ALT Antarctic ice shelves play a key role in controlling the mass loss of the Antarctic Ice Sheet. Increasing evidence from regional studies suggests the possibility of abrupt transitions from low to high basal melt regimes under future climate forcing. The computational cost and complexity of these realistic simulations yet limit their ability to systematically investigate the steady-state response of ice shelves to incremental forcing, the reversibility of abrupt transitions and the underlying positive feedback loops. Here, we report a detailed analysis of abrupt regime changes in an ice-shelf cavity with idealized geometry, subject to prescribed temperature and salinity stratifications in the far field and near-ice-front surface salt fluxes representing the impact of sea-ice production in coastal polynyas. We show that a cold regime emerges when the buoyancy loss in the polynya is sufficient to trigger deep convection, while a warm regime develops otherwise. The steady response of the s

ALT Porting a regional weather model in its entirety to a graphics processing unit (GPU) requires complete implementation of the dynamical core and all physical processes, and improved computational efficiency. This paper introduces WRF-JAX v1.1.28, a JAX reimplementation of the WRF 4.5 dynamical core and the complete CONUS physics suite. We conducted 27 ten-day integrations across nine regions and three initialization months, with a horizontal grid spacing of 3 km and 700×700 grid points, and established two numerical-difference baselines. The full-field RMSEs of wind, temperature, and moisture in WRF-JAX and the WRF internal numerical-difference baseline showed similar long-term evolution: the medians of the case-wise RMSE ratios were 1.05-1.07 at 24 h and 1.02-1.04 at 240 h. The mean sustained integration time on a single NVIDIA A800 was 175.0 s per model hour, corresponding to speedups of 1.17 and 1.05 relative to 128-process single-precision WRF runs compiled with gfortran and ifort,

ALT Computational Fluid Dynamics (CFD) is increasingly used to resolve wind, heat, and pollution patterns in cities with high fidelity but high computational cost. Thermal effects and vegetation are often neglected despite being important drivers, yet their influence may be masked by variability from other uncertain inputs. This work determines how precisely model parameters and boundary conditions must be known for these effects to govern output uncertainty in the velocity, temperature, and concentration fields of a two-dimensional street canyon. A global Sobol analysis of 24 parameters is made tractable by a surrogate trained on Reynolds-Averaged Navier–Stokes (RANS) simulations, combining principal component analysis (PCA) with multilayer perceptrons (MLPs). Two ventilation regimes assess the variance due to thermal and vegetation parameters as uncertainty in all other inputs is progressively reduced. At typical uncertainty levels, turbulence closure constants and inflow turbulence prof

ALT Air quality policy will cut aerosol and ozone precursor emissions, and studies disagree on how the tropical Pacific circulation and the El Nino Southern Oscillation (ENSO) will respond. Here we show, in 12 Earth system models with and without air quality controls, that the cuts strengthen the Pacific trade winds and offset half to two thirds of the weakening projected without them. The response is absent with prescribed sea surface temperatures and detectable only after 2040. It is consistent with the Indian Ocean warming relative to the Pacific, which also ranks the responses to cuts made region by region. ENSO amplitude changes by less than a tenth of its value, the smallest change this ensemble could detect. The change implied by the mean state shift is a sixth of that, and an ENSO model trained without the reduced emission runs predicts none. El Nino's regional impacts still change, because the background climate does.

ALT This paper describes an approach to constructing nowcast and forecast predictive models for the occurrence of high-latitude decameter ionospheric irregularities based on SuperDARN and SECIRA radar data and space weather parameters. The method relies on self-learning pattern recognition in the dynamics of space weather parameters, that influence the irregularities formation. The proposed approach is a data-driven, multiscale method in which the spatial distribution of irregularities is approximated using a neural network of an original architecture, inspired by graph neural networks. The model was trained and tested using data from 11 radars during the period 2010-2025 (SuperDARN: CVW, ICE, ICW, INV, PGR, PYK, RKN, SAS, STO; SECIRA: EKB, MAGW). It is shown that the model achieves optimal performance when using geomagnetic coordinates MLT,MLAT. The optimal set of parameters for the best nowcast and forecast over studied set of parameters is a combination of geomagnetic and solar disturba

