Ensemble Simulations Research Articles

PDO influenced interdecadal summer precipitation change over East China in mid-18th century

There have been few case studies of the relationship between the Pacific Decadal Oscillation (PDO) and the East Asian climate before the pre-industrial era with limited anthropogenic impacts. Using the CESM Last Millennium Ensemble (CESM-LME) simulation with reconstruction evidence, we showed that there was an interdecadal transition of the summer precipitation in East China, with the pattern of “southern flooding and northern drought” in the mid-18th century. The interdecadal transition was influenced by PDO, as suggested by both the reconstruction evidence and simulation. Corresponding to the positive PDO phase change, the East Asia-Pacific pattern teleconnection wave train propagated northward and modulated the circulation and precipitation in East China, together with the southward movement of the East Asian westerly jet. The volcanic double or clustered eruptions are thought to have played a crucial role on the shift of the PDO phase and the decadal summer climate change over East China during the mid-18th century. Incorporating volcanic activity in a reasonable manner would likely improve decadal simulations of East Asian climate in the past and predictions in the future.

Impacts of Changes in Soil Moisture on Urban Heat Islands and Urban Breeze Circulations: Idealized Ensemble Simulations

Soil moisture plays important roles in land surface and hydrological processes, and its changes can greatly affect weather and climate. In this study, we examine how changes in soil moisture impact the urban heat island (UHI) and urban breeze circulation (UBC) through idealized ensemble simulations. As soil moisture increases, the latent heat flux increases considerably in the rural area. Hence, in the rural area, the sensible heat flux and surface temperature decrease, which decreases the rural air temperature. The decrease in rural air temperature leads to increases in UHI intensity and thus UBC intensity. The urban air temperature also decreases with increasing soil moisture since the cooler rural air is advected to the urban area by the enhanced low-level convergent flow of the UBC. However, the decrease in air temperature is smaller in the urban area than in the rural area. As the UBC intensity increases, the sensible heat flux in the urban area increases. The increase in sensible heat flux in the urban area further increases the UHI intensity. The positive feedback between the UHI intensity and the UBC intensity is revealed when soil moisture increases. The decrease in air temperature in both the urban and rural areas leads to the decrease in planetary boundary layer (PBL) height. As a result, the vertical size of the UBC decreases with increasing soil moisture. As the UBC intensity increases with increasing soil moisture, the advection of water vapor from the rural area to the urban area increases. Combined with the decrease in PBL height, this reduces the water vapor deficit or even leads to the water vapor excess in the urban area depending on soil moisture content.

Initial atmospheric conditions control transport of volcanic volatiles, forcing and impacts

Abstract. Volcanic eruptions impact the climate and environment. The volcanic forcing is determined by eruption source parameters, including the mass and composition of volcanic volatiles, eruption season, eruption latitude, and injection altitude. Moreover, initial atmospheric conditions of the climate system play an important role in shaping the volcanic forcing and response. However, our understanding of the combination of these factors, the distinctions between tropical and extratropical volcanic eruptions, and the co-injection of sulfur and halogens remains limited. Here, we perform ensemble simulations of volcanic eruptions at 15 and 64° N in January, injecting 17 Mt of SO2 together with HCl and HBr at 24 km altitude. Our findings reveal that initial atmospheric conditions control the transport of volcanic volatiles from the first month and modulate the subsequent latitudinal distribution of sulfate aerosols and halogens. This results in different volcanic forcing, surface temperature and ozone responses over the globe and Northern Hemisphere extratropics (NHET) among the model ensemble members with different initial atmospheric conditions. NH extratropical eruptions exhibit a larger NHET mean volcanic forcing, surface cooling and ozone depletion compared with tropical eruptions. However, tropical eruptions lead to more prolonged impacts compared with NH extratropical eruptions, both globally and in the NHET. The sensitivity of volcanic forcing to varying eruption source parameters and model dependency is discussed, emphasizing the need for future multi-model studies to consider the influence of initial conditions and eruption source parameters on volcanic forcing and subsequent impacts.

