SEARCH · Engineering Papers

Results for “variability prediction”

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.

SourceResearch connectionFrom yearThrough year

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

At least 1,387 records · Page 77

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Prediction

Abstract The rapid rise of deep learning (DL) in numerical weather prediction (NWP) has led to a proliferation of models which forecast atmospheric variables with comparable or superior skill than traditional physics-based NWP. However, among these leading DL models, there is a wide variance in both the training settings and architecture used. Further, the lack of thorough ablation studies makes it hard to discern which components are most critical to success. In this work, we show that it is possible to attain high forecast skill even with relatively off-the-shelf architectures, simple training procedures, and moderate compute budgets. Specifically, we train a minimally modified Swin Transformer V2 (SwinV2) on ERA5 data and find that it attains superior skill in terms of mean-square errors of deterministic forecasts when compared against the European Centre for Medium-Range Weather Forecasts’ Integrated Forecasting System (IFS). Almost all DL–NWP systems share a core set of hyperparameters and design decisions. To aid and expedite future DL–NWP research, we present an in-depth, systematic exploration of different loss functions, model sizes and depths, patch sizes, and multistep training objectives. We also examine the model performance with metrics beyond the typical accuracy (ACC) and RMSE and investigate how the performance scales with model size. Through our open-source code, scoring pipelines, and models, we share our findings on key aspects of the training pipeline. These ablations reduce the necessity for expensive hyperparameter tuning and lower the barrier to entry for future DL–NWP research. Significance Statement This study investigates the potential of using large-scale transformer-based models for weather prediction, showing that it is possible to achieve high forecast accuracy with simpler, off-the-shelf architectures. By training a minimally modified SwinV2 transformer on ERA5 data, we show that the model achieves competitive forecast skill in terms of mean-square error for key variables, outperforming the European Centre for Medium-Range Weather Forecasts’ Integrated Forecasting System (IFS) at all lead times. Our findings suggest that effective training strategies, such as multistep fine-tuning and channel-weighted losses, significantly enhance the model’s performance. However, we also highlight that these improvements come with trade-offs in other areas, such as ensemble spread and high-frequency spatial detail. This work highlights the promise of deep learning in improving weather forecasts, which could lead to better preparedness and response to weather events, ultimately benefiting society by providing more reliable weather predictions.

Willard, Jared D. [Lawrence Berkeley National Labo↗

DOE OSTI2026

Early calendar life and health prediction of silicon batteries via machine learning with uncertainty quantification

Lithium-ion batteries with silicon anodes promise high energy density but are limited by calendar lifetime. Reducing the long iteration time to obtain experimental results requires predicting calendar lifetime early in a cell's life. In this study, we demonstrate that lightweight machine learning models with feature engineering can provide calendar lifetime estimates from early electrochemical signals. After 1 month of electrochemical aging, the best models achieve 10% error in calendar-life prediction and can separate "bad" from "good" lifetime cells with a mean F1 score of 0.857. As battery systems exhibit inherent variability, four methods for uncertainty quantification are compared, and confidence intervals are demonstrated with an uncertainty of +-3.6 months in lifetime prediction. A feature importance analysis indicates that early patterns in voltage decay are the strongest indicators of calendar lifetime. Finally, this modeling approach has high error when generalizing to new electrode chemistries or testing conditions but with appropriately low confidence.

25 ENERGY STORAGE↗

NASA NTRS1986

Comparison of viscous shock layer and boundary layer reentry heating techniques for Orbiter nose cap

A comparison of two viscous shock layer methods and one boundary layer method for predicting the aerodynamic heating around the Orbiter nose cap during STS-5 entry is presented. The object of the study was to compare these methods with one another and with the measured Orbiter flight data for this trajectory. The nonequilibrium, chemically reacting viscous flow fields obtained by these methods are evaluated, and effects on heating rate of wall catalycity variation with time are presented. The effects of shock slip and combined wall/shock slip are considered at high altitudes (above 300,000 ft). Using the variable wall catalycity analysis, it is shown that heating rates can be predicted within a 5.7 percent flight data band for altitudes between 175,000 ft and 265,000 ft in this trajectory.