ALT Land use regression models relate intra-urban air temperature to spatial predictors such as building volume, tree canopy cover and topography, and are increasingly used to produce fine-scale temperature maps. However, the accuracy of these estimates can be compromised by unrepresentative monitoring networks. Here we show that reference weather station networks, designed for regional rather than intra-urban monitoring, sample only a narrow portion of a city's spatial heterogeneity, missing both the densely built core and the cool, vegetated periphery that set the two ends of the urban temperature range. As a result, city-wide predictions underestimate temperature differences, in ways that cross-validation against the station measurements does not detect. Using Zurich, Switzerland, as a case study, we compare multiple linear regression, generalized additive models and random forests as up to 117 low-cost temperature sensors are added to the four reference weather stations. When trained o

ALT Short-range hindcasts of measured wave spectra are evaluated using a recurrent model initialized by one hourly buoy spectrum and supplied with local wind, fetch and depth. Measurements from three Baltic Sea stations are combined for training in 2017–2020, validation in 2021 and testing in 2022. ERA5 reanalysis supplies winds throughout the twelve-hour prediction interval. The comparison examines supervision of spectral variance, peak frequency and peak amplitude, followed by empirical wind-sea bounds and a local relaxation constraint. Variance and peak-frequency supervision gives the lowest spectral error within the data-driven comparison, whereas additional peak-amplitude supervision gives the lowest wave-height error. In the matched physical comparison, relaxation reduces height RMSE by 5.01\% to PhPtwoHs cm. Extending this constraint through hours 13–24, without spectral targets at those hours, reduces primary spectral RMSE by 2.31\% to PhPthreeSpec unitE. Upper-bound constraints in

ALT Satellite precipitation products face a persistent trade-off: real-time estimates are timely but less accurate, whereas the most reliable products are often released months after observation. This delay keeps high-quality precipitation information outside the decision window for flood warning and disaster response. Here we report Huayu-Global, a cross-constellation deep-learning system that combines three geostationary sensor streams from five satellites through a common retrieval framework and generates coherent quasi-global precipitation fields every thirty minutes. Across more than a million independent station records from two periods outside the training years, Huayu-Global improves event detection and precipitation-amount estimation relative to the real-time products evaluated and reaches delayed-product-level skill in key metrics. Huayu-Global therefore turns operational geostationary observations into a timely, high-skill precipitation layer for flood forecasting, water managem

ALT Artificial intelligence (AI) weather models now forecast weather events skillfully, but how they represent these events internally remains unknown. Sparse autoencoders (SAEs) provide sparse features for probing hidden states, but how information about multiple physical attributes of an event is organized across them remains unclear. Using tropical cyclones in GraphCast as a test case, we analyze 2,115 six-hourly timesteps from 205 cyclones, relating SAE activations to position, intensity, and pressure structure across five Layer-8 decompositions and 16 processor layers. Each attribute relates to multiple features; position and pressure-structure relations overlap in a smaller subset. This organization recurs across independent SAEs and layers without feature alignment. In deeper layers, the leading position feature aligns better with position and pressure structure six hours ahead than at present. These results suggest that the organization of physical-attribute relations provides a re

ALT Attribution of observed historical climate evolution to externally forced change and internal variability is fundamental to understanding climate change and evaluating climate models. Yet such attribution remains challenging because the forced response is intertwined with internal variability in observations. Here, we develop a convolutional long short-term memory network (ConvLSTM) to disentangle these two components. Trained and evaluated using large-ensemble simulations from multiple climate models, ConvLSTM consistently outperforms existing model-based, statistical, and machine-learning approaches. Applying ConvLSTM to observations reveals an evolving spatial pattern of the forced response and substantial contributions from internal variability to recent multidecadal climate trends. For several key climate features whose attribution remains debated, ConvLSTM indicates that internal variability amplified the forced reversal of Atlantic interhemispheric temperature asymmetry, dominat

