC). While the main goal of ISAC in standardization efforts is to detect objects, the byproducts of radar operations can be used to enable new services in 6G, such as weather sensing. Even though weather radars are the most prominent technology for weather detection and monitoring, they are expensive and usually neglect areas in close vicinity. To this end, we propose reusing the dense deployment of 6G base stations for weather sensing purposes by detecting and estimating weather conditions. We implement both a classifier and a regressor as a convolutional neural network trained across measurements with varying precipitation rates and wind speeds. We implement our approach in an ISAC proof-of-concept and conduct a multi-week experiment campaign. Experimental results show that we are able to jointly and accurately classify weather conditions with accuracies of 99.38% and 98.99% for precipitation rate and wind speed, respectively. For estimation, we obtain mean absolute errors of 1.2 mm/h and 1.5 km/h, for precipitation rate and wind speed, respectively. These findings indicate that weather sensing services can be reliably deployed in 6G ISAC networks, broadening their service portfolio and boosting their market value. more
-
Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology¶
While Vision Language Models (VLMs) show advancing reasoning capabilities, their application in meteorology is constrained by a domain gap and a reasoning faithfulness gap. Specifically, mainstream...While Vision Language Models (VLMs) show advancing reasoning capabilities, their application in meteorology is constrained by a domain gap and a reasoning faithfulness gap. Specifically, mainstream Reinforcement Fine-Tuning (RFT) can induce Self-Contradictory Reasoning (Self-Contra), where the model's reasoning contradicts its final answer, which is unacceptable in such a high-stakes domain. To address these challenges, we construct WeatherQA, a novel multimodal reasoning benchmark in meteorology. We also propose Logically Consistent Reinforcement Fine-Tuning (LoCo-RFT), which resolves Self-Contra by introducing a logical consistency reward. Furthermore, we introduce Weather-R1, the first reasoning VLM with logical faithfulness in meteorology, to the best of our knowledge. Experiments demonstrate that Weather-R1 improves performance on WeatherQA by 9.8 percentage points over the baseline, outperforming Supervised Fine-Tuning and RFT, and even surpassing the original Qwen2.5-VL-32B. These results highlight the effectiveness of our LoCo-RFT and the superiority of Weather-R1. Our benchmark and code are available at https://github.com/Marcowky/Weather-R1. more
-
SolarGPT-QA: A Domain-Adaptive Large Language Model for Educational Question Answering in Space Weather and Heliophysics¶
Solar activity, including solar flares, coronal mass ejections (CMEs), and geomagnetic storms can significantly impact satellites, aviation, power grids, data centers, and space missions. Extreme...Solar activity, including solar flares, coronal mass ejections (CMEs), and geomagnetic storms can significantly impact satellites, aviation, power grids, data centers, and space missions. Extreme solar events can cause substantial economic damage with limited advance warning, underscoring the importance of early warning systems, accurate forecasting, and effective education in space science. Although large language models (LLMs) perform well on general tasks, they often lack domain specific knowledge and pedagogical capability to clearly explain complex space science concepts. We introduce SolarGPT-QA, a question answering system based on a domain adapted large language model built on the LLaMA-3 base model. The model is trained using scientific literature and large scale question and answer data generated with GPT-4 and refined using Grok-3 in a student friendly storytelling style. To evaluate response quality, we employ an LLM-as-judge evaluation framework, where a strong reference model assesses generated answers using structured criteria including scientific accuracy, clarity, completeness, and pedagogical effectiveness. Results show that SolarGPT-QA performs strongly relative to general purpose models in zero shot settings and achieves competitive performance compared to instruction tuned models for educational explanations in space weather and heliophysics. Ablation studies indicate that combining domain adaptive pretraining with fine tuning is important for balancing scientific accuracy and educational effectiveness. more
-
Learning a Stochastic Differential Equation Model of Tropical Cyclone Intensification from Reanalysis and Observational Data¶
