Search NASA⌕ Search

SEARCH · Search NASA

Results for “model skill”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Dominant Controls on Preferential Flow and Their Implications for Future Soil Water Fluxes

Abstract Soil water flow, particularly preferential flow (PF), is a critical control on hydrological and biogeochemical processes, including groundwater recharge, contaminant transport, and carbon cycling. However, it remains challenging to predict PF occurrence across large environmental gradients. Here, we developed a deep learning (DL) model to estimate event‐scale soil water flow velocity and the probability of PF occurrence using high‐frequency soil moisture and precipitation data from 33 sites across the National Ecological Observatory Network. The model demonstrated high skill in predicting the binary occurrence of PF (91% F1‐score; 85% accuracy) but the performance was limited in predicting soil water velocity ( R 2 = 0.31). We found that precipitation characteristics (duration, volume, and intensity) were the most important predictors for soil water velocity. Among the non‐precipitation event variables, sand content showed relatively high predictive skill, though differences among non‐event climate variables were generally modest. Lower sand content was associated with increased predicted soil water velocity, a finding that highlights the role of soil structure in producing more non‐uniform flow, which contrasts with traditional uniform flow models. Projecting a reduced DL model under both moderate and high‐emissions future climate scenarios (2060–2099 Representative Concentration Pathways 4.5 and 8.5), we found ∼7.3% increase under RCP4.5 and ∼15% under RCP8.5 of soil water velocities compared to the historical simulation, while modeled likelihood of PF changed little. These findings suggest climate change is not making PF more frequent, but it is making existing PF pathways more efficient with important consequences for associated nutrient and contaminant transport under climate change. Plain Language Summary Water movement in soil is critical for water quality. While often modeled as a uniform flow process, in reality water moves rapidly through cracks and burrows in what is called “preferential flow” (PF), which limits natural filtration and can transport pollutants. We developed a deep learning model, trained on data from 33 U.S. sites, to predict when and how fast this PF occurs based on precipitation, soil, and climate data. The model showed that precipitation characteristics (duration, intensity, volume) were the most important predictors of PF. Lower soil sand content/higher clay content was associated with faster water flow, likely due to clay soils forming aggregates and cracks that water moves through rather than infiltrating uniformly. Further analyses based on climate projections suggest that the speed at which PF occurs will become more rapid under future climate scenarios compared to historical simulation. This highlights the need to represent PF in soil water models when assessing future water quality. Key Points The effect of precipitation peak intensity on soil water velocities declined with increasing precipitation intensity Antecedent soil moisture failed to predict preferential flow (PF), contrasting the high predictive power of sand content Climate predictions suggest that soil water velocities through PF paths will increase ∼15% by 2099

Li, Bonan↗
DOE OSTI2026

Application of artificial intelligence methods in the international roughness index prediction of rigid and composite pavements: a systematic review

The International Roughness Index (IRI) is a widely adopted metric for quantifying pavement roughness, directly influencing vehicle safety, ride comfort, and overall roadway performance. In recent years, the use of Machine Learning (ML) models for IRI prediction has gained momentum, with the goal of improving the allocation of maintenance and rehabilitation resources by enabling accurate assessments of pavement conditions. Most prior reviews, however, have concentrated on flexible pavements, leaving a notable gap regarding rigid and composite pavements. To address this gap, the present study conducts a systematic review of Artificial Intelligence (AI) methods applied to IRI prediction for rigid and composite pavements. Literature published between 2004 and 2025 is synthesized to highlight prevailing trends, methodological contributions, and directions for future research. Particular attention is given to the types of models employed, the datasets used for training and validation, and the role of input variables and data-processing strategies. Across the included studies, ensemble learning methods (especially gradient boosting variants such as XGBoost), artificial neural networks, and hybrid architectures frequently achieved high predictive skill, with several models reporting test-set coefficients of determination approaching 0.9–0.96, indicating strong potential for capturing the influence of traffic, pavement structure, and climatic factors. Since these results are obtained from heterogeneous datasets and evaluation protocols, they are interpreted qualitatively rather than as strict cross-study rankings. Analysis of input variables revealed that pavement age and initial IRI were included in 91% (21 of 23) and 78% (18 of 23) of studies, respectively. Climatic variables such as the freezing index appeared in 57% (13 of 23), while traffic-related factors were considered in 65% (15 of 23). The findings underscore the importance of standardized, high-quality datasets, such as those from the Long-Term Pavement Performance (LTPP) program, along with data consistency, model interpretability, computational efficiency, and replicability in enhancing IRI prediction. Future research should focus on incorporating input variable selection techniques to identify the most influential predictors, thereby improving accuracy and robustness. Integrating these approaches with advanced non-linear data-driven models, coupled with robust hyperparameter optimization, holds considerable promise for strengthening the reliability of IRI prediction and supporting resilient pavement management strategies.