ALT Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly due to imperfect land surface representations in Earth system models. We propose a data-driven framework for high-resolution land-use reconstruction, treated as a semantic-segmentation task, that combines coarse-resolution scenario data and climate classification with static geophysical features to produce annual land-use maps at 1 km resolution. We introduce TerraNostra-Bench, a change-aware evaluation protocol that separates spatial downscaling from autoregressive temporal rollout and scores models on the rare land-use-change pixels rather than the dominant static background. Using it, we compare convolutional (U-Net) and transformer (Swin) backbones in autoregressive and non-autoregressive schemes against persistence, linear, and shallow convolutional baselines. The autoregressive prior is the most informative input yet accumulates error over long rollouts: autoregressive models los

ALT Effectively preparing for changes in extreme flooding requires understanding present and future rainfall extremes with return periods up to ∼100-1000 years, including changes in intensity, spatial structure at km-scale and sub-daily temporal variability. Conventional km-scale climate models give greatly increased realism compared to typical global climate models (GCMs) but are too computationally costly to allow enough simulations for robustly quantifying changes in extremes. This work presents an approach based on video diffusion to generate realistic precipitation at 8.8km-hourly resolution by spatially and temporally downscaling daily, GCM-scale atmospheric variables. The emulator is trained to produce similar output to a 4×-coarsening of the Met Office's 2.2km-resolution UK convection-permitting model. An application for such an emulator is to downscale large-ensemble GCM simulations to allow quantification of ∼100-1000-year return level rainfall, which in turn can be used to drive

ALT Accurate real-time forecasting of atmospheric pollutants is essential for reducing exposure risks and improving public health. Traditional numerical forecasting systems suffer from incomplete parameterizations, uncertain inputs, and high computational cost. Existing deep learning approaches improve efficiency, but often entangle meteorological and pollutant variables within unified forecasting frameworks, limiting flexibility and pollutant-specific representation learning. To address these challenges, we propose AirMPA, a decoupled autoregressive framework for meteorology-to-pollution forecasting. AirMPA predicts 13 atmospheric pollutants at 0.4° spatial resolution and 12-h temporal resolution using meteorological fields, emission priors, and historical pollutant concentrations. The model is built on an improved Swin-Transformer architecture with zonal release attention and dual-branch fusion, enabling more effective modeling of global transport continuity and heterogeneous pollutant d

ALT Radiance-based retrievals and data assimilation require radiative transfer models (RTMs) to simulate radiances and quantify their sensitivities to atmospheric and surface conditions. Conventional RTMs often rely on separately maintained forward, tangent-linear, and adjoint codes, complicating model development and extension. Here, we present the Unified Differentiable and Learnable Radiative Transfer model (UDL-RT), a PyTorch-based framework for all-sky microwave radiative transfer that couples neural-network (NN) parameterizations of gaseous absorption, hydrometeor bulk scattering properties (BSPs), and ocean surface emissivity with an explicit radiative transfer solver in a unified differentiable computational graph. Automatic differentiation directly computes Jacobians with respect to input variables, reducing the model maintenance burden. The NN parameterizations offer flexible representations of complex nonlinear relationships. For example, the NN gas-absorption parameterization r

ALT AI weather prediction models are often regarded as black boxes. Despite their impressive skill, there is little understanding of how the input data is processed during inference to produce the forecast. This limitation arises from the use of high-dimensional latent representations in which individual dimensions are no longer directly interpretable in physical terms. To gain insight into how forecasts are constructed, we propose the method of intermediate decoding for AI weather models and apply it to GraphCast, Aurora and ArchesWeather. In this approach, latent states from intermediate depths are decoded back into meteorological fields. To do this, we use the decoder that has been trained to output the forecast at the end of processing. Since latent states at different depths do not share a consistent basis, we train affine transformations that align intermediate latent states with the decoder's expected input space. Applying this framework to the three models yields the following resu

