8,557 papers in this slice of arXiv.
Adam Subel, Laure Zanna
AI weather emulators benefit from clear objectives and metrics, which have led to the rapid development of models that outperform traditional benchmarks. In contrast, long-term climate emulators must reliably reproduce forced responses over months to centuries, while relying on training objectives that span a small number of model time steps. We assess autoregressive, full-depth ocean emulators using data from the midHolocene experiment of a numerical climate model to examine their skill in responding to surface forcings from an in-distribution, out-of-sample climate. We demonstrate that these emulators generalize to new orbital forcings, reproducing the spatial structure of the large-scale response as well as changes in seasonal patterns and in the spatial structure of ocean variability, while underestimating their amplitude. Baselines that infer the ocean state directly from the boundary forcings also recover much of the large-scale pattern, but only near the surface, and capture neither the seasonal nor the variability changes, indicating that these require some representation of dynamics. Despite these successes, the emulators fail to reproduce the slow, internally driven evolution of the ocean interior. We then show that the emulators' total forced response is well reconstructed by linearly composing their independent responses to each forcing component. Tracking response across training epochs, we find that convergence on mean state metrics in the training climate does not guarantee that the emulators capture the dynamics necessary for a skillful response. Together, these experiments establish the midHolocene as a controlled, ground-truthed setting for diagnosing forced-response failures before emulators are pushed to out-of-distribution climates.
Gergana Gyuleva, Reto Knutti, Robin Noyelle +3
Earth's feedback parameter measures how the Earth system responds to forcing and is inversely proportional to climate sensitivity. Sea-surface temperature (SST) patterns can modulate the value of the feedback parameter. Differences between observed and simulated SSTs have raised the question how the observed SSTs evolution impacts the global feedback. The standard method for estimating this effect uses observed SSTs prescribed to an atmospheric model with fixed pre-industrial atmospheric forcing. This method makes two assumptions: first, that the observed SSTs capture all relevant effects from the forcing, so that prescribing a time-varying forcing is unnecessary; second, that the temporal variations in the feedback parameter are driven by the evolving SST pattern and can be estimated via moving-window regressions. We test these assumptions by running controlled experiments in which SSTs from fully-coupled historical simulations are prescribed to an atmospheric model. We find that the prescribed-SST experiments fail to capture the coupled feedback evolution. This is explained by two effects: First, the absence of prescribed atmospheric forcing, and second, statistical noise arising from the computation of moving-window regressions. We find no evidence of any significant relationship between evolving SST patterns and changes in the feedback time series in a 4000-year pre-industrial control simulation. Any trends in the feedback parameter detected on timescales shorter than ~100 years are indistinguishable from statistical noise, making their attribution to the evolving SST pattern extremely difficult. Our results imply that prescribed SST simulations offer limited potential for inferring temporal changes in Earth's parameter over the observational period.
Yi Xu
Satellite precipitation products such as IMERG exhibit biases that vary with terrain, season, and precipitation regime, leaving the applicability boundaries of machine learning correction unclear. This study proposes the Terrain-Moisture-Intensity (TMI) framework, centered on mechanism purity, extending the correction problem from purely algorithmic optimization to physical consistency diagnosis. A proof-of-concept study in Hunan Province employs IMERG V07, SRTM DEM, and ERA5 variables (tcwv, u10, v10). Ablation results indicate that, under the conditions of this study, terrain-moisture relationships are predominantly additive: RF-Full yields merely +0.001 R^2 gain over LR-Full, while bias rises to 1.282 mm d^-1; MAE decreases by approximately 14%, reflecting a trade-off between tail-fitting improvement and mean shift. SHAP diagnostics identify three categories of boundaries. Spatially, Central Hunan exhibits significant degradation (R^2=0.133) despite strong variable activation, consistent with mechanism fragmentation induced by mixed terrain. Temporally, u10 undergoes directional reversal between summer and spring (+0.096 to -0.156), presenting "silent failure." Extreme precipitation (>=50 mm d^-1) approximates a mechanism saturation frontier rather than isolated out-of-distribution samples, with DEM showing the largest relative amplification in SHAP disorder (+150%). The results demonstrate that machine learning correction performance is primarily constrained by mechanism purity. A pre-registered cross-regional test (Hunan, Guangxi, Guangdong) confirms this screening capability out of sample: a priori coherence proxies predict correction efficiency with a mean absolute error of 2.6 percentage points, while the transfer-versus-retraining contrast separates mechanism mismatch (coastal Guangdong) from portability (Guangxi), establishing the framework as a validated applicability screen.
