Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “forecast error”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Diagnosing Near-Surface Model Errors with Candidate Physics Parameterization Schemes for the Multiphysics Rapid Refresh Forecast System (RRFS) Ensemble during Winter over the Northeastern United States and Southern Great Plains

Abstract During the winter of 2020/21 an ensemble of FV3-LAM forecasts was produced over the contiguous United States for the Winter Weather Experiment using five physics suites. These forecasts are evaluated with the goal of optimizing physics parameterizations within the future operational Rapid Refresh Forecast System (RRFS) in the Unified Forecast System (UFS) realm and for selecting suitable physics suites for a multiphysics RRFS ensemble. The five physics suites have different combinations of land surface models (LSMs), planetary boundary layer (PBL) parameterizations, and surface layer schemes, chosen from those used in current and possible future operational systems and likely to be supported in the operational UFS. Full-season evaluation reveals a persistent near-surface cold bias in the U.S. Northeast from one suite and a nighttime warm bias in the southern Great Plains in another suite, while other suites have smaller biases. A representative case is chosen to diagnose the cause for each of these biases using sensitivity simulations with different physics combinations or modified parameters and verified with additional mesonet observations. The cold bias in the Northeast is attributed to aspects of the Noah-MP LSM over snow cover, where Noah-MP simulates lower soil water content, and thus lower thermal conductivity than other LSMs, leading to less upward ground heat flux during nighttime and consequently lower surface temperature. The nighttime warm bias found in the southern Great Plains is attributed to overestimation of vertical mixing in the K -profile-based eddy-diffusivity mass-flux (K-EDMF) PBL scheme and insufficient land–atmospheric coupling from the GFS surface layer scheme over short vegetation. A few key parameters driving these systematic biases are identified.

Meteorology & Atmospheric Sciences↗
DOE OSTI2025

Generalized framework for likelihood-based field-level inference of growth rate from velocity and density fields

Measuring the growth rate of large-scale structures ( f ) as a function of redshift has the potential to break degeneracies between modified gravity and dark energy models, when combined with expansion-rate probes. Direct estimates of peculiar velocities of galaxies have attracted interest as a means of estimating fσ 8 . In particular, field-level methods can be used to fit the field nuisance parameter along with cosmological parameters simultaneously. This article aims to provide the community with a unified framework for the theoretical modeling of the likelihood-based field-level inference by performing fast field covariance calculations for velocity and density fields. Our purpose is to lay the foundations for a nonlinear extension of the likelihood-based method at the field level. We have developed a generalized framework, implemented in the dedicated software flip to perform a likelihood-based inference of fσ 8 . We derived a new field covariance model, which includes wide-angle corrections. We also included the models previously described in the literature inside our framework. We compared their performance against ours, and we validated our model by comparing it with the two-point statistics of a recent N-body simulation. The tests we performed have allowed us to validate our software and determine the appropriate wavenumber range to integrate our covariance model and its validity in terms of separation. Our framework allows for a wider wavenumber coverage to be used in our calculations than in previous works, which is particularly interesting for nonlinear model extensions. Finally, our generalized framework allows us to efficiently perform a survey geometry-dependent Fisher forecast of the fσ 8 parameter. We show that the Fisher forecast method we developed gives an error bar that is 30% closer to a full likelihood-based estimation than a standard volume Fisher forecast.

Ravoux, Corentin↗
DOE OSTI2025

Transformers and Long Short-Term Memory Transfer Learning for GenIV Reactor Temperature Time Series Forecasting