ALT Earth system models underpin the evidence that informs net-zero policy, yet their energy demands are rarely considered when judging model quality. Using archived output from 159 models spanning five generations of the Coupled Model Intercomparison Project (CMIP), we show that model error has fallen at a constant rate of 13.5 per cent per doubling of compute since 1995. Halving CMIP6 error would require 28 times more compute. Improvements are uneven, with sea-level pressure and surface air temperature errors declining 3.5-fold and 2.7-fold since CMIP1, but precipitation error by only 7 per cent. Machine-learning weather models match or exceed operational forecast skill at a fraction of the runtime, but none publishes measured energy, and including training changes how they rank. We propose a skill-energy framework that combines an empirical Pareto front with a ranking score. These findings argue for standardised reporting of energy use and performance ahead of CMIP8.

ALT Seasonal prediction of Yangtze summer rainfall is challenged by nonstationary oceanic precursors. Here we demonstrate that accounting for the evolution of spring SST and state-dependent land surface information improves predictability. Graph total variation (GTV) is applied to March-May SST fields over the western Pacific, Niño3.4, and tropical Indian Ocean to identify spatially coherent, month-specific SST coefficients for each grid cell and month to form a scalar GTV index. The learned coefficient patterns capture April-to-May ENSO decay and an opposing Indian Ocean adjustment, consistent with coupled Indo-Pacific variability. During 2008-2022, the GTV index prediction outperforms Niño3.4-based and sparse-regression benchmarks. Further improvement is achieved by including interactions of May Indo-China Peninsula soil moisture with Indian Ocean SST, importantly also correcting several underestimated wet summers. Circulation diagnostics associate the learned index with a summer geopote

ALT Atmospheric composition and chemistry-climate interactions are central to predicting future climate change. Yet simulating chemical and aerosol processes is typically the most expensive component of an atmospheric model and is often highly simplified or prescribed entirely. AI weather forecasting foundation models have shown skill rivalling process-based models and are increasingly fine-tuned for new atmospheric tasks. Here, we present the first foundation model to capture interactions between emissions, atmospheric composition, and radiation. We fine-tune the Aurora Earth system foundation model on simulations from the chemistry-climate model UKCA. Our model reproduces daily meteorology, composition, aerosol, and radiation fields of the coupled system with 23 of 27 predicted fields achieving R² above 0.85 in both the troposphere and stratosphere. It reproduces ozone, CO, and temperature with annual mean biases below 4% and the downwelling shortwave and longwave fluxes to within 6%. Ou

ALT In the recent AI Model Intercomparison Project (AIMIP) benchmark, the ACE2.1-ERA5 emulator was shown to underestimate the true near-surface warming trend both during the training period and the out-of-sample extrapolation period. In this work, we present M-ACE2S (Masked-ACE2S), a modified version of the stochastic ACE2S model, which uses variable masking during training and reduces the reliance of M-ACE2S on any single input channel. We show that M-ACE2S improves long-term near-surface air temperature prediction. We also present a novel data normalization strategy called "global mean removal", which, combined with masking, further improves the near-surface temperature forecasts. We show that M-ACE2S outperforms the ACE2S baseline on in-sample data for ERA5 while improving training stability and generalizability of near-surface temperature to unseen forcing when paired with global mean removal.

ALT Utilities request mutual aid crews to restore power after severe storms, and requesting early secures more crews but relies on less accurate forecasts. We examined how forecast lead time affects the value of outage predictions for crew deployment, using operational forecasts from two AI weather models, GraphCast and FourCastNet, to predict outage occurrence for counties across the contiguous United States 24 to 120 hours ahead. Forecasts were evaluated by the share of outage burden captured by the counties where crews would be staged. Captured burden declined with lead time: the loss between three and five days was significant in all analyses, whereas the loss within three days was significant only for outages that had not yet started. Early deployment with all requested crews outperformed late deployment with fewer, and we report the availability ratio at which the two break even. Antecedent land surface predictors computed at forecast valid time include weather from the forecast peri