Thomas M Hamill
An ``Attention Residual U-Net'' method is described for probabilistic quantitative precipitation forecasting (PQPF) that predicts the hourly probability of no precipitation plus the distribution of positive precipitation from a weighted mixture of two Gamma distributions. The neural network is trained on patches of numerical weather prediction (NWP) hourly precipitation from The Weather Company's convection-permitting GRAF (Global high-Resolution Atmospheric Forecasting) model along with terrain information and column-average relative humidity from the National Oceanic and Atmospheric Administration's (NOAA's) Global Forecast System (GFS). The target data are NOAA's Multi-Radar, Multi-Sensor (MRMS) gauge-corrected, quality controlled radar data sampled to the same grid as the GRAF data. The network outputs distributional parameters for each model grid point. Training uses negative log-likelihood as a proper scoring rule, with climatological initialization for stable convergence. Inference is performed as a single forward pass over the contiguous United States (CONUS) domain, with edge-replication padding to satisfy the network's spatial-divisibility requirement. The subsequent forecasts are spatially detailed, highly reliable, and skillful with respect to climatology and a simpler reference forecast method. The method is particularly useful for estimating probabilities in regions with large terrain variation.
Wuqiushi Yao, Or Hadas, Yohai Kaspi
The Hadley circulation is Earth's dominant tropical overturning circulation, regulating atmospheric energy transport, tropical rainfall, and subtropical aridity. Although its variability has been extensively studied on seasonal to decadal climate-change timescales, its subseasonal behaviour remains poorly understood. Here we show that the Madden-Julian Oscillation (MJO), the leading mode of tropical intraseasonal variability, systematically modulates the Hadley circulation and influences global hydroclimate variability. Using reanalysis data and dynamical diagnostics, we identify a robust hemispherically asymmetric Hadley circulation anomaly associated with active MJO events, with amplitudes comparable to the climatological intraseasonal variability of the Hadley circulation. Breaking down the dynamical components reveals that the response is primarily maintained by latent heating associated with moist convection, while the overturning strength is driven by interhemispheric moisture gradients. Lead-lag analyses further show that the Hadley circulation lags the MJO by 4-15 days, indicating that MJO convection may drive overturning adjustments on subseasonal timescales. This coupled MJO-Hadley circulation state reveals a previously overlooked pathway linking tropical intraseasonal oscillations, meridional circulation and the hydrological cycle.
Pedro Sousa, Will Tebbutt, Sadiq Jaffer +3
Global weather reanalyses and forecasts resolve the evolving atmospheric state on coarse grids, but site-specific applications require predictions at arbitrary locations where near-surface conditions also depend on unresolved terrain and land-surface properties. Existing probabilistic downscalers address this gap using hand-crafted topographic descriptors. We ask instead whether Earth observation foundation models can provide transferable sub-grid surface representations for probabilistic weather downscaling. We augment a convolutional conditional neural process that downscales coarse ERA5 reanalysis fields at ~25 km resolution with a learned local surface descriptor, obtained by compressing a patch of TESSERA embeddings at 10 m resolution. Although these embeddings summarise surface conditions over annual timescales, they improve downscaling of instantaneous 2 m temperature and 10 m wind speed by encoding persistent surface properties that capture a location's departure from the coarse-grid atmospheric state. Across five climatically diverse regions, the embedding improves point and probabilistic skill at stations held out in both space and time, overall improving CRPS skill by 11.5% for 2 m temperature and 6.2% for 10 m wind speed. We further analyse how its contribution differs by variable, finding that topography explains more of temperature's sub-grid structure, while TESSERA provides additional surface information for wind speed. These improvements persist when the coarse input is changed from ERA5 to forecasts from the Aurora AI forecasting model, and when predicting at newly deployed stations with no regional history. To our knowledge, this is the first evidence that long-timescale Earth-observation embeddings can support short-timescale weather downscaling where sub-grid departures are systematically structured by persistent surface properties.