Automated monitoring of the coolant temperature can enable autonomous operation of generation IV reactors (GenIV), thus reducing their operating and maintenance costs. Automation can be accomplished with machine learning (ML) models trained on historical sensor data. However, the performance of ML usually depends on the availability of large amount of training data, which is difficult to obtain for GenIV, as this technology is still under development. We propose the use of transfer learning (TL), which involves utilizing knowledge across different domains, to compensate for this lack of training data. TL can be used to create pre-trained ML models with data from small-scale research facilities, which can then be fine-tuned to monitor GenIV reactors. In this work, we develop pre-trained Transformer and long short-term memory (LSTM) networks by training them on temperature measurements from thermal hydraulic flow loops operating with water and Galinstan fluids at room temperature at Argonne National Laboratory. The pre-trained models are then fine-tuned and re-trained with minimal additional data to perform predictions of the time series of high temperature measurements obtained from the Engineering Test Unit (ETU) at Kairos Power. The performance of the LSTM and Transformer networks is investigated by varying the size of the lookback window and forecast horizon. The results of this study show that LSTM networks have lower prediction errors than Transformers, but LSTM errors increase more rapidly with increasing lookback window size and forecast horizon compared to the Transformer errors.

LSTM↗
DOE OSTI2023

Machine Learning–Adjusted WRF Forecasts to Support Wind Energy Needs in Black Start Operations

Abstract The push for increased capacity of renewable sources of electricity has led to the growth of wind-power generation, with a need for accurate forecasts of winds at hub height. Forecasts for these levels were uncommon until recently, and that, combined with the nocturnal collapse of the well-mixed boundary layer and daytime growth of the boundary layer through the levels important for energy generation, has contributed to errors in numerical modeling of wind generation resources. The present study explores several machine learning algorithms to both forecast and correct standard WRF Model forecasts of winds and temperature at hub height within wind turbine plants over several different time periods that are critical for the anticipation of potential blackouts and aiding in black start operations on the power grid. It was found that mean square error for day-2 wind forecasts from the WRF Model can be improved by over 90% with the use of a multioutput neural network, and that 60-min forecasts of WRF error, which can then be used to adjust forecasts, can be made with an LSTM with great accuracy. Nowcasting of temperature and wind speed over a 10-min period using an LSTM produced very low error and especially skillful forecasts of maximum and minimum values over the turbine plant area.

17 WIND ENERGY↗
DOE OSTI2023

Forecasting Day-Ahead Solar Irradiance for Puerto Rico Using the WRF Model and NSRDB

Accurately predicting solar energy resources is a major challenge in integrating photovoltaics generation on the electric grid. Numerical weather prediction has been recognized by the solar energy community as a major approach to provide solar resource forecasts at various locations and for a variety of timescales. In this study, as a part of the Puerto Rico Grid Resilience and Transitions to 100% Renewable Energy Study (PR100), we develop day-head solar irradiance forecast data using the Weather Research and Forecasting (WRF) model at 3 km and hourly/5-minute. The global horizontal irradiance (GHI) and direct normal irradiance (DNI) forecasts simulated from the WRF model are postprocessed by a simple optimization method using satellite-derived gridded observations from the National Solar Radiation Data Base (NSRDB) to reduce error and bias of the solar irradiance forecasts covering 2018-2020. The NSRDB contributes to improving the GHI and DNI forecasts and also offers the opportunity for an in-depth analysis to evaluate their accuracy over a wide range of Puerto Rico regions. Preliminary results show overall improvements of GHI forecasts up to 37% (DNI: 15%) for mean absolute error and 97% (DNI: 76%) for mean bias error by applying a postprocessing technique to WRF model output.

data models↗
DOE OSTI2025

A cross-dimensional analysis of data-driven short-term load forecasting methods with large-scale smart meter data