Tropical cyclones are among the most consequential weather hazards, yet estimates of their risk are limited by the relatively short historical record. To extend these records, researchers often...Tropical cyclones are among the most consequential weather hazards, yet estimates of their risk are limited by the relatively short historical record. To extend these records, researchers often generate large ensembles of synthetic storms using simplified models of cyclone intensification. Developing such models, however, has traditionally required substantial theoretical effort. Here we explore whether equation-discovery methods, a class of data-driven techniques designed to infer governing equations, can accelerate the process of developing simplified intensification models. Using observational storm data (IBTrACS) together with environmental conditions from reanalysis (ERA5), we learn a compact stochastic differential equation describing tropical cyclone intensity evolution. We focus on TCs because their dynamics are well studied and a hierarchy of reduced-order models exist, enabling direct comparison of the learned model to physically-derived counterparts. We find that the learned model simulates synthetic TCs whose intensification statistics and hazard estimates are consistent with observations and competitive with a leading physics-based TC intensification model. Our model also reproduces known nonlinear dynamical behavior of tropical cyclones, including as a saddle node bifurcation as inner core ventilation is increased. This result shows that equation-discovery approaches, when applied directly to storm intensity, can recover not only realistic statistics but also physically meaningful dynamical structure. These findings highlight the potential for data-driven methods to complement existing theory and reduced-order models in the study of extreme weather. more
-
Weather-Aware Transformer for Real-Time Route Optimization in Drone-as-a-Service Operations¶
This paper presents a novel framework to accelerate route prediction in Drone-as-a-Service operations through weather-aware deep learning models. While classical path-planning algorithms, such as A...This paper presents a novel framework to accelerate route prediction in Drone-as-a-Service operations through weather-aware deep learning models. While classical path-planning algorithms, such as A and Dijkstra, provide optimal solutions, their computational complexity limits real-time applicability in dynamic environments. We address this limitation by training machine learning and deep learning models on synthetic datasets generated from classical algorithm simulations. Our approach incorporates transformer-based and attention-based architectures that utilize weather heuristics to predict optimal next-node selections while accounting for meteorological conditions affecting drone operations. The attention mechanisms dynamically weight environmental factors including wind patterns, wind bearing, and temperature to enhance routing decisions under adverse weather conditions. Experimental results demonstrate that our weather-aware models achieve significant computational speedup over traditional algorithms while maintaining route optimization performance, with transformer-based architectures showing superior adaptation to dynamic environmental constraints. The proposed framework enables real-time, weather-responsive route optimization for large-scale DaaS operations, representing a substantial advancement in the efficiency and safety of autonomous drone systems. more
-
Latent-Constrained Conditional VAEs for Augmenting Large-Scale Climate Ensembles¶
Large climate-model ensembles are computationally expensive; yet many downstream analyses would benefit from additional, statistically consistent realizations of spatiotemporal climate variables. We...Large climate-model ensembles are computationally expensive; yet many downstream analyses would benefit from additional, statistically consistent realizations of spatiotemporal climate variables. We study a generative modeling approach for producing new realizations from a limited set of available runs by transferring structure learned across an ensemble. Using monthly near-surface temperature time series from ten independent reanalysis realizations (ERA5), we find that a vanilla conditional variational autoencoder (CVAE) trained jointly across realizations yields a fragmented latent space that fails to generalize to unseen ensemble members. To address this, we introduce a latent-constrained CVAE (LC-CVAE) that enforces cross-realization homogeneity of latent embeddings at a small set of shared geographic 'anchor' locations. We then use multi-output Gaussian process regression in the latent space to predict latent coordinates at unsampled locations in a new realization, followed by decoding to generate full time series fields. Experiments and ablations demonstrate (i) instability when training on a single realization, (ii) diminishing returns after incorporating roughly five realizations, and (iii) a trade-off between spatial coverage and reconstruction quality that is closely linked to the average neighbor distance in latent space. more
-
Predictive Modeling of Power Outages during Extreme Events: Integrating Weather and Socio-Economic Factors¶