Zachary I Espinosa, Nathaniel Cresswell-Clay, William Yik +6
While AI has shown remarkable promise in atmospheric and meteorological forecasting, accurately simulating other components of the Earth system with AI remains an active frontier. We present DLESyM-Ocean, a Deep Learning Earth System Model that simulates global present-day sea ice and upper ocean conditions. Unlike conventional probabilistic models optimized via diffusion objectives or losses such as continuous-ranked probability score, DLESyM-Ocean is trained using a patch energy score loss. When driven by atmospheric forcing, DLESyM-Ocean produces a well-calibrated, spatially coherent, and skillful ensemble of sea ice and upper ocean conditions with minimal bias relative to reanalysis products. DLESyM-Ocean is stable when autoregressively run for multi-year simulations and produces a climatology and variability with minimal bias compared with reanalysis. We evaluate case studies including a recent sea ice extreme, a severe marine heatwave, the 2023 El Niño transition, and the 2023 spike in global mean temperature. In all of these case studies, DLESyM-Ocean produces realistic surface and subsurface trajectories and ample ensemble diversity in response to common atmospheric forcing, suggestive of learned autoregressive ocean dynamics. When coupled with other Earth system components, such as the atmosphere, the computational efficiency of DLESyM-Ocean makes it a promising tool for subseasonal to seasonal forecasting.
Gregory J. Hakim, Jeffrey S. Whitaker, Bo Huang +1
Atmospheric reanalyses combine observations with model forecasts using complex data assimilation systems. We test whether a differentiable weather model permits a simpler and more accurate method based on a long-window four-dimensional variational data assimilation (4D-Var) formulation that omits the conventional background-error term. The method uses automatic differentiation to find optimal NeuralGCM initial conditions that minimize the misfit to real surface-pressure observations distributed across overlapping windows of two to seven days, assuming no model error. Cycling at 6-hour intervals for three months beginning 1 January 2015 yields a stable reanalysis with smaller error relative to ERA5 in 500-hPa geopotential height than the Twentieth Century Reanalysis version 3 (20CRv3), which uses an ensemble Kalman filter to assimilate the same observations. Every window produces smaller errors than 20CRv3, with analysis error for the four-day window approximately 55% smaller than for 20CRv3. At the end of the four-day window, which does not benefit from future observations, error remains approximately 38% smaller than 20CRv3. Analyses degrade slightly beyond four days, which we attribute to the increasing importance of model error.
Xiang Weng, Xiao Lu, Jiawei Li +8
Many air quality models indicate that rapid reductions in nitrogen oxides (NOx), without comparable controls on volatile organic compounds, have worsened summertime ozone pollution in urban China, producing a short-term strong ozone penalty. Other models, however, simulate the opposite response, suggesting that cutting down NOx has already helped mitigate ozone pollution. This contradiction obscures understanding of atmospheric chemistry and weakens guidance on control policy design. Here, we reconcile this disagreement and reveal the underestimated benefits of NOx emission reductions using a machine learning framework integrated with an observational constraint. We first constrain ozone responses under a 30% NOx reduction, comparable to the magnitude of NOx emission declines across major Chinese city clusters between 2015 and 2023. The constrained results indicate that ozone decreases prevail across urban China, with only small increases mainly in July 2015. This challenges the widespread ozone worsening that many models predict. We then extend the constraint across 10-60% NOx reductions, establishing its use for rapid ozone sensitivity diagnosis without exhaustive scenario modeling. This diagnosis shows that sustained NOx control increasingly favored ozone mitigation during 2015-2023, benefiting a growing share of China's population. These results underscore that continued NOx reductions can deliver larger ozone mitigation benefits than many models suggest.