Electricity load forecasting is essential to utility operation and power grid stability. A wide spectrum of data-driven methods, ranging from linear regression models to more recent deep learning models have been adopted to forecast electric load over the years. However, there still lacks a holistic evaluation of the applicability of conventional statistical and machine learning based algorithms with respect to different temporal and spatial scopes, computational requirements, and sensitivity of model-tuning. Enabled by a large-scale electricity load profile dataset of over 40,000 residential customers in a utility region, we conducted a cross-dimensional analysis of data-driven load forecasting methods. Three regression-based and seven deep learning algorithms with different model configurations were evaluated in terms of their overall and peak load prediction accuracy, and training burdens, across spatial aggregation levels ranging from the transformer, feeder, substation, to neighborhood. We found, first, the load forecasting accuracy is constrained by a predictability boundary, influenced by the forecasting horizon and spatial aggregation level. Specifically, RandomForest, XGBoost, TFT, TSMixer, and TiDE models achieved less than 10 % prediction error for up to 96-h ahead forecasting for district, substation, and feeder levels, while other models struggle at long-horizon predictions; Second, for winter and summer peak load dates, most models were able to predict the peak demand timing within ± 1 h, but the prediction percentage error varied by models, with TFT and TiDE models being the top performers; Third, models with similar prediction accuracy can differ in training burden by an order of magnitude. Therefore, choosing model configurations that balance prediction performance and computational resource is an important practical consideration for large-scale deployment of the machine learning based load forecasting. The outcome of this study can guide researchers and practitioners to choose the proper load forecasting algorithms based on their problem scope, required accuracy, and available resources. The predictability boundary can serve as a benchmark for electricity load forecasting problems with new algorithms and datasets.

Li, Han↗
DOE OSTI2023

Modeling the 4D discharge of lithium-ion batteries with a multiscale time-dependent deep learning framework

The lithium-ion battery (LIB) field is moving towards the direction of investigating spatially resolved physical phenomena in the 3D porous microstructure of electrodes. These pore-scale simulations give new insights into the local dynamics of lithiation/de-lithiation and charge transport, Nevertheless, the computational time of these simulations limits the integration of these models in optimization workflows of cycling conditions or electrode manufacturing processes. Machine learning models present a way of assessing in real-time the performance of materials. While several successful techniques for replicating simulations with machine learning have been proposed, this case study presents a more demanding problem, due to the necessity of understanding the behavior of heterogeneous 3D local data, as it evolves in time: this poses both a scientific and a technical challenge. To this end, we propose an autoregressive multiscale convolutional neural network model to predict relevant quantities at the pore-scale in the solid phase: the lithium concentration (in the active material) and potential (in the active material and carbon binder). Here, these are ultimately used to reconstruct the battery discharge curve. 3D images of the electrode microstructures are the input to the network, trained with a dataset of finite element method simulations to predict the discharge behavior of the cathode side in lithium ion batteries. We propose this machine learning model as a proof-of-concept of the applicability of multiscale networks for time-dependent physics problems. The trained model exhibits very high accuracy (with errors lower than 2 %) in forecasting the discharge behavior of new unseen cathodes.

25 ENERGY STORAGE↗
DOE OSTI2023

Dynamic Bayesian Networks for Fault Prognosis

A dynamic Bayesian Network (DBN)-based fault prognosis framework is proposed in this study to predict the future fault probabilities of gradual faults. The proposed framework utilizes the trend in prediction error generated from data driven forecasting models to estimate the future fault beliefs. The accuracy and scalability of the proposed method is evaluated using the data from a Modelica-based virtual testbed. Overall, the developed framework demonstrates good potential in estimating future fault probabilities of gradual faults.

Pradhan, Ojas↗
DOE OSTI2022

Forecasting distributed energy resources adoption for power systems

Failing to incorporate accurate distributed energy resource penetration forecasts into long-term resource and transmission planning can lead to cost inefficiencies at best and system failures at worst. We have developed an open-source tool that employs an advanced Bass specification to calibrate and forecast technology adoption. The advanced specification includes geographic clustering, exogenously estimated market size, and dynamic time steps. Training on historical adoption of rooftop photovoltaics at the U.S. county-level and using detailed techno-economic estimates, our model achieves a two-year average mean-absolute-percentage-error of 19% in predicting system counts at the county-level, weighted by population. Model error was negatively correlated with market maturity - the error was 12% for counties in states with at least 28 W-per-capita of installed capacity. The advanced specification significantly reduces unweighted forecasting percent error compared to a conventional Bass specification: from 196% to 25% for capacity and from 226% to 22% for system count.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

Improved Prediction of Cold-Air Pools in the Weather Research and Forecasting Model Using a Truly Horizontal Diffusion Scheme for Potential Temperature