Shortwave Radiative Flux Variability Through the Lens of the Pacific Decadal Oscillation

AbstractThe variability of the shortwave radiative fluxes at the surface and top of atmosphere (TOA) is examined in a pre‐industrial modeling setup using the Pacific Decadal Oscillation (PDO) as a possible pacemaker of atmospheric decadal‐scale variability. Within models from the Coupled Model Intercomparison Project—Phase 6, downwelling shortwave radiation at the surface, the net shortwave fluxes at the surface and TOA, as well as cloud radiative effects show remarkably similar patterns associated with the PDO. Through ensemble simulations designed with a pure PDO pattern in the North Pacific only, we show that the PDO relates to about 20%–40% of the unforced year‐to‐year variability of these shortwave fluxes over the Northern Hemispheric continents. The sea surface temperature imprint on shortwave‐flux variability over land is larger for spatially aggregated time series as compared to smaller areas, due to the blurring effect of small‐scale atmospheric noise. The surface and TOA radiative flux anomalies associated with the PDO index range of [−1.64; 1.64] are estimated to reach up to ±6 Wm−2 for North America, ∓3 Wm−2 for India and ±2 Wm−2 for Europe. We hypothesize that the redistribution of clouds in response to a North Pacific PDO anomaly can impact the South Pacific and North Atlantic SSTs.

Urban influence on convective precipitation in the Paris region: Hectometric ensemble simulations in a case study

AbstractThe purpose of this study is to investigate the influence of the urban environment of the Paris region on an isolated convective cell that formed downwind of the city on May 7, 2022, using the Meso‐NH research atmospheric model at a horizontal scale of 300 m. To account for all sources of forecast uncertainty, the initial and lateral boundary conditions of the simulations are provided by an ensemble prediction system. A multi‐layer urban scheme is used to represent the influence of buildings on the airflow accurately. Two sets of ensemble simulations are performed: the first set (URB) uses a fine‐scale surface description of the city, while the second set (NOURB) replaces urban surfaces with vegetation. This sensitivity test shows that, despite the high variability of simulated precipitation within the ensemble, the city of Paris plays a statistically significant role in the initiation of convection in this case. Convective cells are initiated over the city for several members of the URB ensemble, while almost no precipitation is simulated for the same members of the NOURB ensemble. The mean 6‐h rainfall accumulation of the URB ensemble is increased by 70% over Paris (compared with the NOURB ensemble) and no statistically significant trend is found around the city. The analysis reveals that the capital experiences a higher sensible heat flux due to drier and warmer air, resulting in enhanced vertical velocities and an increase in boundary‐layer height in the URB ensemble. Additionally, the total water content and cloud fraction over Paris are intensified, leading to more precipitation. These findings suggest that urbanisation has a notable impact on convection and precipitation processes in this case.

A novel dynamic ensemble of numerical weather prediction for multi-step wind speed forecasting with deep reinforcement learning and error sequence modeling

Accurate wind forecasts for one day ahead or longer periods have significant impacts on the safe and efficient dispatch of power grids, where Numerical Weather Prediction (NWP) serves as the essential tool, such as ensemble NWP integrating multiple single simulations. Typically, ensembles include all single members with fixed weights; however, the relative accuracy of each member may change over time. This study introduces an attractive idea: improving ensemble performance by dynamically recognizing and avoiding low-performing members. It proposes a dynamic ensemble strategy based on NWP, reinforcement learning and error sequence correction. The process begins with Weather Research and Forecasting ensemble simulations. A dynamic framework is then constructed by mapping the multi-step ensemble problem into a Markov decision process, which is further solved using deep deterministic policy gradient. Subsequently, a hybrid deep learning model, comprising temporal convolutional network and bidirectional long short-term memory, is constructed for error sequence estimation of dynamic ensemble, using the high-frequency information of NWP as input. Conducting experiments at two wind farms, and focusing on the 24-h wind speed forecast with a 15-min time resolution, the proposed system demonstrates a reliable and stable ensemble throughout the entire forecasting horizon, significantly reducing the probability of large forecasting errors.

Technical note: An assessment of the performance of statistical bias correction techniques for global chemistry–climate model surface ozone fields

Abstract. State-of-the-art chemistry–climate models (CCMs) still show biases compared to ground-level ozone observations, illustrating the difficulties and challenges remaining in the simulation of atmospheric processes governing ozone production and loss. Therefore, CCM output is frequently bias-corrected in studies seeking to explore the health or environmental impacts from changing air quality burdens. Here, we assess four statistical bias correction techniques of varying complexities and their application to surface ozone fields simulated with four CCMs and evaluate their performance against gridded observations in the EU and US. We focus on two time periods (2005–2009 and 2010–2014), where the first period is used for development and training and the second to evaluate the performance of techniques when applied to model projections. We find that all methods are capable of significantly reducing the model bias. However, biases are lowest when we apply more complex approaches such as quantile mapping and delta functions. We also highlight the sensitivity of the correction techniques to individual CCM skill at reproducing the observed distributional change in surface ozone. Ensemble simulations available for one CCM indicate that model ozone biases are likely more sensitive to the process representation embedded in chemical mechanisms than to meteorology.