Andrew Goffin, Gregory Babic, Andrew DeRusha +3
Optical power densities for standoff spectroscopy, remote sensing, directed energy, and free-space optical communications are limited by diffraction and adverse atmospheric conditions such as turbulence, fog, and wind. Air waveguides, generated by ultrashort-pulsed laser filamentation, are a promising approach for transmission and collection of optical signals over long distances, overcoming beam diffraction and, for point-like sources, inverse square signal falloff with distance. In this work, we demonstrate outdoor guiding for the first time over a record length of 100 m, exceeding the prior (indoor) record of 42 m. We correlate air waveguide performance to a range of real atmospheric conditions including turbulent refractive index structure parameter (Cn2) values up to 2.5×10−14m−2/3, crosswind speeds up to 2 m/s, as well as temperature, pressure, and humidity variations. Accompanying propagation simulations provide insight into the real effects of these environmental perturbations, particularly crosswind, on waveguide performance and lifetime. Our results pave the way for quasi-continuous air waveguiding with kHz-scale repetition rate filaments in challenging outdoor environments.
Elynn Wu, James P. C. Duncan, Troy Arcomano +11
We present a stochastic coupled emulator of E3SM version 3, built on the SamudrACE framework, which couples an atmosphere emulator (ACE2) with a full-depth ocean emulator (Samudra). We replace the deterministic atmosphere emulator with its stochastic counterpart, ACE2S, and fine-tune the coupled system with a probabilistic objective, so that the atmosphere acts as a source of internal variability for the ocean. Trained on 105 years of a pre-industrial control simulation and evaluated on an independent 400 years, the emulator reproduces E3SMv3's mean climate state with biases much smaller than existing model-to-observation differences. Relative to a deterministic baseline, stochastic training maintains internal variability across timescales, most notably in the ENSO power spectrum, eddy-rich SST anomalies, and sea ice variability in the marginal ice zone. The emulator captures daily precipitation accurately up to the 99.99th percentile, but underestimates the rarest tropical extremes. These results show that stochastic coupled emulators can reproduce long-timescale variability with high fidelity, while extrapolation to unseen extremes remains a key challenge.
Ariel Zhitnitsky
Transient star-like objects of unknown origin have been identified in the first Palomar Observatory Sky Survey (POSS-1) as part of the Vanishing and Appearing Sources during a Century of Observations (VASCO) project. The source of the transients recorded by POSS-1 remains unknown, which is the warrant to coin the observed phenomena as Mysterious Transients (MT). We advocate an idea that the dark matter (DM) in form of the axion quark nuggets (AQN) made of standard model quarks (or antiquarks) and gluons, similar to the old idea of the Witten's strangelets, could simultaneously explain all the observed MT signals (including very short time scale for flash itself, association with nuclear test timing, observed alignments of several MT events, correlation with UAP reports, etc) collected or recorded for many years. Essentially we argue that the MT is a cousin of Ball Lightning (BL) events, also observed for centuries, without commonly accepted physics explanation. The basic parameters of this model (such as the typical baryon charge of the nuggets) had been fixed long ago by explaining the observed excess of radiation at variety of scales: from galactic to the solar, to local Earth's environments. In this work we use the same framework with the same set of parameters to study the observed MT phenomena. We also suggest several tests which substantiate or refute our proposal. We also present some suggestions on type of instruments required to study this specific (and well defined) type of the UAP events representing the cousins of BL and MT events in the AQN framework.