Ting, P. C.↗

NASA NTRS1988

Studies of the dependence of the microwave radar cross section on ocean surface variables during the FASINEX experiment

The ability of theoretical radar cross section (RCS) models to predict the absolute magnitude of the ocean radar cross section under a wide variety of sea and atmospheric conditions was studied using experimental data from the FASINEX Experiment. This consists of RCS data from a Ku-band scatterometer mounted on an aircraft (10 separate flights were conducted), a wide variety of atmospheric measurements (including stress) and sea conditions. Theoretical models are tested. Where discrepancies are observed, revisions are hypothesized and evaluated.

Weissman, D. A.↗

NASA NTRS2012

An Efficient Deterministic Approach to Model-based Prediction Uncertainty Estimation

Prognostics deals with the prediction of the end of life (EOL) of a system. EOL is a random variable, due to the presence of process noise and uncertainty in the future inputs to the system. Prognostics algorithm must account for this inherent uncertainty. In addition, these algorithms never know exactly the state of the system at the desired time of prediction, or the exact model describing the future evolution of the system, accumulating additional uncertainty into the predicted EOL. Prediction algorithms that do not account for these sources of uncertainty are misrepresenting the EOL and can lead to poor decisions based on their results. In this paper, we explore the impact of uncertainty in the prediction problem. We develop a general model-based prediction algorithm that incorporates these sources of uncertainty, and propose a novel approach to efficiently handle uncertainty in the future input trajectories of a system by using the unscented transformation. Using this approach, we are not only able to reduce the computational load but also estimate the bounds of uncertainty in a deterministic manner, which can be useful to consider during decision-making. Using a lithium-ion battery as a case study, we perform several simulation-based experiments to explore these issues, and validate the overall approach using experimental data from a battery testbed.

Daigle, Matthew J.↗

NASA NTRS1984

Applications of Sequential Estimation to Numerical Weather Prediction

The main objective of this cooperative research with NASA's Goddard Laboratory for Atmospheric Sciences (GLAS) is to use information about the atmosphere acquired from new types of observations, especially from satellites, in order to deepen our understanding of its behavior on time scales from hours to years. This is achieved by: (1) improving the methods for processing point observations into complete fields in space and time, using sequential estimation theory; and (2) analyzing low-frequency atmospheric variability by the methods of dynamical system theory, suitably modified to enhance practical predictability.

Ghil, M.↗

DOE OSTI2024

Weak-form inference for hybrid dynamical systems in ecology

Species subject to predation and environmental threats commonly exhibit variable periods of population boom and bust over long timescales. Understanding and predicting such behaviour, especially given the inherent heterogeneity and stochasticity of exogenous driving factors over short timescales, is an ongoing challenge. A modelling paradigm gaining popularity in the ecological sciences for such multi-scale effects is to couple short-term continuous dynamics to long-term discrete updates. We develop a data-driven method utilizing weak-form equation learning to extract such hybrid governing equations for population dynamics and to estimate the requisite parameters using sparse intermittent measurements of the discrete and continuous variables. The method produces a set of short-term continuous dynamical system equations parametrized by long-term variables, and long-term discrete equations parametrized by short-term variables, allowing direct assessment of interdependencies between the two timescales. We demonstrate the utility of the method on a variety of ecological scenarios and provide extensive tests using models previously derived for epizootics experienced by the North American spongy moth ( Lymantria dispar dispar ).