Predicting the pathways of string-like motions in metallic glasses via path-featurizing graph neural networks.

String-like motions (SLMs)-cooperative, "snake"-like movements of particles-are crucial for dynamics in diverse glass formers. Despite their ubiquity, questions persist: Do SLMs prefer specific paths? If so, can we predict these paths? Here, in Al-Sm glasses, our isoconfigurational ensemble simulations reveal that SLMs do follow certain paths. By designing a graph neural network (GNN) to featurize the environment around directional paths, we achieve a high-fidelity prediction of likely SLM pathways, solely based on the static structure. GNN gauges a structural measure to assess each path's propensity to engage in SLMs, akin to a "softness" metric, but for paths rather than for atoms. Our GNN interpretation reveals the critical role of the bottleneck zone along a path in steering SLMs. By monitoring "path softness," we elucidate that SLM-favored paths transit from fragmented to interconnected upon glass transition. Our findings reveal that, beyond atoms or clusters, glasses have another dimension of structural heterogeneity: "paths."

Elevation-dependent warming: observations, models, and energetic mechanisms

Abstract. Observational data and numerical models suggest that, under climate change, elevated land surfaces warm faster than non-elevated ones. Proposed drivers of this “elevation-dependent warming” (EDW) include surface albedo and water vapour feedbacks, the temperature dependence of longwave emission, and aerosols. Yet the relative importance of each proposed mechanism both regionally and at large scales is unclear, highlighting an incomplete physical understanding of EDW. Here we expand on previous regional studies and use gridded observations, atmospheric reanalysis, and a range of climate model simulations to investigate EDW over the historical period across the tropics and subtropics (40° S to 40° N). Observations, reanalysis, and fully coupled models exhibit annual mean warming trends (1959–2014), binned by surface elevation, which are larger over elevated surfaces and broadly consistent across datasets. EDW varies by season, with stronger observed signals in local winter and autumn. Analysis of large ensembles of single-forcing simulations (1959–2005) suggests historical EDW is likely a forced response of the climate system rather than an artefact of internal variability and is primarily driven by increasing greenhouse gas concentrations. To gain quantitative insight into the mechanisms contributing to large-scale EDW, a forcing–feedback framework based on top-of-atmosphere energy balance is applied to the fully coupled models. This framework identifies the Planck and surface albedo feedbacks as being robust drivers of EDW (i.e. enhancing warming over elevated surfaces), with energy transport by the atmospheric circulation also playing an important role. In contrast, water vapour and cloud feedbacks along with weaker radiative forcing in elevated regions oppose EDW. Implications of the results for understanding future EDW are discussed.

Human–machine partnerships at the exascale: exploring simulation ensembles through image databases

Human–machine partnerships at the exascale: exploring simulation ensembles through image databases

An enhanced fourier neural operator surrogate for radioactive plume transport forecasting

Accurate real-time forecasts of atmospheric plume behavior are crucial for effective management of environmental release incidents. However, the computational demands of weather simulations and particle transport codes limit their applicability during emergencies. In this study, we employ a U-Net enhanced Fourier Neural Operator (U-FNO) to statistically emulate the calculations of the WSPEEDI dose forecasting numerical simulator, using pre-calculated ensemble simulations. The developed emulator is capable of effectively simulating any radioactive-release scenario and generating the time series of dose distribution in the environment 4000 times faster than the numerical simulator, while still maintaining high accuracy. It predicts the plume direction, extent, and dose-rate magnitudes using initial- and boundary-condition meteorological data as input. The speed and efficiency of this framework offers a powerful tool for swift decision-making during emergencies, facilitating risk-informed protective actions, evacuation execution, and zone delineation. Its application extends to various contaminant release and transport problems, and can be instrumental in engineering tasks requiring uncertainty quantification (UQ) for environmental risk assessment.