Swastik Agrawal, Nishkal Hundia, Ziyue Liu +1
Probabilistic coastal hazard assessments require accurate characterization of tropical cyclone (TC) parameters, yet datasets often contain missing records for the radius of maximum winds (Rmax), a key variable in Joint Probability Method analyses. This study evaluates data-driven approaches for Rmax imputation, including one-dimensional Convolutional Neural Networks (1DCNNs), Long Short-Term Memory (LSTM) networks, and conventional machine learning models. We examine physics-informed input augmentation, temporal modeling, and transfer learning using synthetic RAFT and STORM datasets for pre-training and observational IBTrACS data for fine-tuning. Including the radius of 34-knot winds (R34) substantially improves performance across all model types. Temporal models achieve higher average correlations than non-temporal models despite using approximately an order of magnitude fewer samples, indicating better preservation of relative Rmax variability across storms. This advantage is more pronounced when R34 is unavailable, suggesting temporal information can partially compensate for missing storm-size predictors. Transfer learning does not improve performance, likely because synthetic datasets have lower and less variable Rmax distributions than IBTrACS. These findings demonstrate the potential of temporal deep learning for reconstructing incomplete TC records and highlight the importance of physics-informed inputs, observational data availability, and distributional consistency in coastal hazard assessment.
Marion P. Mittermaier
Parts of Kerala were hit by devastating floods three years in a row. This sequence was historically without precedent. This paper uses a multivariate object-based approach to examine the global forecasts of the Met Office Unified Model for the 2018, 2019 and 2020 monsoon seasons to identify and understand the large-scale synoptic drivers that led to the floods. Identifying similarities between synoptic drivers behind these flooding events was a key objective, as was understanding whether one could enhance predictability by using a multivariate approach for post-processing forecast output, using variables other than just precipitation, which is often inherently less predictable on its own. To this end event identification focused on the analyses first, and then on a day 5 forecast. The study found that the multivariate version of the Method for Object-based Diagnostic Evaluation (MvMODE) was able to successfully identify sequences of days in all three seasons corresponding to the event dates, which in combination, had flood-producing potential. This was achieved in both the analyses and in the 5-day forecasts, proving that a) the events share common synoptic drivers and b) there is inherent predictability which can be tapped into. The 5-day forecasts matched the analysed objects on each occasion, proving that the underlying large-scale drivers may be predictable into the medium-range. Based on the results, the paper proposes a conceptual synoptic pattern evolution which can help identify such events in future. The synoptic pattern has some similarities to atmospheric rivers in the mid-latitudes.
Tasnia Noboni, Tuhin Das
A tethered autogyro with articulated rotors can operate as an unmanned aerial vehicle capable of energy-efficient, long-duration deployment by utilizing ambient wind energy to sustain flight. This article presents a model-based attitude control technique for such a system using a full-fidelity dynamic model. Using Lagrangian approach combined with Blade Element Momentum Theory and catenary mechanics, a previously developed 2D hybrid model is extended to three dimensions. The new model describes the complete rigid-body motion of the frame, including roll and yaw dynamics, and is augmented with rotor speed and flapping degrees of freedom for each blade. Equilibrium characteristics are examined through steady-state responses and compared with the prior model. The resulting trends of equilibria are found to be consistent with those reported in the literature. A feedback control strategy based on regenerative differential rotor braking is developed to modulate all three attitude angles. Simulations demonstrate effective attitude regulation and stable flight.
Lucas J. Howard, Elizabeth A. Barnes
Ensemble forecasting aims to sample the conditional distribution of outcomes; whether AI forecast ensembles do this correctly in a joint sense remains largely untested. We train a diffusion model for probabilistic subseasonal coastal sea level forecasts at eight US East Coast tide gauge stations, with sea level derived from reanalysis, and find that marginal and joint forecast quality decouple: positive skill at every station and lead time marginally, while joint spatial structure is worse than climatological draws. A shuffle-based permutation decomposition reveals this failure is invisible to the energy score but detected by the variogram score. Lorenz-96 experiments across 0.7-170 equivalent years show the gap persists regardless of training volume and is reproduced by a linear baseline, indicating structural inadequacy of the learned distribution. A dynamical ensemble does not replicate the failure while a deterministic emulator does, suggesting it is specific to learned emulators rather than ensemble forecasting generally.
