Search NASA⌕ Search

SEARCH · Search NASA

Results for “forecast accuracy”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

A new method for inferring city emissions and lifetimes of nitrogen oxides from high-resolution nitrogen dioxide observations: a model study

We present a new method to infer emissions and lifetimes of nitrogen oxides (NO x ) based on tropospheric nitrogen dioxide (NO 2 ) observations together with reanalysis wind fields for cities located in polluted backgrounds. Since the accuracy of the method is difficult to assess due to lack of “true values” that can be used as a benchmark, we apply the method to synthetic NO 2 observations derived from the NASA-Unified Weather Research and Forecasting (NU-WRF) model at a high horizontal spatial resolution of 4 km × 4 km for cities over the continental United States. We compare the inferred emissions and lifetimes with the values given by the NU-WRF model to evaluate the method. The method is applicable to 26 US cities. The derived results are generally in good agreement with the values given by the model, with the relative differences of 2 % ± 17 % (mean ± standard deviation) and 15 % ± 25 % for lifetimes and emissions, respectively. Our investigation suggests that the use of wind data prior to the satellite overpass time improves the performance of the method. The correlation coefficients between inferred and NU-WRF lifetimes increase from 0.56 to 0.79 and for emissions increase from 0.88 to 0.96 when comparing results based on wind fields sampled simultaneously with satellite observations and averaged over 9 h data prior to satellite observations, respectively. We estimate that uncertainties in NO x lifetime and emissions arising from the method are approximately 15 % and 20 %, respectively, for typical (US) cities. The total uncertainties reach up to 43% (lifetimes) and 45% (emissions) by considering the additional uncertainties associated with satellite NO 2 observations and wind data. We expect this new method to be applicable to NO 2 observations from the TROPOspheric Monitoring Instrument (TROPOMI) and geostationary satellites, such as Geostationary Environment Monitoring Spectrometer (GEMS) or the Tropospheric Emissions: Monitoring Pollution (TEMPO) instrument, to estimate urban NO x emissions and lifetimes globally.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Real-Time Regional PV Spinning Reserve Estimator with AGC Look-Ahead Windows

Curtailed PV generation is a zero-marginal cost spinning reserve that can be used for a number of active power control services. However, unlike the traditional spinning reserve providers, i.e., fossil-fueled generators, who have well-defined operating characteristics, e.g., available headroom or potential high limit (PHL), PV plants have by nature variable and uncertain operating characteristics. To ensure the effective coordination between PV plants and the system operator during an active power control event, accurate forecasts of the PV PHL are essential. A novel reference-control grouping based scaling method has been proposed by NREL to estimate the PV PHL in real-time. This work further enhances the methodology by: 1) improving the model accuracy through machine learning; 2) considering look-ahead windows introduced by the computation and communication latencies; 3) applying the method to regional spinning reserve estimation. A significant performance improvement, over 99% of estimation error reduction, has been observed based on real-world data collected by CAISO and PV plant operators.

potential high limit↗
DOE OSTI2023

Real-Time Regional PV Spinning Reserve Estimator with AGC Look-Ahead Windows: Preprint

Curtailed PV generation is a zero-marginal cost spinning reserve that can be used for a number of active power control services. However, unlike the traditional spinning reserve providers, i.e., fossil-fueled generators, who have well-defined operating characteristics, e.g., available headroom or potential high limit (PHL), PV plants have by nature variable and uncertain operating characteristics. To ensure the effective coordination between PV plants and the system operator during an active power control event, accurate forecasts of the PV PHL are essential. A novel reference-control grouping based scaling method has been proposed by NREL to estimate the PV PHL in real-time. This work further enhances the methodology by: 1) improving the model accuracy through machine learning; 2) considering look-ahead windows introduced by the computation and communication latencies; 3) applying the method to regional spinning reserve estimation. A significant performance improvement, over 1.6% of estimation error reduction, has been observed based on real-world data collected by CAISO and PV plant operators.