42 ENGINEERING↗
DOE OSTI2026

Hierarchical Testing of a Hybrid Machine Learning‐Physics Global Atmosphere Model

Machine learning (ML)-based models have demonstrated high skill and computational efficiency, often outperforming conventional physics-based models in weather and subseasonal predictions. While prior studies have assessed their fidelity in capturing synoptic-scale atmospheric dynamics, their performance across timescales and under out-of-distribution forcing, such as +3K or +4K uniform-warming forcings, and the sources of biases remain elusive, to establish the model's reliability for Earth science. Here, we design three sets of experiments targeting synoptic-scale phenomena, interannual variability, and out-of-distribution uniform-warming forcings. We evaluate the Neural General Circulation Model (NeuralGCM), a hybrid model integrating a dynamical core with ML-based component, against observations and physics-based Earth system models (ESMs). At the synoptic scale, NeuralGCM captures the evolution and propagation of extratropical cyclones with performance comparable to ESMs. At the interannual scale, when forced by El Niño-Southern Oscillation sea surface temperature (SST) anomalies, NeuralGCM successfully reproduces associated teleconnection patterns but exhibits deficiencies in capturing nonlinear response. Under out-of-distribution uniform-warming forcings, NeuralGCM simulates similar responses in global-average temperature and precipitation and reproduces large-scale tropospheric circulation features similar to those in ESMs. Notable weaknesses include overestimating the tracks and spatial extent of extratropical cyclones, biases in the teleconnected wave train triggered by tropical SST anomalies, and differences in upper-level warming and stratospheric circulation responses to SST warming compared to physics-based ESMs. The causes of these weaknesses were explored. Despite the noted weaknesses, NeuralGCM reproduces responses across experiments reasonably and performs comparably to ESMs. By integrating a dynamical core with ML, NeuralGCM shows potential for developing ML-based ESMs.

global warming↗
DOE OSTI2025

“Godzilla,” the Extreme African Dust Event of June 2020: Origins, Transport, and Impact on Air Quality in the Greater Caribbean Basin

In June 2020, the tropical Atlantic and the Caribbean Basin were affected by a series of African dust outbreaks unprecedented in size and intensity. These events, informally named “Godzilla,” coincided with CALIMA, a large field campaign, offering a rare opportunity to assess the impact of African dust on air quality in the Greater Caribbean Basin. Network measurements of respirable particles (i.e., PM 10 and PM 2.5 ) showed that dust significantly degraded regional air quality and increased the risk to public health in the Caribbean, the southern United States, northern South America, and Central America. CALIMA examined the meteorological context of Godzilla dust events over North Africa and how these conditions might relate to the greatly increased dust emissions and enhanced transport to the Americas. Godzilla was linked to strong pressure anomalies over West Africa, resulting in a large-scale geostrophic wind anomaly at 700 hPa over North Africa. We used surface-based and columnar measurements to test the performance of two frequently used aerosol forecast models: the NASA Goddard Earth Observing System (GEOS) and Weather Research and Forecasting Model coupled with Chemistry (WRF-Chem) models. The models showed some skills but differed substantially between their forecasts, suggesting large uncertainties in these forecasts that are critical for issuing early warnings of health-threatening dust events. Our results demonstrate the value of an integrated approach in characterizing the spatial and temporal variability of African dust transport and assessing its impact on regional air quality. Future studies are needed to improve models and to track the long-term changes in dust transport from Africa under a changing climate.