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

Data from: Coupled machine learning-ecosystem ensemble models substantially improve predictions of nitrous oxide (N 2 O) fluxes from US croplands

Nitrous oxide (N₂O) is a potent and persistent greenhouse gas, with rising atmospheric concentrations driven in part by inefficient use of synthetic nitrogen (N) fertilizers in agriculture. Predicting soil N₂O emissions is challenging due to high spatial and temporal variability arising from complex soil biogeochemical processes. Process-based ecosystem models and standalone machine learning (ML) approaches without extensive site-specific calibration often miss high emission episodes. Here, we show how an Ensemble Modeling System (EMS) based on outputs from an ensemble of ecosystem models coupled to an ensemble of ML models can improve predictions and understanding of N2O fluxes from US cropland. Trained and validated on approximately 12,000 N2O chamber measurements at 17 U.S. Midwest sites (six crops, 35 management practices), the EMS accurately predicted daily fluxes of N2O at both training (R² = 0.84, RMSE = 16.4 g N ha⁻¹ d⁻¹) and held-out testing sites (R² = 0.84, RMSE = 6.2 g N ha⁻¹ d⁻¹). Analyses identified six dominant N₂O drivers: soil organic carbon (SOC), NH₄⁺, NO₃⁻, water-filled pore space (WFPS), soil temperature, and biomass production. Wet, warm soils produced large N₂O peaks only with sufficient SOC and mineral N; in low-SOC soils, fluxes remained low. Incorporating these drivers into process-based models might significantly improve their predictive capacity. The EMS demonstrates a strong potential to predict N₂O fluxes at unseen sites, enabling more reliable regional inventories, improved gap-filling where measurements are sparse, and enhanced understanding of mechanisms to advance targeted mitigation strategies in food, feed, and bioenergy crops.

agricultural sciences↗

DOE OSTI2026

Resilience Metrics Framework for Solar Photovoltaics

This presentation was given at the Photovoltaic Specialist Conference (PVSC) 54 in New Orleans, Louisiana. Photovoltaic (PV) systems are routinely exposed to extreme weather, including wind and hail storms. Historically, most systems have proven to be resilient to such events, but some storms have damaged PV systems, leading to physical and financial loss. Storm hardening measures and specific system attributes can reduce this risk. This work introduces a set of resilience metrics and a framework for quantifying, comparing, and predicting PV system resilience. The framework is divided into two parts: 1) predictive, attribute metrics based on site and component characteristics, and 2) impact metrics that assess post-storm performance. Metrics are weighted and aggregated, producing hazard-specific resilience scores. We derive damage functions from storm-impacted PV systems, establishing a baseline against which post-storm performance can be compared. This damage was widely variable across hail and wind intensities, and field hail damage was less than predicted by laboratory tests, suggesting that system features - in addition to storm conditions - influence damage likelihood. Finally, the metrics framework is demonstrated using three case studies of storm damaged PV systems. Although additional data are needed to create attribute specific damage functions and establish metric weights, this study presents a methodology for evaluating PV resilience and contributes new damage functions to the literature.

14 SOLAR ENERGY↗

NASA NTRS2014

Dissertation Defense Computational Fluid Dynamics Uncertainty Analysis for Payload Fairing Spacecraft Environmental Control Systems