potential high limit↗
DOE OSTI2021

AI-Improved Resolution Projections of Population Characteristics and Imperviousness Can Improve Resolution and Accuracy of Urban Flood Predictions

Focal Area: (2) Predictive modeling through the use of AI techniques and AI-derived model components. Specifically, we call for the use of deep generative models from ML for providing high-resolution projections of impervious surface area, as well as neural network solvers for fast approximation of urban hydrodynamics to provide greatly enhanced forecasts of future urban flood dynamics.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Assessing shellfish water exposure to fecal bacteria pollution in Salish Sea: three-dimensional modeling and implications for monitoring

Fecal bacteria (FB) contamination poses significant risks to shellfish safety and management in coastal and estuarine waters. Despite extensive pollution identification and correction efforts, FB contamination in shellfish-growing areas persists in the Salish Sea, highlighting the need to identify overlooked sources and better understand FB transport from riverine and shoreline inputs to shellfish beds. To address this, a high-resolution three-dimensional hydrodynamic model coupled with FB kinetics was developed and applied to a case study site in Salish Sea—Portage Bay—to simulate freshwater plume circulation, flushing dynamics, and bacterial transport. Daily FB loading from the major freshwater inflow—Nooksack River was generated by both linear interpolation and integrating a machine learning approach (XGBoost), trained on historical hydrological and meteorological data. The model successfully reproduced both the magnitude and seasonal variation of FB concentrations in Portage Bay for the year of 2021, demonstrating that simplified FB kinetics with first-order decay due to mortality was effective in this dynamic coastal environment with short flushing time. Model results identified the Nooksack River as the dominant far-field FB source, while scenario simulations showed that near-field coastal stormwater outfalls elevated local FB levels following rainfall, particularly under low-flow conditions. The XGBoost prediction provided comparable or superior accuracy to linear interpolation, particularly during periods of missing observational data, by capturing short-term variability and event-driven loading more effectively. Integrating data-driven riverine FB inputs with mechanistic coastal numerical modeling provides a robust framework for operational forecasting of shellfish bed exposure risk and supports adaptive monitoring and management of shellfish growing areas in the Salish Sea and similar coastal systems.

Salish Sea↗
DOE OSTI2023

Frost prediction using machine learning and deep neural network models

This study describes accurate, computationally efficient models that can be implemented for practical use in predicting frost events for point-scale agricultural applications. Frost damage in agriculture is a costly burden to farmers and global food security alike. Timely prediction of frost events is important to reduce the cost of agricultural frost damage and traditional numerical weather forecasts are often inaccurate at the field-scale in complex terrain. In this paper, we developed machine learning (ML) algorithms for the prediction of such frost events near Alcalde, NM at the point-scale. ML algorithms investigated include deep neural network, convolution neural networks, and random forest models at lead-times of 6–48 h. Our results show promising accuracy (6-h prediction RMSE = 1.53–1.72°C) for use in frost and minimum temperature prediction applications. Seasonal differences in model predictions resulted in a slight negative bias during Spring and Summer months and a positive bias in Fall and Winter months. Additionally, we tested the model transferability by continuing training and testing using data from sensors at a nearby farm. We calculated the feature importance of the random forest models and were able to determine which parameters provided the models with the most useful information for predictions. We determined that soil temperature is a key parameter in longer term predictions (>24 h), while other temperature related parameters provide the majority of information for shorter term predictions. The model error compared favorable to previous ML based frost studies and outperformed the physically based High Resolution Rapid Refresh forecasting system making our ML-models attractive for deployment toward real-time monitoring of frost events and damage at commercial farming operations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

