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

ALT Urban hydrodynamic flood models typically rely on a surveyed terrain model, an explicit pipe drainage network, and rain gauge measurements, none of which were available for the inundation following Typhoon Matmo in My Dinh and Tay Mo, Hanoi, on 7 October 2025. The present study addresses this issue by documenting the construction and calibration of a 32.8 km² 3Di subgrid model under severe data constraints, demonstrating how unmonitored catchments can be simulated using openly accessible sources. Specifically, a 1 m digital elevation model was systematically repaired for river and lake bathymetry, unsurveyed water bodies, road underpasses, and an excavation pit to re-establish essential overland flow paths. In addition, assigned infiltration rates across land-cover classes were utilized to stand in for the unrecorded subsurface sewer system, while half-hourly satellite precipitation from the IMERG Late product provided rainfall forcing for a closed two-dimensional domain. Model calibra

ALT Conventional deep convection schemes remain a primary source of uncertainty in global climate models, yet replacing them with data-driven alternatives while maintaining physical consistency and numerical stability is an open challenge. We present a hybrid configuration of the Community Atmosphere Model version 6 (CAM6), in which a fully connected deep neural network replaces the Zhang-McFarlane deep convection scheme (ZM), while radiation, turbulence, and other cloud processes are left unchanged. The network is trained on output from a storm-resolving global model - the global System for Atmospheric Modeling (gSAM) - using a coarse-graining approach to derive subgrid-scale convective fluxes and tendencies. This data-driven parameterization is ported to CAM6 and found to run stably for more than a decade while conserving energy and moisture. It produces a broadly realistic climatology without retuning the remaining parameterizations. Relative to the default Zhang-McFarlane scheme, the n

ALT High-resolution precipitation datasets are essential for weather forecasting, hydrological modeling, and climate risk assessment, yet observation-based gridded products often lack the spatial detail required for regional applications. Here we present PrecipCorrDiff, a diffusion-based downscaling framework built by modifying the original corrector diffusion based archetecture that incorporates a customized loss function and a multi-scale residual generation strategy to improve the precipitation especially the representation of extremes. PrecipCorrDiff generates 0.0625° resolution India Meteorological Department (IMD) precipitation fields from 0.25° gridded data while preserving precipitation statistics and reconstructing fine-scale spatial variability. Validation against independent IMD station observations, comparing the proposed framework with the SRGAN-based model and the original CorrDiff model, indicates that the proposed framework substantially improves the representation of spati

ALT Inferring climate fields at higher spatio-temporal resolutions from coarse representations is essential for accessing socioeconomic and environmental impacts. The downscaling of modelled climate fields faces a trade-off between data storage constraints, simulation efficiency, and resolution requirements. While many methods for spatial downscaling have been proposed, joint spatio-temporal downscaling has received comparable little attention. When deriving, for example, daily fields from climate datasets that are available only as monthly averages at coarser spatial resolution, it is highly challenging to faithfully reproduce extreme event statistics and spatiotemporal consistency. To address this task, we introduce a generative machine learning approach, using a diffusion model to jointly downscale monthly temperature and precipitation fields into temporally consistent daily fields at higher spatial resolution. We demonstrate that our approach can generate high-dimensional multivariate

ALT This work introduces a Process Additive Neural Network (PANN) framework to disentangle compensating biases in atmospheric models, where errors in different physical processes can offset each other and obscure their origins. Using a single-column model, each PANN branch represents the tendency error associated with a separate physical process, and the summed branch outputs approximate the total error relative to a reference tendency. Once trained successfully, the branch outputs are expected to provide process-level error attributions and, when averaged, estimates of process-level bias. Initial experiments focus on cloud-related processes in OpenIFS SCM case studies, where cloud and convection tendencies are strongly coupled and compensation is difficult to diagnose using standard approaches. The aim is not to replace human interpretation of physical processes, but to extend it to regimes where model complexity, process interaction, and compensating errors make direct diagnosis difficul

ALT Under anthropogenic greenhouse forcing, climate models project a decrease in year-to-year temperature variability in the mid-to-high latitudes and an increase in the tropics and subtropics. Here, we examine year-to-year temperature variability in the CESM Large Ensemble in concert with an idealized stochastic moist energy balance model (SMEBM) with effective surface heat capacity and local feedback parameter specified based on CESM. We find that the zonal-mean CESM variability change pattern largely persists after filtering out the impact of El Niño. The SMEBM largely captures this change pattern. In the SMEBM, changes in the mid-to-high latitudes are driven by changes in the effective heat capacity due to sea ice retreat, combined with changes in anomalous moist static energy convergence modulated by the polar-amplified time-mean temperature change. The CESM local feedback parameter evolves to be less stabilizing in the low latitudes, which causes tropical and subtropical variability

ALT We present the RemoTAP-Hybrid algorithm for global aerosol products retrieved from Multi-Angle Polarimeters (MAP), and apply it to one-year aerosol retrievals from the SPEXone MAP instrument. For the first time, Multiple Collaborated Neural Networks (MCNN) are used to perform global aerosol MAP retrievals over land and ocean. The combined use of MCNN with a full physics inversion in RemoTAP-Hybrid, significantly improves accuracy and computational speed of SPEXone aerosol retrievals. We validate the retrieved Aerosol Optical Depth (AOD), Angstrom Exponent (AE), Single Scattering Albedo (SSA), Absorption AOD (AAOD), Fine mode AOD (FAOD), Coarse mode AOD (CAOD), and fine mode effective radius (refffine) with AERONET data. The validation suggests that aerosol retrievals can be further improved when extending the aerosol description to include a fine non-spherical mode. For AOD, the Root-Mean-Square Error (RMSE) is 0.051 (0.037) over land (ocean), while 78.3% (80.8%) of the retrievals are

ALT Fronts, eddies, jets, and meanders populate the ocean surface and play a key role in organizing transport and mixing across a wide range of scales. From a Lagrangian perspective, frontal structures are conveniently detected as surface filaments that act as barriers to horizontal transport. However, the degree to which these structures maintain coherence below the surface and the relationship between horizontal and vertical motions in their vicinity remain poorly understood. Here we analyze two such filaments in the western Mediterranean Sea, south of the Ibiza Channel, using a high-resolution ocean simulation and Lagrangian diagnostics specifically designed to characterize submesoscale transport. Backward Finite-Size Lyapunov Exponents (FSLE) computed at successive depths reveal nearly vertical, curtain-like structures extending several tens of meters into the water column, with intensity decreasing with depth. Vertical-velocity sections across the filaments show coherent downward moti

ALT Rainfall forecasts over the Western Himalaya remain poor, and the relative contributions of the cumulus and microphysics parameterizations to that error are not well constrained.