Spacecraft thermal protection systems are at risk of being damaged due to airflow produced from Environmental Control Systems. There are inherent uncertainties and errors associated with using Computational Fluid Dynamics to predict the airflow field around a spacecraft from the Environmental Control System. This paper describes an approach to quantify the uncertainty in using Computational Fluid Dynamics to predict airflow speeds around an encapsulated spacecraft without the use of test data. Quantifying the uncertainty in analytical predictions is imperative to the success of any simulation-based product. The method could provide an alternative to traditional "validation by test only" mentality. This method could be extended to other disciplines and has potential to provide uncertainty for any numerical simulation, thus lowering the cost of performing these verifications while increasing the confidence in those predictions. Spacecraft requirements can include a maximum airflow speed to protect delicate instruments during ground processing. Computational Fluid Dynamics can be used to verify these requirements; however, the model must be validated by test data. This research includes the following three objectives and methods. Objective one is develop, model, and perform a Computational Fluid Dynamics analysis of three (3) generic, non-proprietary, environmental control systems and spacecraft configurations. Several commercially available and open source solvers have the capability to model the turbulent, highly three-dimensional, incompressible flow regime. The proposed method uses FLUENT, STARCCM+, and OPENFOAM. Objective two is to perform an uncertainty analysis of the Computational Fluid Dynamics model using the methodology found in "Comprehensive Approach to Verification and Validation of Computational Fluid Dynamics Simulations". This method requires three separate grids and solutions, which quantify the error bars around Computational Fluid Dynamics predictions. The method accounts for all uncertainty terms from both numerical and input variables. Objective three is to compile a table of uncertainty parameters that could be used to estimate the error in a Computational Fluid Dynamics model of the Environmental Control System /spacecraft system. Previous studies have looked at the uncertainty in a Computational Fluid Dynamics model for a single output variable at a single point, for example the re-attachment length of a backward facing step. For the flow regime being analyzed (turbulent, three-dimensional, incompressible), the error at a single point can propagate into the solution both via flow physics and numerical methods. Calculating the uncertainty in using Computational Fluid Dynamics to accurately predict airflow speeds around encapsulated spacecraft in is imperative to the success of future missions.

CFD↗

NASA NTRS2014

Dissertation Defense: Computational Fluid Dynamics Uncertainty Analysis for Payload Fairing Spacecraft Environmental Control Systems

Spacecraft thermal protection systems are at risk of being damaged due to airflow produced from Environmental Control Systems. There are inherent uncertainties and errors associated with using Computational Fluid Dynamics to predict the airflow field around a spacecraft from the Environmental Control System. This paper describes an approach to quantify the uncertainty in using Computational Fluid Dynamics to predict airflow speeds around an encapsulated spacecraft without the use of test data. Quantifying the uncertainty in analytical predictions is imperative to the success of any simulation-based product. The method could provide an alternative to traditional validation by test only mentality. This method could be extended to other disciplines and has potential to provide uncertainty for any numerical simulation, thus lowering the cost of performing these verifications while increasing the confidence in those predictions.Spacecraft requirements can include a maximum airflow speed to protect delicate instruments during ground processing. Computational Fluid Dynamics can be used to verify these requirements; however, the model must be validated by test data. This research includes the following three objectives and methods. Objective one is develop, model, and perform a Computational Fluid Dynamics analysis of three (3) generic, non-proprietary, environmental control systems and spacecraft configurations. Several commercially available and open source solvers have the capability to model the turbulent, highly three-dimensional, incompressible flow regime. The proposed method uses FLUENT, STARCCM+, and OPENFOAM. Objective two is to perform an uncertainty analysis of the Computational Fluid Dynamics model using the methodology found in Comprehensive Approach to Verification and Validation of Computational Fluid Dynamics Simulations. This method requires three separate grids and solutions, which quantify the error bars around Computational Fluid Dynamics predictions. The method accounts for all uncertainty terms from both numerical and input variables. Objective three is to compile a table of uncertainty parameters that could be used to estimate the error in a Computational Fluid Dynamics model of the Environmental Control System spacecraft system.Previous studies have looked at the uncertainty in a Computational Fluid Dynamics model for a single output variable at a single point, for example the re-attachment length of a backward facing step. For the flow regime being analyzed (turbulent, three-dimensional, incompressible), the error at a single point can propagate into the solution both via flow physics and numerical methods. Calculating the uncertainty in using Computational Fluid Dynamics to accurately predict airflow speeds around encapsulated spacecraft in is imperative to the success of future missions.