STRIDES: automated uniform models for 30 quadruply imaged quasars

ABSTRACT Gravitational time delays provide a powerful one-step measurement of H0, independent of all other probes. One key ingredient in time-delay cosmography are high-accuracy lens models. Those are currently expensive to obtain, both, in terms of computing and investigator time (105–106 CPU hours and ∼0.5–1 yr, respectively). Major improvements in modelling speed are therefore necessary to exploit the large number of lenses that are forecast to be discovered over the current decade. In order to bypass this roadblock, we develop an automated modelling pipeline and apply it to a sample of 31 lens systems, observed by the Hubble Space Telescope in multiple bands. Our automated pipeline can derive models for 30/31 lenses with few hours of human time and <100 CPU hours of computing time for a typical system. For each lens, we provide measurements of key parameters and predictions of magnification as well as time delays for the multiple images. We characterize the cosmography-readiness of our models using the stability of differences in the Fermat potential (proportional to time delay) with respect to modelling choices. We find that for 10/30 lenses, our models are cosmography or nearly cosmography grade (<3 per cent and 3–5 per cent variations). For 6/30 lenses, the models are close to cosmography grade (5–10 per cent). These results utilize informative priors and will need to be confirmed by further analysis. However, they are also likely to improve by extending the pipeline modelling sequence and options. In conclusion, we show that uniform cosmography grade modelling of large strong lens samples is within reach.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

OperonSEQer: A set of machine-learning algorithms with threshold voting for detection of operon pairs using short-read RNA-sequencing data

Operon prediction in prokaryotes is critical not only for understanding the regulation of endogenous gene expression, but also for exogenous targeting of genes using newly developed tools such as CRISPR-based gene modulation. A number of methods have used transcriptomics data to predict operons, based on the premise that contiguous genes in an operon will be expressed at similar levels. While promising results have been observed using these methods, most of them do not address uncertainty caused by technical variability between experiments, which is especially relevant when the amount of data available is small. In addition, many existing methods do not provide the flexibility to determine the stringency with which genes should be evaluated for being in an operon pair. We present OperonSEQer, a set of machine learning algorithms that uses the statistic and p-value from a non-parametric analysis of variance test (Kruskal-Wallis) to determine the likelihood that two adjacent genes are expressed from the same RNA molecule. We implement a voting system to allow users to choose the stringency of operon calls depending on whether your priority is high recall or high specificity. In addition, we provide the code so that users can retrain the algorithm and re-establish hyperparameters based on any data they choose, allowing for this method to be expanded as additional data is generated. We show that our approach detects operon pairs that are missed by current methods by comparing our predictions to publicly available long-read sequencing data. OperonSEQer therefore improves on existing methods in terms of accuracy, flexibility, and adaptability.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Meeting Global Health Needs via Infectious Disease Forecasting: Development of a Reliable Data-Driven Framework

Infectious diseases (IDs) have a significant detrimental impact on global health. Timely and accurate ID forecasting can result in more informed implementation of control measures and prevention policies. To meet the operational decision-making needs of real-world circumstances, we aimed to build a standardized, reliable, and trustworthy ID forecasting pipeline and visualization dashboard that is generalizable across a wide range of modeling techniques, IDs, and global locations. We forecasted 6 diverse, zoonotic diseases (brucellosis, campylobacteriosis, Middle East respiratory syndrome, Q fever, tick-borne encephalitis, and tularemia) across 4 continents and 8 countries. We included a wide range of statistical, machine learning, and deep learning models (n=9) and trained them on a multitude of features (average n=2326) within the One Health landscape, including demography, landscape, climate, and socioeconomic factors. The pipeline and dashboard were created in consideration of crucial operational metrics—prediction accuracy, computational efficiency, spatiotemporal generalizability, uncertainty quantification, and interpretability—which are essential to strategic data-driven decisions. While no single best model was suitable for all disease, region, and country combinations, our ensemble technique selects the best-performing model for each given scenario to achieve the closest prediction. For new or emerging diseases in a region, the ensemble model can predict how the disease may behave in the new region using a pretrained model from a similar region with a history of that disease. The data visualization dashboard provides a clean interface of important analytical metrics, such as ID temporal patterns, forecasts, prediction uncertainties, and model feature importance across all geographic locations and disease combinations. As the need for real-time, operational ID forecasting capabilities increases, this standardized and automated platform for data collection, analysis, and reporting is a major step forward in enabling evidence-based public health decisions and policies for the prevention and mitigation of future ID outbreaks.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Evaluation and Intercomparison of Small Uncrewed Aircraft Systems Used for Atmospheric Research