Steady but model dependent Arctic amplification of the forced temperature response in 21st century CMIP6 projections

We examine sources of uncertainty in projections of Arctic amplification (AA) using the CMIP6 multi-model (MM) ensemble and single model initial-condition large ensembles of historical and future scenario simulations. In the CMIP6 MM mean, the annual mean AA ratio is steady at approximately 2.5, both in time and across scenarios, resulting in negligibly small scenario uncertainty in the magnitude of AA. Deviations from the steady value can be found at the low and high emission scenarios due to different root causes, with the latter being mostly evident in the summer and autumn seasons. Best estimates of model uncertainty are at least an order of magnitude larger than scenario uncertainty in CMIP6. The large ensembles reveal that irreducible internal variability has a similar magnitude to model uncertainty for most of the 21st century, except in the lowest emission scenario at the end of the 21st century when it could be twice as large.

Future Projections of Precipitation Extremes for Greece Based on an Ensemble of High-Resolution Regional Climate Model Simulations

An assessment of the projected changes in precipitation extremes for the 21st century is presented here for Greece and its individual administrative regions. The analysis relies on an ensemble of high-resolution Regional Climate Model (RCM) simulations following various Representative Concentration Pathways (RCP2.6, RCP4.5, and RCP8.5). The simulated changes in future annual total precipitation (PRTOT) under the examined scenarios are generally negative but statistically non-robust, except towards the end of the century (2071–2100) over high-altitude mountainous regions in Western Greece, Peloponnese, and Crete under RCP8.5. The pattern of change in the number of very heavy precipitation days (R20) is linked to the respective pattern of the PRTOT change with a statistically robust decrease of up to −5 days per year only over parts of the high-altitude mountainous regions in Western Greece, Peloponnese, and Crete for 2071–2100 under RCP8.5. Contrasting the future tendency for decrease in total precipitation and R20, the changes in the intensity of precipitation extremes show a tendency for intensification. However, these change patterns are non-robust for all periods and scenarios. Statistical significance is indicated for the highest 1-day precipitation amount in a year (Rx1day) for the administrative regions of Thessaly, Central Greece, Ionian Islands, and North Aegean under RCP8.5 in 2071–2100. The changes in the contribution of the wettest day per year to the annual total precipitation (RxTratio) are mainly positive but non-robust for most of Greece and all scenarios in the period 2021–2050, becoming more positive and robust in 2071–2100 for RCP8.5. This work highlights the necessity of taking into consideration high-resolution multi-model RCM estimates in future precipitation extremes with various scenarios, for assessing their potential impact on flood episodes and the strategic planning of structure resilience at national and regional level under the anticipated human-induced future climate change.

Dental biomaterials redefined: molecular docking and dynamics-driven dental resin composite optimization

BackgroundDental resin-based composites are widely recognized for their aesthetic appeal and adhesive properties, which make them integral to modern restorative dentistry. Despite their advantages, adhesion and biomechanical performance challenges persist, necessitating innovative strategies for improvement. This study addressed the challenges associated with adhesion and biomechanical properties in dental resin-based composites by employing molecular docking and dynamics simulation.MethodsMolecular docking assesses the binding energies and provides valuable insights into the interactions between monomers, fillers, and coupling agents. This investigation prioritizes SiO2 and TRIS, considering their consistent influence. Molecular dynamics simulations, executed with the Forcite module and COMPASS II force field, extend the analysis to the mechanical properties of dental composite complexes. The simulations encompassed energy minimization, controlled NVT and NPT ensemble simulations, and equilibration stages. Notably, the molecular dynamics simulations spanned a duration of 50 ns.ResultsSiO2 and TRIS consistently emerged as influential components, showcasing their versatility in promoting solid interactions. A correlation matrix underscores the significant roles of van der Waals and desolvation energies in determining the overall binding energy. Molecular dynamics simulations provide in-depth insights into the mechanical properties of dental composite complexes. HEMA-SiO2-TRIS excelled in stiffness, BisGMA-SiO2-TRIS prevailed in terms of flexural strength, and EBPADMA-SiO2-TRIS offered a balanced combination of mechanical properties.ConclusionThese findings provide valuable insights into optimizing dental composites tailored to diverse clinical requirements. While EBPADMA-SiO2-TRIS demonstrates distinct strengths, this study emphasizes the need for further research. Future investigations should validate the computational findings experimentally and assess the material's response to dynamic environmental factors.