The terrain-following vertical coordinate system used by many atmospheric models, including the Weather Research and Forecasting (WRF) Model, is prone to errors in regions of complex terrain. These errors stem, in part, from the calculation of horizontal gradients within the diffusion term of the momentum or scalar evolution equations. In WRF, such gradients can be calculated along coordinate surfaces, or using metric terms that help account for grid skewness. However, neither of these options ensures a truly horizontal gradient calculation, especially if a grid cell is skewed enough that the heights of the neighboring grid points used in the calculation fall outside the vertical range of the cell. In this work, an improved scheme that uses Taylor series approximations to vertically interpolate variables to the level necessary for a truly horizontal gradient calculation is implemented in WRF for the diffusion of potential temperature. The scheme is validated using an atmosphere-at-rest configuration, in which spurious flows develop only as a result of numerical errors and can thus be used as a proxy for model performance. Following validation, the method is applied to the simulation of cold-air pools (CAPs), which occur in regions of complex terrain and are characterized by strong near-surface temperature gradients. Using the truly horizontal scheme, idealized simulations demonstrate reduced numerical mixing in a quiescent CAP, and a realistic case study in the Columbia River basin shows a reduction in positive wind speed bias by up to roughly 20% compared to observations from the Second Wind Forecast Improvement Project.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Day-Ahead Probabilistic Forecasting of Net-Load and Demand Response Potentials with High Penetration of Behind-the-Meter Solar-plus-Storage

The goal of this project is to develop advanced methods for day-ahead net-load forecasting, by leveraging the state-of-the-art machine learning techniques. The developed models produce both point and probabilistic forecasts for a variety of use cases, and are versatile to work with different types of data sets. The innovation lies in the novel design of the architectures, leveraging the most recent advances in machine learning that have not been explored in power systems, accompanied by techniques in the broader artificial intelligence fields such as fuzzy systems. This project has achieved the following accomplishments: (1) preprocessing of over 10 data sets covering varying geographical regions, time horizons, and system levels, which form a robust foundation for training and evaluating forecasting models across a wide range of realistic grid scenarios; (2) development of an interactive web app that enables exploratory analysis of load and generation data, and supports better understanding of data trends, anomalies, and correlations, facilitating model development and stakeholder engagement; (3) implementation of over 10 benchmark models for point and probabilistic forecasting, which include a mix of conventional machine learning methods and state-of-the-art deep learning approaches, providing a comprehensive baseline for performance comparison and validation of the proposed models; (4) development of a fuzzy system based gradient boosting model, tailored for small (less than 3 years) data sets, which achieves a mean absolute percentage error (MAPE) of 4% for point forecasting and a 20% improvement in average pinball loss for probabilistic forecasting; (5) development of a Transformer (a state-of-the-art deep learning architecture) based neural network model, tailored for large (3 years or more) data sets, which achieves a MAPE of 2% for point forecasting and a 20% improvement in average pinball loss for probabilistic forecasting; (6) development of a methodology for quantifying DR potential, and extensions of the previous models for multi-target forecasting of net load and DR potential, which achieve a MAPE of 10% for DR potential.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Probabilistic Day-Ahead Forecasting Using an Analog Ensemble Approach for Wind Farm Grid Services