Abstract Small uncrewed aircraft systems (sUAS) are regularly being used to conduct atmospheric research and are starting to be used as a data source for informing weather models through data assimilation. However, only a limited number of studies have been conducted to evaluate the performance of these systems and assess their ability to replicate measurements from more traditional sensors such as radiosondes and towers. In the current work, we use data collected in central Oklahoma over a 2-week period to offer insight into the performance of five different sUAS platforms and associated sensors in measuring key weather data. This includes data from three rotary-wing and two fixed-wing sUAS and included two commercially available systems and three university-developed research systems. Flight data were compared to regular radiosondes launched at the flight location, tower observations, and intercompared with data from other sUAS platforms. All platforms were shown to measure atmospheric state with reasonable accuracy, though there were some consistent biases detected for individual platforms. This information can be used to inform future studies using these platforms and is currently being used to provide estimated error covariances as required in support of assimilation of sUAS data into weather forecasting systems.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

A Digital Twin Framework Utilizing Machine Learning for Robust Predictive Maintenance: Enhancing Tire Health Monitoring

We introduce a novel digital twin (DT) framework for the predictive maintenance of long-term physical systems. Using monitoring tire health as an application, we show how the DT framework can be used to enhance automotive safety and efficiency, and how the technical challenges can be overcome using a three-step approach. First, to manage the data complexity over a long operation span, we employ data reduction techniques to concisely represent physical tires using historical performance and usage data. Relying on these data, for fast real-time prediction, we train a transformer-based model offline on our concise dataset to predict future tire health over time, represented as remaining casing potential (RCP). Based on our architecture, our model quantifies both epistemic and aleatoric uncertainties, providing reliable confidence intervals around predicted RCP. Second, to incorporate real-time data, we update the predictive model in the DT framework, ensuring its accuracy throughout its lifespan with the aid of hybrid modeling and the use of the discrepancy function. Third, to assist decision-making in predictive maintenance, we implement a tire state decision algorithm, which strategically determines the optimal timing for tire replacement based on RCP forecasted by our transformer model. This approach ensures that our DT accurately predicts system health, continually refines its digital representation, and supports predictive maintenance decisions. Furthermore, our framework effectively embodies a physical system, leveraging big data and machine learning (ML) for predictive maintenance, model updates, and decision-making.

advanced computing infrastructure↗
DOE OSTI2024

Tilted lidar profiling: Development and testing of a novel scanning strategy for inhomogeneous flows

The most common profiling techniques for the atmospheric boundary layer based on a monostatic Doppler wind lidar rely on the assumption of horizontal homogeneity of the flow. This assumption breaks down in the presence of either natural or human-made obstructions that can generate significant flow distortions. The need to deploy ground-based lidars near operating wind turbines for the American WAKE experimeNt (AWAKEN) spurred a search for novel profiling techniques that could avoid the influence of the flow modifications caused by the wind farms. With this goal in mind, two well-established profiling scanning strategies have been retrofitted to scan in a tilted fashion and steer the beams away from the more severely inhomogeneous region of the flow. Results from a field test at the National Renewable Energy Laboratory's 135-m meteorological tower show that the accuracy of the horizontal mean flow reconstruction is insensitive to the tilt of the scan, although higher-order wind statistics are severely deteriorated at extreme tilts mainly due to geometrical error amplification. A numerical study of the AWAKEN domain based on the Weather Research and Forecasting Model and large-eddy simulation are also conducted to test the effectiveness of tilted profiling. It is shown that a threefold reduction of the error on inflow mean wind speed can be achieved for a lidar placed at the base of the turbine using tilted profiling.