Aerosols/particulates↗
NASA NTRS2013

Model Sensitivity to North Atlantic Freshwater Forcing at 8.2 Ka

We compared four simulations of the 8.2 ka event to assess climate model sensitivity and skill in responding to North Atlantic freshwater perturbations. All of the simulations used the same freshwater forcing, 2.5 Sv for one year, applied to either the Hudson Bay (northeastern Canada) or Labrador Sea (between Canada's Labrador coast and Greenland). This freshwater pulse induced a decadal-mean slowdown of 10-25%in the Atlantic Meridional Overturning Circulation (AMOC) of the models and caused a large-scale pattern of climate anomalies that matched proxy evidence for cooling in the Northern Hemisphere and a southward shift of the Intertropical Convergence Zone. The multi-model ensemble generated temperature anomalies that were just half as large as those from quantitative proxy reconstructions, however. Also, the duration of AMOC and climate anomalies in three of the simulations was only several decades, significantly shorter than the duration of approx.150 yr in the paleoclimate record. Possible reasons for these discrepancies include incorrect representation of the early Holocene climate and ocean state in the North Atlantic and uncertainties in the freshwater forcing estimates.

simulation↗
NASA NTRS2022

A New Snow Module Improves Predictions of the Isotope-Enabled MAIDENiso Forest Growth Model

The representation of snow processes in forest growth models is necessary to accurately predict the hydrological cycle in boreal ecosystems and the isotopic signature of soil water extracted by trees, photosynthates and tree-ring cellulose. Yet, most process-based models do not include a snow module; consequently, their simulations may be biased in cold environments. Here, we modified the MAIDENiso model to incorporate a new snow module that simulates snow accumulation, melting and sublimation, as well as thermal exchanges driving freezing and thawing of the snow and the soil. We tested these implementations in two sites in eastern and western Canada for black spruce (Picea mariana (Mill.) B.S.P.) and white spruce (Picea glauca (Moench) Voss) forests, respectively. The new snow module improves the skills of the model to predict components of the hydrological cycle. The MAIDENiso model is now able to reproduce the spring discharge peak and to simulate stable oxygen isotopes in tree-ring cellulose more realistically than in the original snow-free version of the model. The new implementation also results in simulations with a higher contribution from the source water on the oxygen isotopic composition of the simulated cellulose, leading to more accurate estimates of cellulose isotopic composition. Future work may include the development of inverse modelling with this new version of MAIDENiso to produce robust reconstructions of the hydrological cycle and isotope processes in cold environments.

Snow processes↗
NASA NTRS1981

Pursuit tracking and higher levels of skill development in the human pilot

A model of the human pilot is offered for pursuit tracking tasks; the model encompasses an existing model for compensatory tracking. The central hypothesis in the development of this model states that those primary structural elements in the compensatory model responsible for the pilot's equalization capabilities remain intact in the pursuit model. In this latter case, effective low-frequency inversion of the controlled-element dynamics occurs by feeding-forward derived input rate through the equalization dynamics, with low-frequency phase droop minimized. The sharp reduction in low-frequency phase lag beyond that associated with the disappearance of phase droop is seen to accompany relatively low-gain feedback of vehicle output. The results of some recent motion cue research are discussed and interpreted in terms of the compensatory-pursuit display dichotomy. Tracking with input preview is discussed in a qualitative way. In terms of the model, preview is shown to demand no fundamental changes in structure or equalization and to allow the pilot to eliminate the effective time delays that accrue in the inversion of the controlled-element dynamics. Precognitive behavior is discussed, and a model that encompasses all the levels of skill development outlined in the successive organizations of perception theory is finally proposed.