Wind resource assessment and wind power forecasting are used in research and industry to anticipate future power output at scales ranging from individual wind turbines to entire wind farms. Probabilistic day-ahead wind forecasting is useful for anticipating how a wind farm could potentially participate in the day-ahead market by providing upper and lower bounds for expected power generation, thus informing grid operators of its uncertainty. Understanding this uncertainty is part of a larger project focused on building a platform that combines efforts in weather forecasting, aerodynamic and economic modeling to create maximum value of a wind plant to better provide services to the grid. This effort is also known as the Atmosphere to Electrons to Grid (A2E2G) project. One method for producing a probabilistic forecast is through the analog ensemble approach (Delle Monache et al., 2011). This method leverages historical forecasts and their corresponding observations as a training data set from which future forecasts can be made. For some future forecast, the most similar historical forecasts (analogs) are identified on a regular time basis such as once per a 3-hour window. The most similar analogs, based on a metric such as root mean square error (RMSE), are recorded and their corresponding verifying observations are used as an ensemble member for this future forecast. Prior work in this area demonstrates improvements over raw Numerical Weather Prediction (NWP) forecasts and shows skill similar to techniques such as logistic regression and machine learning (Delle Monache et al., 2013; Alessandrini et al., 2015). Here, we take the High-Resolution Rapid Refresh model (HRRR) day-ahead forecast (0-36 hours) to create a probabilistic day-ahead forecast using an analog ensemble approach. The HRRR has an hourly temporal resolution, with a spatial resolution of 3 km. The 12 UTC HRRR model run is downloaded every day for one year from August 2019 - July 2020, with the first 11 months serving as a bank of analogs from which the forecasting algorithm can create a probabilistic forecast. Once downloaded, the original HRRR forecast is temporally interpolated to 5-minutes, aligning with both the temporal resolution of the observations as well as the timescale relevant for day-ahead power forecasts. The forecast is validated at the M2 tower at the Flatirons Campus of the National Renewable Energy Laboratory (NREL) at a typical wind turbine height of 80 m. Variables such as wind speed, wind direction, and turbulence intensity are incorporated into the probabilistic forecast model and weighted according to their relative importance to the forecast. Based on metrics such as mean bias error (MBE), mean absolute error (MAE), and root mean square error, the analog ensemble forecast outperforms the raw HRRR forecast during the testing period of July 2020. Figure 1 illustrates an example day-ahead forecast compared against the verifying observations. The general variability and ramps are captured throughout the day, with potential to further improve the analog ensemble model through machine learning techniques.

numerical weather prediction↗
DOE OSTI2020

Assessing Uncertainties and Approximations in Solar Heating of the Climate System

In calculating solar radiation, climate models make many simplifications, in part to reduce computational cost and enable climate modeling, and in part from lack of understanding of critical atmospheric information. Whether known errors or unknown errors, the community's concern is how these could impact the modeled climate. The simplifications are well known and most have published studies evaluating them, but with individual studies it is difficult to compare. Here, we collect a wide range of such simplifications in either radiative transfer modeling or atmospheric conditions and assess potential errors within a consistent framework on climate-relevant scales. We build benchmarking capability around a solar heating code (Solar-J) that doubles as a photolysis code for chemistry and can be readily adapted to consider other errors and uncertainties. The broad classes here include: use of broad wavelength bands to integrate over spectral features; scattering approximations that alter phase function and optical depths for clouds and gases; uncertainty in ice-cloud optics; treatment of fractional cloud cover including overlap; and variability of ocean surface albedo. We geographically map the errors in W m -2 using a full climate re-creation for January 2015 from a weather forecasting model. For many approximations assessed here, mean errors are ~2 W m -2 with greater latitudinal biases and are likely to affect a model’s ability to match the current climate state. Combining this work with previous studies, we make priority recommendations for fixing these simplifications based on both the magnitude of error and the ease or computational cost of the fix.

58 GEOSCIENCES↗
DOE OSTI2023

A novel data gaps filling method for solar PV output forecasting

This study proposes a modified gaps filling method, expanding the column mean imputation method and evaluated using randomly generated missing values comprising 5%, 10%, 15%, and 20% of the original data on power output. The XGBoost algorithm was implemented as a forecasting model using the original and processed datasets and two sources of solar radiation data, namely, Shortwave Radiation (SWR) from Advanced Himawari Imager 8 (AHI-8) and Surface Solar Radiation Downward (SSRD) from ERA5 global reanalysis data. Further, the accuracy of the two sets of forecasted power output was evaluated using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Results show that by applying the proposed gap filling method and using SWR in forecasting solar photovoltaic (PV) output, the improvement in the RMSE and MAE values range from 12.52% to 24.30% and from 21.10% to 31.31%, respectively. Meanwhile, using SSRD, the improvement in the RMSE values range from 14.01% to 28.54% and MAE values from 22.39% to 35.53%. To further evaluate the accuracy of the proposed gap-filling method, the proposed method could be validated using different datasets and other forecasting methods. Future studies could also consider applying the said method to datasets with data gaps higher than 20%.