A Machine-Learning-Assisted Classification Algorithm for the Detection of Archaeological Proxies (Cropmarks) Based on Reflectance Signatures

The detection of subsurface archaeological remains using a range of remote sensing methods poses several challenges. Recent studies regarding the detection of archaeological proxies like those of cropmarks highlight the complexity of the phenomenon. In this work, we present three different methods, and associated indices, for identifying stressed reflectance signatures indicating buried archaeological remains, based on a dataset of measured ground spectroradiometric reflectance. Several spectral profiles between the visible and near-infrared parts of the spectrum were taken in a controlled environment in Cyprus during 2011–2012 and are re-used in this study. The first two (spectral) methods are based on a suitable analysis of the spectral signatures in (1) the visible part of the spectrum, in particular in the neighborhood of 570 nm, and (2) the red edge part of the spectrum, in the neighborhood of 730 nm. Machine learning (decision trees) allows for the deduction of suitable wavelengths to focus on in order to formulate the proposed indices and the associated classification criteria (decision boundaries) that can enhance the detection probability of stressed vegetation. Noise in the signal is taken into account by simulating reflectance signatures perturbed by white noise. Applying decision tree classification on the ensemble of simulations and basic statistical analysis, we refine the formulation of the indices and criteria for the noisy signatures. The success rate of the proposed methods is over 90%. The third method rests on the estimation of vegetation/canopy reflectance parameters through inversion of the physical-based PROSAIL reflectance model and the associated classification through machine learning methods. The obtained results provide further insights into the formation of stress vegetation that occurred due to the presence of shallow buried archaeological remains, which are well aligned with physical-based models and existing empirical knowledge. To the best of the authors’ knowledge, this is the first study demonstrating the usefulness of radiative transfer models such as PROSAIL for understanding the formation of cropmarks. Similar studies can support future research directions towards the development of regional remote sensing methods and algorithms if systematic observations are adequately dispersed in space and time.

The added value of simulated near-surface wind speed over the Alps from a km-scale multimodel ensemble

The advancement of computational resources has allowed researchers to run convection-permitting regional climate model (CPRCM) simulations. A pioneering effort promoting a multimodel ensemble of such simulations is the CORDEX Flagship Pilot Studies (FPS) on “Convective Phenomena over Europe and the Mediterranean” over an extended Alps region. In this study, the Distribution Added Value metric is used to determine the improvement of the representation of all available FPS hindcast simulations for the daily mean near-surface wind speed. The analysis is performed on normalized empirical probability distributions and considers station observation data as the reference. The use of a normalized metric allows for spatial comparison among the different regions (coast and inland), altitudes and seasons. This approach permits a direct assessment of the added value between the CPRCM simulations against their global driving reanalysis (ERA-Interim) and respective coarser resolution regional model counterparts. In general, the results show that CPRCMs add value to their global driving reanalysis or forcing regional model, due to better-resolved topography or through better representation of ocean-land contrasts. However, the nature and magnitude of the improvement in the wind speed representation vary depending on the model, the season, the altitude, or the region. Among seasons, the improvement is usually larger in summer than winter. CPRCMs generally display gains at low and medium-range altitudes. In addition, despite some shortcomings in comparison to ERA-Interim, which can be attributed to the assimilation of wind observations on the coast, the CPRCMs outperform the coarser regional climate models, both along the coast and inland.

GrainGNN: A dynamic graph neural network for predicting 3D grain microstructure

We propose GrainGNN, a surrogate model for the evolution of polycrystalline grain structure under rapid solidification conditions in metal additive manufacturing. High fidelity simulations of solidification microstructures are typically performed using multicomponent partial differential equations (PDEs) with moving interfaces. The inherent randomness of the PDE initial conditions (grain seeds) necessitates ensemble simulations to predict microstructure statistics, e.g., grain size, aspect ratio, and crystallographic orientation. Currently such ensemble simulations are prohibitively expensive and surrogates are necessary.In GrainGNN, we use a dynamic graph to represent interface motion and topological changes due to grain coarsening. We use a reduced representation of the microstructure using hand-crafted features; we combine pattern finding and altering graph algorithms with two neural networks, a classifier (for topological changes) and a regressor (for interface motion). Both networks have an encoder-decoder architecture; the encoder has a multi-layer transformer long-short-term-memory architecture; the decoder is a single layer perceptron.We evaluate GrainGNN by comparing it to high-fidelity phase field simulations for in-distribution and out-of-distribution grain configurations for solidification under laser power bed fusion conditions. GrainGNN results in 80%–90% pointwise accuracy; and nearly identical distributions of scalar quantities of interest (QoI) between phase field and GrainGNN simulations compared using Kolmogorov-Smirnov test. GrainGNN's inference speedup (PyTorch on single x86 CPU) over a high-fidelity phase field simulation (CUDA on a single NVIDIA A100 GPU) is 150×–2000× for 100-initial grain problem. Further, using GrainGNN, we model the formation of 11,600 grains in 220 seconds on a single CPU core.