Hess, R. A.↗
NASA NTRS2008

Skill Assessment in Ocean Biological Data Assimilation

There is growing recognition that rigorous skill assessment is required to understand the ability of ocean biological models to represent ocean processes and distributions. Statistical analysis of model results with observations represents the most quantitative form of skill assessment, and this principle serves as well for data assimilation models. However, skill assessment for data assimilation requires special consideration. This is because there are three sets of information in the free-run model, data, and the assimilation model, which uses Data assimilation information from both the flee-run model and the data. Intercom parison of results among the three sets of information is important and useful for assessment, but is not conclusive since the three information sets are intertwined. An independent data set is necessary for an objective determination. Other useful measures of ocean biological data assimilation assessment include responses of unassimilated variables to the data assimilation, performance outside the prescribed region/time of interest, forecasting, and trend analysis. Examples of each approach from the literature are provided. A comprehensive list of ocean biological data assimilation and their applications of skill assessment, in both ecosystem/biogeochemical and fisheries efforts, is summarized.

Gregg, Watson W.↗
DOE OSTI2024

Relating flow resistance to equivalent roughness

Describing flow resistance using the physical properties of an underlying surface is a recalcitrant problem in overland flow models. If discharge measurements are available, an equivalent roughness (e.g., Manning’s n) can be calibrated to represent the effects of surface properties within the domain with a single numerical value. Alternatively, the flow resistance can be estimated from discharge and velocity measured at a point, typically a runoff plot outlet. However, such experimental estimates are often inconsistent with the equivalent roughness determined from calibration to discharge, even if both derive from the same dataset. For example, if Manning’s equation is used to parameterize flow resistance, the Manning’s n obtained by calibrating a model to discharge differs from the value of n calculated from measured flow and velocity at the hillslope outlet. Here, this discrepancy is resolved by deriving a correction factor relating experimentally-determined flow resistance to the equivalent roughness. The derived correction factor is tested for four commonly-used resistance formulations using 129 rainfall simulator experiments. The correction factor is necessary to reproduce measured velocities, and yields minor improvements in discharge prediction. Plain Language Summary: Accurate runoff prediction is needed for land and water management in dryland regions, where sporadic and limited rainfall necessitate efficient water use and drought mitigation strategies. The skill of runoff models is known to be hindered by out ability to estimate flow resistance, which is the quantity that describes how energy is lost from flowing water to the underlying surface. Typically, models represent flow resistance with an equivalent roughness, e.g., Manning’s n, that is adjusted until the model can reproduce available discharge observations at watershed scale. However, the flow resistance measured in plot-scale experiments (1–10 m) often exceeds equivalent roughness coefficients by a factor of 10. This means that the direct use of plot-scale experimental data to parameterize runoff models could cause errors in discharge and runoff velocity predictions. Here, we resolve these differences by deriving an analytic correction factor that relates flow resistance to the equivalent roughness required for models to reproduce experimental velocity and discharge data. This correction factor is tested using rainfall simulator data from 129 experiments performed in the US Southwest covering a wide range of precipitation intensities, soil textures and vegetation types. Use of the correction factor substantially improves model prediction of flow velocity, which is needed for reproducing the timing of flood events and the estimation of erosion.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2013