17 WIND ENERGY↗
DOE OSTI2021

Impact of Aerosol and Cloud on the Solar Energy Potential over the Central Gangetic Himalayan Region

We examine the impact of atmospheric aerosols and clouds on the surface solar radiation and solar energy at Nainital, a high-altitude remote location in the central Gangetic Himalayan region (CGHR). For this purpose, we exploited the synergy of remote-sensed data in terms of ground-based AERONET Sun Photometer and satellite observations from the MODerate Resolution Imaging Spectroradiometer (MODIS) and the Meteosat Second Generation (MSG), with radiative transfer model (RTM) simulations and 1 day forecasts from the Copernicus Atmosphere Monitoring Service (CAMS). Clouds and aerosols are one of the most common sources of solar irradiance attenuation and hence causing performance issues in the photovoltaic (PV) and concentrated solar power (CSP) plant installations. The outputs of RTM results presented with high accuracy under clear, cloudy sky and dust conditions for global horizontal (GHI) and beam horizontal irradiance (BHI). On an annual basis the total aerosol attenuation was found to be up to 105 kWh m –2 for the GHI and 266 kWh m –2 for BHI, respectively, while the cloud effect is much stronger with an attenuation of 245 and 271 kWh m –2 on GHI and BHI. The results of this study will support the Indian solar energy producers and electricity handling entities in order to quantify the energy and financial losses due to cloud and aerosol presence.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Sensitivity of Regional WRF‐Chem Air Quality and Weather Simulations to Biomass‐Burning Emission Data Sets: A Case Study of the Impact of Canadian Wildfire on the US°

This study focuses on the period from June 26 to 29, 2023, when record‐breaking Canadian wildfires severely impacted air quality in the Midwest United States. Using the Weather Research and Forecasting Model with Chemistry (WRF‐Chem) and four biomass‐burning data sets (Fire Inventory from NCAR version 1, Fire Inventory from NCAR version 2.5, Quick Fire Emissions Data set [QFED], and Regional ABI‐VIIRS Emission), we analyzed aerosol transport from Canada to the US and assessed the model's accuracy in predicting PM 2.5 , O 3 , CO and aerosol weather feedback. Model simulations were compared with ground‐based and remote sensing observations as well as field measurements from the Community Research on Climate and Urban Science (CROCUS) project. Our findings show that the movement of a low‐pressure system from the Great Lakes to the Atlantic, combined with the high‐pressure system over the Atlantic, caused the transport of aerosols from Canadian wildfires to the US. Results show WRF‐Chem significantly underestimated key atmospheric components: aerosol optical depth (AOD) by over 50%, PM 2.5 by 65%–90% and peak O 3 concentrations by 50%–55% across four biomass burning data sets. Additionally, CO and NO 2 concentrations were underpredicted. The substantial underestimation of PM 2.5 led to an overestimation of temperature by up to 3.6 °C primarily due to excessive downward shortwave radiation, which resulted from the underestimation of direct aerosol effects and an increase in sensible heat flux. Among the biomass‐burning data sets, QFED produced the most accurate AOD and PM 2.5 predictions due to improved wildfire emission estimates, leading to a 1.0 to 1.5 °C reduction in temperature overestimation during the daytime. These findings underscore the need for improving wildfire emission estimates for trace gases and aerosols to enhance air quality and weather feedback predictions.

WRF-chem model↗
DOE OSTI2024

Deep Learning-Based Weather-Related Power Outage Prediction with Socio-Economic and Power Infrastructure Data

This paper presents a deep learning-based approach for hourly power outage probability prediction within census tracts encompassing a utility company's service territory. Two distinct deep learning models, conditional Multi-Layer Perceptron (MLP) and unconditional MLP, were developed to forecast power outage probabilities, leveraging a rich array of input features gathered from publicly available sources including weather data, weather station locations, power infrastructure maps, socio-economic and demographic statistics, and power outage records. Given a one-hour-ahead weather forecast, the models predict the power outage probability for each census tract, taking into account both the weather prediction and the location's characteristics. The deep learning models employed different loss functions to optimize prediction performance. Our experimental results underscore the significance of socio-economic factors in enhancing the accuracy of power outage predictions at the census tract level.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