20th‐Century Antarctic Sea Level Mitigation Driven by Uncertain East Antarctic Accumulation History

AbstractIncreasing snow accumulation over the Antarctic Ice Sheet may mitigate future sea level rise. However, current estimates of mitigation potential are poorly constrained due to limited records of past variability. We present an annually resolved reconstruction of Antarctic snow accumulation from 1801 to 2000 CE, employing a paleoclimate data assimilation methodology to integrate ice core records with a multi‐model ensemble of climate simulations. Our reconstruction correlates well with instrumental reanalysis, and we find that Antarctic accumulation rates increased over the 20th‐century, resulting in a modest amount (∼1 mm) of sea level mitigation. Mitigation is primarily driven by an accelerating trend since around 1970. Our results contrast with previous mitigation estimates of ∼10–12 mm; this discrepancy is due to poorly constrained baseline estimates of 19th‐century accumulation in East Antarctica. Our reconstruction suggests that the uncertainty of future sea level mitigation from increasing Antarctic accumulation has been underestimated.

Quantifying Contributions of External Forcing and Internal Variability to Arctic Warming During 1900–2021

AbstractArctic warming has significant environmental and social impacts. Arctic long‐term warming trend is modulated by decadal‐to‐multidecadal variations. Improved understanding of how different external forcings and internal variability affect Arctic surface air temperature (SAT) is crucial for explaining and predicting Arctic climate changes. We analyze multiple observational data sets and large ensembles of climate model simulations to quantify the contributions of specific external forcings and various modes of internal variability to Arctic SAT changes during 1900–2021. We find that the long‐term trend and total variance in Arctic‐mean SAT since 1900 are largely forced responses, including warming due to greenhouse gases and natural forcings and cooling due to anthropogenic aerosols. In contrast, internal variability dominates the early 20th century Arctic warming and mid‐20th century Arctic cooling. Internal variability also explains ∼40% of the recent Arctic warming from 1979 to 2021. Unforced changes in Arctic SAT are largely attributed to two leading modes. The first is pan‐Arctic warming with stronger loading over the Eurasian sector, accounting for 70% of the unforced variance and closely related to the positive phase of the unforced Atlantic Multidecadal Oscillation (AMO). The second mode exhibits relatively weak warming averaged over the entire Arctic with warming over the North American‐Pacific sector and cooling over the Atlantic sector, explaining 10% of the unforced variance and likely caused by the positive phase of the unforced Interdecadal Pacific Oscillation (IPO). The AMO‐related changes dominate the unforced Arctic warming since 1979, while the IPO‐related changes contribute to the decadal SAT changes over the North American‐Pacific Arctic.

A Nonstationary Stochastic Rainfall Generator Conditioned on Global Climate Models for Design Flood Analyses in the Mississippi and Other Large River Basins

AbstractExisting stochastic rainfall generators (SRGs) are typically limited to relatively small domains due to spatial stationarity assumptions, hindering their usefulness for flood studies in large basins. This study proposes StormLab, an SRG that simulates precipitation events at 6‐hr and 0.03° resolution in the Mississippi River Basin (MRB). The model focuses on winter and spring storms caused by water vapor transport from the Gulf of Mexico—the key flood‐generating storm type in the basin. The model generates anisotropic spatiotemporal noise fields that replicate local precipitation structures from observed data. The noise is transformed into precipitation through parametric distributions conditioned on large‐scale atmospheric fields from a climate model, reflecting spatial and temporal nonstationarity. StormLab can produce multiple realizations that reflect the uncertainty in fine‐scale precipitation arising from a specific large‐scale atmospheric environment. Model parameters were fitted monthly from December–May, based on storms identified from 1979 to 2021 ERA5 reanalysis data and Analysis of Record for Calibration (AORC) precipitation. StormLab then generated 1,000 synthetic years of precipitation events based on 10 CESM2 ensemble simulations. Empirical return levels of simulated annual maxima agree well with AORC data and show an overall increase in 1‐ to 500‐year events in the future period (2022–2050). To our knowledge, this is the first SRG simulating nonstationary, anisotropic high‐resolution precipitation over continental‐scale river basins, demonstrating the value of conditioning such stochastic models on large‐scale atmospheric variables. StormLab provides a wide range of extreme precipitation scenarios for design floods in the MRB and can be further extended to other large river basins.