Fluid Dynamics↗

NASA NTRS2020

Calibration Probe Uncertainty and Validation for the Hypersonic Material Environmental Test System

This paper presents an uncertainty analysis of the stagnation-point calibration probe surface predictions for conditions that span the performance envelope of the Hypersonic Materials Environmental Test System facility located at NASA Langley Research Center. A second-order stochastic expansion was constructed over 47 uncertain parameters to evaluate the sensitivities, identify the most significant uncertain variables, and quantify the uncertainty in the stagnation-point heat flux and pressure predictions of the calibration probe for a low- and high-enthalpy test condition. A sensitivity analysis showed that measurement bias uncertainty is the most significant contributor to the stagnation-point pressure and heat flux variance for the low-enthalpy condition. For the high-enthalpy condition, a paradigm shift in sensitivities revealed the computational fluid dynamics model input uncertainty as the main contributor. A comparison between the prediction and measurement of the stagnation-point conditions under uncertainty showed that there was evidence of statistical disagreement. A validation metric was proposed and applied to the prediction uncertainty to account for the statistical disagreement when compared to the possible stagnation-point heat flux and pressure measurements.

Brune, Andrew J.↗

DOE OSTI2024

Predictive analytics of selections of russet potatoes

We explore the application of machine learning algorithms specifically to enhance the selection process of Russet potato (Solanum tuberosum L.) clones in breeding trials by predicting their suitability for advancement. This study addresses the challenge of efficiently identifying high-yield, disease-resistant, and climate-resilient potato varieties that meet processing industry standards. Leveraging manually collected data from trials in the state of Oregon, we investigate the potential of a wide variety of state-of-the-art binary classification models. The dataset includes 1086 clones, with data on 38 attributes recorded for each clone, focusing on yield, size, appearance, and frying characteristics, with several control varieties planted consistently across four Oregon regions from 2013 to 2021. We conduct a comprehensive analysis of the dataset that includes preprocessing, feature engineering, and imputation to address missing values. We focus on several key metrics such as accuracy, F1-score, and Matthews correlation coefficient (MCC) for model evaluation. The top-performing models, namely a feedforward neural network classifier (Neural Net), a histogram-based gradient boosting classifier (HGBC), and a support vector machine classifier (SVM), demonstrate consistent and significant results. To further validate our findings, we conducted a simulation study using the aims, data-generating mechanisms, estimands, methods, and performance measures (ADEMP) framework, simulating different data-generating scenarios to assess model robustness and performance through true positive, true negative, false positive, and false negative distributions, area under the receiver operating characteristic curve (AUC-ROC) and MCC. The simulation results highlight that non-linear models like SVM and HGBC consistently show higher AUC-ROC and MCC than logistic regression, thus outperforming the traditional linear model across various distributions, and emphasizing the importance of model selection and tuning in agricultural trials. Variable selection further enhances model performance and identifies influential features in predicting trial outcomes. The findings emphasize the potential of machine learning in streamlining the selection process for potato varieties, offering benefits such as increased efficiency, substantial cost savings, and judicious resource utilization. Our study contributes insights into precision agriculture and showcases the relevance of advanced technologies for informed decision-making in breeding programs.

60 APPLIED LIFE SCIENCES↗

NASA NTRS1979

Some practical observations on the accelerated testing of Nickel-Cadmium Cells

A large scale test of 6.0 Ah Nickel-Cadmium Cells conducted at the Naval Weapons Support Center, Crane, Indiana has demonstrated a methodology for predicting battery life based on failure data from cells cycled in an accelerated mode. After examining eight variables used to accelerate failure, it was determined that temperature and depth of discharge were the most reliable and efficient parameters for use in accelerating failure and for predicting life.