This paper presents a novel learning based framework for predicting power outages caused by extreme events. The proposed approach targets low-probability high-consequence outage scenarios and...This paper presents a novel learning based framework for predicting power outages caused by extreme events. The proposed approach targets low-probability high-consequence outage scenarios and leverages a comprehensive set of features derived from publicly available data sources. We integrate EAGLE-I outage records from 2014 to 2024 with weather, socioeconomic, infrastructure, and seasonal event data. Incorporating social and demographic indicators reveals patterns of community vulnerability and improves understanding of outage risk during extreme conditions. Four machine learning models are evaluated, including Random Forest (RF), Graph Neural Network (GNN), Adaptive Boosting (AdaBoost), and Long Short-Term Memory (LSTM). Experimental validation is performed on a large-scale dataset covering counties in the lower peninsula of Michigan. Among all models tested, the LSTM network achieves higher accuracy. more
-
Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation¶
Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap,...Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap, we present Omni-Weather, the first multimodal foundation model that unifies weather generation and understanding within a single architecture. Omni-Weather integrates a radar encoder for weather generation tasks, followed by unified processing using a shared self-attention mechanism. Moreover, we construct a Chain-of-Thought dataset for causal reasoning in weather generation, enabling interpretable outputs and improved perceptual quality. Extensive experiments show Omni-Weather achieves state-of-the-art performance in both weather generation and understanding. Our findings further indicate that generative and understanding tasks in the weather domain can mutually enhance each other. Omni-Weather also demonstrates the feasibility and value of unifying weather generation and understanding. more
-
Reconstructing Pre-Satellite Tropical Cyclogenesis Climatology Using Deep Learning¶
A reliable tropical cyclone (TC) climatology is the key to assessing historical and future changes in TC activities. While global TC records have been systematically maintained since the early 1940s,...A reliable tropical cyclone (TC) climatology is the key to assessing historical and future changes in TC activities. While global TC records have been systematically maintained since the early 1940s, substantial uncertainties remain for the pre-satellite era during which TC observations relied mostly on scattered aircraft reconnaissance and sporadic ship reports. This study presents a deep learning (DL) approach to reconstruct historical TC activity in the western North Pacific (WNP) basin, with a main focus on the pre-satellite era. Using data feature enrichment tailored for tropical cyclogenesis (TCG), we demonstrate that DL can effectively capture the main characteristics and changes in TCG climatology during the post-satellite era. With additional cross-validations, the reconstruction of TCG climatology is then extended to a pre-satellite period (1940-1960) during which TC base-track datasets are most uncertain. Our DL reconstruction reveals a significant missing of TCG in the current best-track data between September and November during the pre-satellite era. Such a TCG undercount in the best track data occurs mainly around 10-15\(^\circ\)N in the central WNP, while coastal regions show better consistency with DL reconstruction. These findings not only highlight the potential of DL for improving historical assessments of TC activity, but also advance our understanding of TCG processes by identifying key environmental conditions conducive to TC formation. The DL approach presented herein can be applied to other ocean basins, climate proxies, or reanalysis datasets for future TC climate studies. more
-
A Statistical Framework for Spatial Boundary Estimation and Change Detection: Application to the Sahel Sahara Climate Transition¶
Spatial boundaries, such as ecological transitions or climatic regime interfaces, capture steep environmental gradients, and shifts in their structure can signal emerging environmental changes....Spatial boundaries, such as ecological transitions or climatic regime interfaces, capture steep environmental gradients, and shifts in their structure can signal emerging environmental changes. Quantifying uncertainty in spatial boundary locations and formally testing for temporal shifts remains challenging, especially when boundaries are derived from noisy, gridded environmental data. We present a unified framework that combines heteroskedastic Gaussian process (GP) regression with a scaled Maximum Absolute Difference (MAD) Global Envelope Test (GET) to estimate spatial boundary curves and assess whether they evolve over time. The heteroskedastic GP provides a flexible