An Assessment of the Skill of GEOS-5 Seasonal Forecasts

The seasonal forecast skill of the NASA Global Modeling and Assimilation Office coupled global climate model (CGCM) is evaluated based on an ensemble of 9-month lead forecasts for the period 1993 to 2010. The results from the current version (V2) of the CGCM consisting of the GEOS-5 AGM coupled to the MOM4 ocean model are compared with those from an earlier version (V1) in which the AGCM (the NSIPP model) was coupled to the Poseidon Ocean Model. It was found that the correlation skill of the Sea Surface Temperature (SST) forecasts is generally better in V2, especially over the sub-tropical and tropical central and eastern Pacific, Atlantic, and Indian Ocean. Furthermore, the improvement in skill in V2 mainly comes from better forecasts of the developing phase of ENSO from boreal spring to summer. The skill of ENSO forecasts initiated during the boreal winter season, however, shows no improvement in terms of correlation skill, and is in fact slightly worse in terms of root mean square error (RMSE). The degradation of skill is found to be due to an excessive ENSO amplitude. For V1, the ENSO amplitude is too strong in forecasts starting in boreal spring and summer, which causes large RMSE in the forecast. For V2, the ENSO amplitude is slightly stronger than that in observations and V1 for forecasts starting in boreal winter season. An analysis of the terms in the SST tendency equation, shows that this is mainly due to an excessive zonal advective feedback. In addition, V2 forecasts that are initiated during boreal winter season, exhibit a slower phase transition of El Nino, which is consistent with larger amplitude of ENSO after the ENSO peak season. It is found that this is due to weak discharge of equatorial Warm Water Volume (WWV). In both observations and V1, the discharge of equatorial WWV leads the equatorial geostrophic easterly current so as to damp the El Nino starting in January. This process is delayed by about 2 months in V2 due to the slower phase transition of the equatorial zonal current from westerly to easterly.

GMAO↗
DOE OSTI2026

Forced Component Estimation Statistical Method Intercomparison Project (ForceSMIP)

Anthropogenic climate change is unfolding rapidly, yet its regional manifestation can be obscured by internal variability. A primary goal of climate science is to identify the externally forced climate response from among the noise of internal variability. Separating the forced response from internal variability can be addressed in climate models by using a large ensemble to average over different possible realizations of internal variability. However, with only one realization of the real world, it is a major challenge to isolate the forced response directly in observations. In the Forced Component Estimation Statistical Method Intercomparison Project (ForceSMIP), contributors used existing and newly developed statistical and machine learning methods to estimate the forced response over 1950–2022 within individual realizations of the climate system. Participants used neural networks, linear inverse models, fingerprinting methods, and low-frequency component analysis, among other approaches. These methods were trained using large ensembles from multiple climate models and then applied to observations. Here, we evaluate method performance within large ensembles and investigate the estimates of the forced response in observations. Our results show that many different types of methods are skillful for estimating the forced response in climate models, though the relative skill of individual methods varies depending on the variable and evaluation metric. Methods with comparable skill in models can give a wide range of estimates of the forced response pattern in observations, illustrating the epistemic uncertainty in forced response estimates. ForceSMIP gives new insights into the forced response in observations, its uncertainty, and methods for its estimation.

Climate attribution↗
NASA NTRS2018

Assessing Version 4 of the SMAP L4_SM Data Product

Version 4 of the SMAP Level 4 Surface and Root Zone Soil Moisture (L4_SM) product benefits from an improved land surface modeling system. Surface soil moisture is typically drier by several volumetric percent in Version 4 compared to Version 3, whereas root zone soil moisture is wetter in Version 4 in some regions and drier in others. Results from core validation site comparisons show that Version 4 of the L4_SM data product meets the accuracy requirement, which is formulated in terms of the RMSE after removal of the long-term mean difference (ubRMSE). The overall ubRMSE of the 3-hourly L4_SM data at the 9 km scale is 0.039 m3 m-3 for surface soil moisture and 0.029 m3 m-3 for root zone soil moisture, below the 0.04 m3 m-3 requirement. L4_SM surface and root zone soil moisture estimates are more skillful than model-only simulation estimates that are not informed by SMAP brightness temperature observations, with statistically significant improvements at the 5% level for surface soil moisture R and anomaly R values. Results from comparisons of the L4_SM product to in situ measurements from more than 400 sparse network sites corroborate the core validation site results.