Onkar Jadhav, Tim French, Ivica Janekovic +2
The large-scale oceanic and atmospheric forecasts provided by global climate models typically lack sufficient resolution to accurately capture the response of the coastal ocean to atmospheric forcing and coastal circulation that drive fine-scale SST variability. Dynamical downscaling is computationally prohibitive, when applied to extensive coastlines, predictive ensembles, or long time periods. Therefore, this work presents a statistical downscaling of sea surface temperature (SST) from the seasonal coupled ocean-atmosphere forecast system (ACCESS-S2) using machine learning techniques. This study proposes a novel deep learning framework that uses a U-Net to generate an initial high-resolution SST estimate, which is subsequently refined using a residual corrective approach. The target SST fields are derived from the Regional Ocean Modeling System (ROMS). This two step approach called Residual Corrective Neural Network (RCNN) progressively refines initial U-Net predictions by incorporating dynamically scaled residuals at each step, enabling accurate capture of broad patterns and fine-grained features such as eddies and fronts. We also introduce a custom loss-assisted RCNN variant to improve performance during extreme events, which may be absent from training data due to climate-driven shifts in SST extremes. The framework efficiently downscales SST along the west coast of Australia. A 2011 marine heatwave case study shows that the RCNN improves ACCESS-S2 SST predictions by increasing horizontal resolution from 25 km to 2 km, enabling identification of fine-scale anomalies unresolved in the ACCESS-S2 dataset. This balance between computational efficiency and accuracy supports applications in coastal impact assessment and marine ecosystem studies.
Rashad P E, Akshay Sunil
Extreme monsoon rainfall over Kerala presents a major operational forecasting challenge because of the interaction of Arabian Sea moisture transport, mesoscale convection, coastal convergence, and strong orographic forcing along the Western Ghats. Spatial analysis showed that WFS reproduced the principal Western-Ghats-aligned rainfall corridor and represented localized high-intensity rainfall structures more distinctly than the smoother global-model guidance examined for the event. The results demonstrate the complementary roles of operational regional guidance and higher-resolution diagnostic forecasts and highlight the importance of region-specific calibration, spatial verification, and continued evaluation across multiple monsoon events and forecast lead times.
Kevin Speer, Bryan Quaife, Jie Sun
In this Chapter we explore the nature and theory of ember transport using observations from controlled laboratory settings, prescribed fire, and wildland fire. Specific examples and statistics from fires are used to gain insight and motivate a hierarchy of modeling approaches from simple idealized models to full-physics atmospheric boundary layer models. The emphasis is on the fundamental processes involved in moving embers away from their sources in vegetation and structures on and near the ground or in the atmospheric boundary layer winds and turbulent flows. We describe the problem first in terms of basic theory about the rate of spread of wildland fire, examine the physical principles at work in ember transport for two principle modes of transport near the ground and in the atmosphere well above the surface, and connect these to statistical models for transport.
Ieuan Higgs, Todd Jones, Kieran Hunt +1
As artificial intelligence (AI) systems transition from research prototypes to operational tools in Earth system science and forecasting, establishing trust in their predictions becomes increasingly important. Although model inputs and outputs are observable, the internal decision-making of modern AI models remains complex and hard to interpret, earning them the label ``black boxes.'' Explainable artificial intelligence (XAI) offers techniques to provide insight into these processes. However, most XAI methods were developed for classification tasks, raising questions about their suitability for the regression problems that dominate geoscientific applications. We review XAI approaches through this lens, organising them into a structured framework and examining both their theoretical foundations and practical behaviour. To ground this discussion, we apply a selection of methods to a machine learning emulator of the Lorenz 1963 system, an archetypal chaotic model that provides a tractable, physically meaningful setting for exposing the limitations and failure modes of general-purpose XAI in regression contexts. We then survey how these and related methods have been applied across a variety of Earth system sciences. We further situate XAI within the model development lifecycle, linking methodological choices to the needs of different stakeholder groups across operational Earth system science. We close by identifying gaps in existing methodologies and outlining a forward-looking research agenda, with practical recommendations for the responsible, effective use of XAI in regression applications of geoscientific modelling and forecasting.