probabilistic reconstruction of boundary lines, capturing spatially varying mean structure and location specific variability, while the test offers a rigorous hypothesis testing tool for detecting departures from expected boundary behaviors. Simulation studies show that the proposed method achieves the correct size under the null and high power for detecting local boundary shifts. Applying our framework to the Sahel Sahara transition zone, using annual Koppen Trewartha climate classifications from 1960 to 1989, we find no statistically significant decade scale changes in the arid and semi arid or semi arid and non arid interfaces. However, the method successfully identifies localized boundary shifts during the extreme drought years of 1983 and 1984, consistent with climate studies documenting regional anomalies in these interfaces during that period. more
-
Winter Precipitation Type Diagnosis and Uncertainty Quantification with a Physically Consistent Machine Learning Method¶
Correctly forecasting the timing and location of changes in winter precipitation type could help decision makers mitigate the worst impacts of winter storms. Multiple precipitation type algorithms...Correctly forecasting the timing and location of changes in winter precipitation type could help decision makers mitigate the worst impacts of winter storms. Multiple precipitation type algorithms have been developed from both physical and statistical perspectives, but all of them struggle in certain scenarios, and most of them do not account for uncertainty with a single model. We developed an evidential neural network that can predict both the probability of each winter precipitation type as well as the epistemic uncertainty. We trained our model on quality controlled and curated observations from the crowd-sourced mPING dataset in conjunction with vertical profiles from the NOAA Rapid Refresh model analyses. Our static and interactive evaluation revealed that the data curation procedure resulted in meteorologically consistent forecasts and appropriately represents uncertainty in difficult regimes where predictability may be limited by the atmospheric representations of current NWP models. We compare our model to both the Rapid Refresh NWP model in addition to other thermodynamic area-based methods from June of 2020 through June of 2022 and from a High Resolution Rapid Refresh central plains case study from December 24-26, 2023. more
-
ByteStorm: a multi-step data-driven approach for Tropical Cyclones detection and tracking¶
Accurate tropical cyclones (TCs) tracking represents a critical challenge in the context of weather and climate science. Traditional tracking schemes mainly rely on subjective thresholds, which may...Accurate tropical cyclones (TCs) tracking represents a critical challenge in the context of weather and climate science. Traditional tracking schemes mainly rely on subjective thresholds, which may introduce biases in their skills on the geographical region of application and are often computationally and data-intensive, due to the management of a large number of variables. We present ByteStorm, an efficient data-driven framework for reconstructing TC tracks. It leverages deep learning networks to detect TC centers (via classification and localization), using only relative vorticity (850 mb) and mean sea-level pressure. Then, detected centers are linked into TC tracks through the BYTE algorithm. ByteStorm is benchmarked with state-of-the-art deterministic trackers on the main global TC formation basins. The proposed framework achieves good tracking skills in terms of Probability of Detection and False Alarm Rate, accurately reproduces Seasonal and Inter-Annual Variability, and reconstructs reliable, smooth and coherent TC tracks. These results highlight the potential of integrating deep learning and computer vision to provide robust, computationally efficient and skillful data-driven alternatives to TC tracking. more
-
Extending Integrated Assessment Model scenarios until 2150 using an emulation Framework¶
Whereas there is growing interest in exploring longer-term climate with overshoot, including tipping elements, beyond 2100, most Integrated Assessment Models (IAMs) generate emissions scenarios only...Whereas there is growing interest in exploring longer-term climate with overshoot, including tipping elements, beyond 2100, most Integrated Assessment Models (IAMs) generate emissions scenarios only till 2100. Here we propose a framework to extend scenarios until 2150 using an emulator of IAMs. Our framework offers a potential interim solution for developing very long-term scenarios, such as the Scenario Model Intercomparison Project (ScenarioMIP), circumventing the challenges of fully simulating IAMs beyond 2100. more
-
Conditional updates of neural network weights for increased out of training performance¶
This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime...This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks. more