Reichle, R.↗
NASA NTRS2017

Simulating PACE Global Ocean Radiances

The NASA PACE mission is a hyper-spectral radiometer planned for launch in the next decade. It is intended to provide new information on ocean biogeochemical constituents by parsing the details of high resolution spectral absorption and scattering. It is the first of its kind for global applications and as such, poses challenges for design and operation. To support pre-launch mission development and assess on-orbit capabilities, the NASA Global Modeling and Assimilation Office has developed a dynamic simulation of global water-leaving radiances, using an ocean model containing multiple ocean phytoplankton groups, particulate detritus, particulate inorganic carbon (PIC), and chromophoric dissolved organic carbon (CDOC) along with optical absorption and scattering processes at 1 nm spectral resolution. The purpose here is to assess the skill of the dynamic model and derived global radiances. Global bias, uncertainty, and correlation are derived using available modern satellite radiances at moderate spectral resolution. Total chlorophyll, PIC, and the absorption coefficient of CDOC (aCDOC), are simultaneously assimilated to improve the fidelity of the optical constituent fields. A 5-year simulation showed statistically significant (P < 0.05) comparisons of chlorophyll (r = 0.869), PIC (r = 0.868), and a CDOC (r =0.890) with satellite data. Additionally, diatoms (r = 0.890), cyanobacteria (r = 0.732), and coccolithophores (r = 0.716) were significantly correlated with in situ data. Global assimilated distributions of optical constituents were coupled with a radiative transfer model (Ocean-Atmosphere Spectral Irradiance Model, OASIM) to estimate normalized water-leaving radiances at 1 nm for the spectral range 250-800 nm. These unassimilated radiances were within 0.074 mW/sq cm/micron/sr of MODIS-Aqua radiances at 412, 443, 488, 531, 547, and 667 nm. This difference represented a bias of 10.4% (model low). A mean correlation of 0.706 (P < 0.05) was found with global distributions of MODIS radiances. These results suggest skill in the global assimilated model and resulting radiances. The reported error characterization suggests that the global dynamical simulation can support some aspects of mission design and analysis. For example, the high spectral resolution of the simulation supports investigations of band selection. The global nature of the radiance representations supports investigations of satellite observing scenarios. Global radiances at bands not available in current and past missions support investigations of mission capability. PACE, ocean color, water-leaving radiances, biogeochemical model, radiative transfer model

PIC↗
NASA NTRS1992

Persistence and predictability in a perfect model

A realistic two-level GCM is used to examine the relationship between predictability and persistence. Predictability is measured by the average divergence of ensembles of solutions starting from perturbed initial conditions, and persistence is defined in terms of the autocorrelation function based on a single long-term model integration. The average skill of the dynamical forecasts is compared with the skill of simple persistence-based statistical forecasts. For initial errors comparable in magnitude to present-day analysis errors, the statistical forecast loses all skill after about one week, reflecting the lifetime of the lowest frequency fluctuations in the model. Large ensemble mean dynamical forecasts would be expected to remain skillful for about 3 wk. The disparity between the skill of the statistical and dynamical forecasts is greater for the higher frequency modes, which have little memory beyond 1 d, yet remain predictable for about 2 wk. The results are analyzed in terms of two characteristic time scales.