Mcdermott, P. P.↗

DOE OSTI2021

Laboratory Investigation of Gas Transport Through Variably Saturated Rock [Slides]

Project Overview: Noble gas fission products, such as xenon (Xe), are monitored to detect nuclear tests. For well-contained subsurface tests, transport to the surface will impact detected isotopic ratios, complicating event identification. Role of water saturation in subsurface transport is not well understood. Historic tests have taken place near or below the water table. To accurately predict breakthrough times and fractionation, gas transport must be characterized through intact rock with variable saturation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

NASA NTRS2019

Analyzing Machine Learning Predictions of Passive Microwave Brightness Temperature Spectral Difference Over Snow-Covered Terrain in High Mountain Asia

Snow is an important component of the terrestrial freshwater budget in high mountainAsia (HMA) and contributes to the runoff in Himalayan rivers through snowmelt. Despitethe importance of snow in HMA, considerable spatiotemporal uncertainty exists across the different estimates of snow water equivalent for this region. In order to better estimate snow water equivalent, radiative transfer models are often used in conjunction with microwave brightness temperature measurements. In this study, the efficacy of support vector machines (SVMs), a machine learning technique, to predict passive microwave brightness temperature spectral difference (1Tb) as a function of geophysical variables (snow water equivalent, snow depth, snow temperature, and snow density) is explored through a sensitivity analysis. The use of machine learning (as opposed to radiative transfer models) is a relatively new and novel approach for improving snow water equivalent estimates. The Noah-MP land surface model within the NASALand Information System framework is used to simulate the hydrologic cycle over HMA and model geophysical variables that are then used for SVM training. The SVMsserve as a nonlinear map between the geophysical space (modeled in Noah-MP) andthe observation space (1Tb as measured by the radiometer). Advanced MicrowaveScanning Radiometer-Earth Observing System measured passive microwave brightness temperatures over snow-covered locations in the HMA region are used as training data during the SVM training phase. Sensitivity of well-trained SVMs to each Noah-MP modeled state variable is assessed by computing normalized sensitivity coefficients. Sensitivity analysis results generally conform with the known first-order physics. Input states that increase volume scattering of microwave radiation, such as snow density and snow water equivalent, exhibit a plurality of positive normalized sensitivity coefficients. In general, snow temperature was the most sensitive input to the SVM predictions. The sensitivity of each state is location and time dependent. The signs of normalized sensitivity coefficients that indicate physical irrationality are ascribed to significant cross-correlation between Noah-MP simulated states and decreased SVM prediction capability at specific locations due to insufficient training data. SVM prediction pitfalls do exist that serve to highlight the limitations of this particular machine learning algorithm.

high mountain Asia↗

NASA NTRS1980

A short-range objective nocturnal temperature forecasting model

A relatively simple, objective, nocturnal temperature forecasting model suitable for freezing and near-freezing conditions has been designed so that a user, presumably a weather forecaster, can put in standard meteorological data at a particular location and receive an hour-by-hour prediction of surface and air temperatures for that location for an entire night. The user has the option of putting in his own estimates of wind speeds and background sky radiation which are treated as independent variables. An analysis of 141 test runs show that 57.4% of the time the model predicts to within 1 C for the best cases and to within 3 C for 98.0% of all cases.

Sutherland, R. A.↗

DOE OSTI2022

Analysis of Inlier and Outlier Compounds with Respect to Artificial Neural Network Cetane Number Prediction Accuracy

Artificial neural networks (ANNs) are exceptional at forming non-linear correlations between multivariate input and target variables; however, they are often seen as a “black box” approach, since how ANNs form these correlations is somewhat ambiguous. Furthermore, the process underlying how ANNs learn from inlier and outlier samples within the input dataset is not fully understood. Intuitively, it is expected that training ANNs with inlier samples will increase prediction accuracy and training with outlier samples will reduce prediction accuracy; though, in practice, this is not always true. The present work identifies and analyzes inliers and outliers of existing experimental cetane number (CN) data encompassing a variety of compounds and compound groups. It also investigates how ANNs trained to predict CN perform with and without outliers included in the training data, and whether a relationship exists between inliers/outliers and ANN prediction accuracy across the whole dataset and for individual samples. Additionally, individual outlier compounds are analyzed, highlighting how they structurally differ from inlier compounds.

09 BIOMASS FUELS↗