Energy & Fuels↗
DOE OSTI2020

Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing

A main challenge towards ensuring large-scale and seamless integration of photovoltaic systems is to improve the accuracy of energy yield forecasts, especially in grid areas of high photovoltaic shares. The scope of this paper is to address this issue by presenting a unified methodology for hourly-averaged day-ahead photovoltaic power forecasts with improved accuracy, based on data-driven machine learning techniques and statistical post-processing. More specifically, the proposed forecasting methodology framework comprised of a data quality stage, data-driven power output machine learning model development (artificial neural networks), weather clustering assessment (K-means clustering), post-processing output optimisation (linear regressive correction method) and the final performance accuracy evaluation. The results showed that the application of linear regression coefficients to the forecasted outputs of the developed day-ahead photovoltaic power production neural network improved the performance accuracy by further correcting solar irradiance forecasting biases. The resulting optimised model provided a mean absolute percentage error of 4.7% when applied to historical system datasets. Finally, the model was validated both, at a hot as well as a cold semi-arid climatic location, and the obtained results demonstrated close agreement by yielding forecasting accuracies of mean absolute percentage error of 4.7% and 6.3%, respectively. Finally, the validation analysis provides evidence that the proposed model exhibits high performance in both forecasting accuracy and stability.

42 ENGINEERING↗
DOE OSTI2026

LAF-Net: A Deep Residual and Cross-Attention Framework for Day-Ahead Load Forecasting: Preprint

Accurate day-ahead load forecasting is essential for reliable power system operations and market efficiency. System operators such as the Midcontinent Independent System Operator (MISO) rely on forecasts from multiple vendors, yet combining them effectively remains a persistent challenge due to vendor-specific biases. This paper presents a novel LSTM-Attention Fusion Network with Error Representation (LAF-Net) that enhances day-ahead hourly load forecasting through deep residual learning and multi-modal cross-attention. The proposed model builds a historical error memory from past vendor performance and dynamically queries it with future hour context to generate adaptive, hour-specific trust weights for each vendor. A bounded residual correction further refines forecasts by mitigating systematic and temporally localized errors. Tested on real MISO LBA data with multi-vendor forecasts, LAF-Net consistently outperforms the best vendor baseline across all 38 LBAs, achieving more than a 40% reduction in system-level mean absolute error (MAE) during peak load hours relative to the best vendor baseline.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Addressing delayed case reporting in infectious disease forecast modeling

Infectious disease forecasting is of great interest to the public health community and policymakers, since forecasts can provide insight into disease dynamics in the near future and inform interventions. Due to delays in case reporting, however, forecasting models may often underestimate the current and future disease burden. In this paper, we propose a general framework for addressing reporting delay in disease forecasting efforts with the goal of improving forecasts. We propose strategies for leveraging either historical data on case reporting or external internet-based data to estimate the amount of reporting error. We then describe several approaches for adapting general forecasting pipelines to account for under- or over-reporting of cases. We apply these methods to address reporting delay in data on dengue fever cases in Puerto Rico from 1990 to 2009 and to reports of influenza-like illness (ILI) in the United States between 2010 and 2019. Through a simulation study, we compare method performance and evaluate robustness to assumption violations. Our results show that forecasting accuracy and prediction coverage almost always increase when correction methods are implemented to address reporting delay. Some of these methods required knowledge about the reporting error or high quality external data, which may not always be available. Provided alternatives include excluding recently-reported data and performing sensitivity analysis. This work provides intuition and guidance for handling delay in disease case reporting and may serve as a useful resource to inform practical infectious disease forecasting efforts.

59 BASIC BIOLOGICAL SCIENCES↗