Schubert, Siegfried D.↗
NASA NTRS2007

Lessons Learned from Deploying an Analytical Task Management Database

Defining requirements, missions, technologies, and concepts for space exploration involves multiple levels of organizations, teams of people with complementary skills, and analytical models and simulations. Analytical activities range from filling a To-Be-Determined (TBD) in a requirement to creating animations and simulations of exploration missions. In a program as large as returning to the Moon, there are hundreds of simultaneous analysis activities. A way to manage and integrate efforts of this magnitude is to deploy a centralized database that provides the capability to define tasks, identify resources, describe products, schedule deliveries, and generate a variety of reports. This paper describes a web-accessible task management system and explains the lessons learned during the development and deployment of the database. Through the database, managers and team leaders can define tasks, establish review schedules, assign teams, link tasks to specific requirements, identify products, and link the task data records to external repositories that contain the products. Data filters and spreadsheet export utilities provide a powerful capability to create custom reports. Import utilities provide a means to populate the database from previously filled form files. Within a four month period, a small team analyzed requirements, developed a prototype, conducted multiple system demonstrations, and deployed a working system supporting hundreds of users across the aeros pace community. Open-source technologies and agile software development techniques, applied by a skilled team enabled this impressive achievement. Topics in the paper cover the web application technologies, agile software development, an overview of the system's functions and features, dealing with increasing scope, and deploying new versions of the system.

O'Neil, Daniel A.↗
NASA NTRS2020

Prediction Skill of the 2012 U.S. Great Plains Flash Drought in Subseasonal Experiment (SubX) Models

Flash droughts refer to droughts that develop much more rapidly than normal (i.e., on the order of weeks to a few months). Such droughts can have devastating impacts on agriculture, water resources, and ecosystems. The ability to predict flash droughts in advance would greatly enhance our preparation for them and potentially mitigate their impacts. We investigated the prediction skill of U.S. flash droughts at subseasonal lead times in global forecast systems participating in the Subseasonal Experiment (SubX) project. An additional comprehensive set of hindcasts with NASA?s GEOSv2.1, a model with relatively high prediction skill, was performed to investigate the separate contributions of atmospheric and land initial conditions to flash drought prediction skill. Here we focus on results for the 2012 Great Plains flash drought, noting that the findings based on this event are generally applicable to other U.S. flash droughts. The prediction skill of the SubX models is quite variable. While the skill is limited to less than 2 weeks in most models, it is considerably higher (3-4 weeks or more) for certain models and initialization dates. The enhanced prediction skill is found to originate from two robust sources: 1) accurate soil moisture initialization, and 2) the satisfactory representation of quasi-stationary cross-North Pacific Rossby wave trains that lead to the rapid intensification of flash droughts. Our results corroborate earlier findings that accurate soil moisture initialization is important for skillful subseasonal forecasts and highlight the need for additional research on the sources and predictability of drought-inducing quasi-stationary Rossby waves.

DeAngelis, Anthony M.↗
DOE OSTI2025

Complementing Dynamical Downscaling With Super‐Resolution Convolutional Neural Networks

Despite advancements in Artificial Intelligence (AI) methods for climate downscaling, significant challenges remain for their practicality in climate research. Current AI-methods exhibit notable limitations, such as limited application in downscaling Global Climate Models (GCMs), and accurately representing extremes. To address these challenges, we implement an AI-based methodology using super-resolution convolutional neural networks (SRCNN), trained and evaluated on 40 years of daily precipitation data from a reanalysis and a high-resolution dynamically downscaled counterpart. The dynamical downscaled simulations, constrained using spectral nudging, enable the replication of historical events at a higher resolution. This allows the SRCNN to emulate dynamical downscaling effectively. Modifications, such as incorporating elevation data and data pre-processing enhances overall model performance, while using exponential and quantile loss functions improve the simulation of extremes. Our findings show SRCNN models efficiently and skillfully downscale precipitation from GCMs. Future work will expand this methodology to downscale additional variables for future climate projections.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1992

Adaptive filtering and prediction of the Southern Oscillation index

Singular spectrum analysis (SSA), a variant of principal component analysis, is applied to a time series of the Southern Oscillation index (SOI). The analysis filters out variability unrelated to the Southern Oscillation and separates the high-frequency, 2- to 3-year variability, including the quasi-biennial oscillation, from the lower-frequency 4- to 6-year El Nino cycle. The maximum entropy method (MEM) is applied to forecasting the prefiltered SOI. Prediction based on MEM-associated autoregresive models has useful skill for 30-36 months. A 1993-1994 La Nina event is predicted based on data through February 1992.

Keppenne, Christian L.↗