High-Resolution Wind Resource Data Set of the Greater Puerto Rico Region

In February 2022, the U.S. Department of Energy and six national laboratories launched the Puerto Rico Grid Resilience and Transitions to 100% Renewable Energy Study (PR100). PR100 aims to provide a comprehensive analysis of possible pathways for Puerto Rico's energy future, with a goal of 100% renewable energy by 2050. As a part of the renewable energy potential assessment in this project, we developed 20 years (2001-2020) of data using a numerical weather prediction (NWP) model for onshore and offshore wind resource assessment for the Puerto Rico. The research steps in developing the long-term wind resource data sets based on the NWP model were: 1. Model wind resource based on the Weather Research and Forecasting (WRF) model. 2. Develop WRF model configurations for Puerto Rico. 3. Test WRF with 11 different physics parameterizations for planetary boundary layer (PBL). 4. Assess WRF output from the different PBL schemes against observations. 5. Select a final model configuration which can produce the modeled wind speed with sufficient accuracy. 6. Produce 20 years wind resource data sets for Puerto Rico region. In the first stage of our framework for developing wind resource data, we developed a WRF model configuration using two nested domains (9 km and 3 km) to cover Puerto Rico and U.S. Virgin Islands and downscale the ERA5 reanalysis data (0.25 degrees x 0.25 degrees; hourly interval) to a 3-km domain. For the second stage, we implemented one-year simulations focused on using 11 different PBL physics parameterizations to find a combination of WRF physics parameterizations that could provide accurately modeled wind speed for Puerto Rico. We also analyzed the sensitivity of the modeled wind speed to PBL schemes for onshore and offshore locations. The WRF output resulting from the 11 WRF experiments using different PBL parameterizations were evaluated against observations obtained from the National Data Buoy Center (NDBC) as well as at hub height for a location for which measurements were available. A final model setup selected through the validation with observational data was used to produce 20 years of data with 3-km spatial and 5-minute temporal resolution. The WRF model output was post-processed to include wind profiles and basic atmospheric variables in a format that can be easily used for downstream modeling. The 20 years of wind resource data will be made available through NREL and support the estimation of wind energy development costs for the PR100 study.

17 WIND ENERGY↗
DOE OSTI2026

Hurricane wind field representation shapes storm surge and building-scale flood hazard estimates

Coastal flood hazard estimates rely on precise hurricane wind forecasts to assess damage and risk. Here, we demonstrate that errors in hurricane wind field representation can lead to significant biases in storm surge and property-level damage estimates. Using Hurricane Ian (2022) as a case study, we compare widely used parametric, reanalysis, and hybrid wind datasets. Improved wind field accuracy reduces storm surge and damage estimate bias by up to 70\%. Our results underscore the importance of accurately predicting hurricane wind structure in hazard assessments.

Coastal Flooding↗
DOE OSTI2021

A composite likelihood approach for inference under photometric redshift uncertainty

ABSTRACT Obtaining accurately calibrated redshift distributions of photometric samples is one of the great challenges in photometric surveys like LSST, Euclid, HSC, KiDS, and DES. We present an inference methodology that combines the redshift information from the galaxy photometry with constraints from two-point functions, utilizing cross-correlations with spatially overlapping spectroscopic samples, and illustrate the approach on CosmoDC2 simulations. Our likelihood framework is designed to integrate directly into a typical large-scale structure and weak lensing analysis based on two-point functions. We discuss efficient and accurate inference techniques that allow us to scale the method to the large samples of galaxies to be expected in LSST. We consider statistical challenges like the parametrization of redshift systematics, discuss and evaluate techniques to regularize the sample redshift distributions, and investigate techniques that can help to detect and calibrate sources of systematic error using posterior predictive checks. We evaluate and forecast photometric redshift performance using data from the CosmoDC2 simulations, within which we mimic a DESI-like spectroscopic calibration sample for cross-correlations. Using a combination of spatial cross-correlations and photometry, we show that we can provide calibration of the mean of the sample redshift distribution to an accuracy of at least 0.002(1 + z), consistent with the LSST-Y1 science requirements for weak lensing and large-scale structure probes.

(cosmology:) large-scale structure of Universe↗