Search NASA⌕ Search

SEARCH · Search NASA

Results for “prediction 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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

UniKP: a unified framework for the prediction of enzyme kinetic parameters

Prediction of enzyme kinetic parameters is essential for designing and optimizing enzymes for various biotechnological and industrial applications, but the limited performance of current prediction tools on diverse tasks hinders their practical applications. Here, we introduce UniKP, a unified framework based on pretrained language models for the prediction of enzyme kinetic parameters, including enzyme turnover number (k cat ), Michaelis constant (K m ), and catalytic efficiency (k cat / K m ), from protein sequences and substrate structures. A two-layer framework derived from UniKP (EF-UniKP) has also been proposed to allow robust k cat prediction in considering environmental factors, including pH and temperature. In addition, four representative re-weighting methods are systematically explored to successfully reduce the prediction error in high-value prediction tasks. We have demonstrated the application of UniKP and EF-UniKP in several enzyme discovery and directed evolution tasks, leading to the identification of new enzymes and enzyme mutants with higher activity. UniKP is a valuable tool for deciphering the mechanisms of enzyme kinetics and enables novel insights into enzyme engineering and their industrial applications.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1993

An improved far field drag calculation method for nonlinear CFD codes

An improved method to calculate drag based on far field conditions is presented and demonstrated. The method is illustrated using two CFD codes, PARC and CFL3D, and examining their ability to preserve lift and drag coefficients along grid line defined integration paths. The flow fields were generated by solving the Euler equations for a NACA 0012 airfoil at a free stream Mach number of 0.8 and angle of attack of 1.25 degrees. In comparison to force coefficients obtained by surface pressure integration, neither code acceptably preserved both force coefficients throughout the near and far fields. An investigation into the relationship between numerical prediction error and calculated force coefficients revealed a direct connection between solution mass conservation error and force coefficients error. A method to correct the predicted force coefficients based on integrated mass conservation error is described and demonstrated. The corrected force coefficients for both codes are shown to be more accurate than the uncorrected values. The correction method is applicable to both two and three dimensions and is independent of the algorithm used to generate the flow field.

Sirbaugh, James R.↗
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↗
NASA NTRS2019

Casper-1, Part 6: Uncertainty Quantification, Factor Effects, and Outlier Analysis for an On-Board Airplane Trajectory Prediction Function

This report presents data analysis results for a simulation-based approach named CASPEr (Characterization of Airplane State Prediction Error) to characterize the performance of onboard energy state and automation mode prediction functions for terminal area arrival and approach phases of flight over a wide range of conditions. In particular, the results include quantification of energy state (i.e., altitude and airspeed) prediction performance, models for prediction performance as a function of initial energy state (i.e., initial altitude, airspeed, and weight) and weather factors, and analysis of outlier prediction performance. Wind speed, wind direction, and wind gradient were found to be major factors in energy state prediction performance. Initial energy and gust intensity were also significant factors in airspeed prediction performance. Furthermore, the results suggest that errors in automation mode prediction may be a major contributor to outlier prediction performance.

Torres-Pomales, Wilfredo↗
NASA NTRS2016

Consistent Evaluation of ACOS-GOSAT, BESD-SCIAMACHY, CarbonTracker, and MACC Through Comparisons to TCCON

Consistent validation of satellite CO2 estimates is a prerequisite for using multiple satellite CO2 measurements for joint flux inversion, and for establishing an accurate long-term atmospheric CO2 data record. Harmonizing satellite CO2 measurements is particularly important since the differences in instruments, observing geometries, sampling strategies, etc. imbue different measurement characteristics in the various satellite CO2 data products. We focus on validating model and satellite observation attributes that impact flux estimates and CO2 assimilation, including accurate error estimates, correlated and random errors, overall biases, biases by season and latitude, the impact of coincidence criteria, validation of seasonal cycle phase and amplitude, yearly growth, and daily variability. We evaluate dry-air mole fraction (X(sub CO2)) for Greenhouse gases Observing SATellite (GOSAT) (Atmospheric CO2 Observations from Space, ACOS b3.5) and SCanning Imaging Absorption spectroMeter for Atmospheric CHartographY (SCIAMACHY) (Bremen Optimal Estimation DOAS, BESD v2.00.08) as well as the CarbonTracker (CT2013b) simulated CO2 mole fraction fields and the Monitoring Atmospheric Composition and Climate (MACC) CO2 inversion system (v13.1) and compare these to Total Carbon Column Observing Network (TCCON) observations (GGG2012/2014). We find standard deviations of 0.9, 0.9, 1.7, and 2.1 parts per million vs. TCCON for CT2013b, MACC, GOSAT, and SCIAMACHY, respectively, with the single observation errors 1.9 and 0.9 times the predicted errors for GOSAT and SCIAMACHY, respectively. We quantify how satellite error drops with data averaging by interpreting according to (error(sup 2) equals a(sup 2) plus b(sup 2) divided by n (with n being the number of observations averaged, a the systematic (correlated) errors, and b the random (uncorrelated) errors). a and b are estimated by satellites, coincidence criteria, and hemisphere. Biases at individual stations have year-to-year variability of 0.3 parts per million, with biases larger than the TCCON predicted bias uncertainty of 0.4 parts per million at many stations. We find that GOSAT and CT2013b under-predict the seasonal cycle amplitude in the Northern Hemisphere (NH) between 46 and 53 degrees North latitude, MACC over-predicts between 26 and 37 degrees North latitude, and CT2013b under-predicts the seasonal cycle amplitude in the Southern Hemisphere (SH). The seasonal cycle phase indicates whether a data set or model lags another data set in time. We find that the GOSAT measurements improve the seasonal cycle phase substantially over the prior while SCIAMACHY measurements improve the phase significantly for just two of seven sites. The models reproduce the measured seasonal cycle phase well except for at Lauder_125HR (CT2013b) and Darwin (MACC). We compare the variability within 1 day between TCCON and models in June-July-August; there is correlation between 0.2 and 0.8 in the NH, with models showing 10-50 percent the variability of TCCON at different stations and CT2013b showing more variability than MACC. This paper highlights findings that provide inputs to estimate flux errors in model assimilations, and places where models and satellites need further investigation, e.g., the SH for models and 45-67 degrees North latitude for GOSAT and CT2013b.

ACOS-GOSAT↗
NASA NTRS2007

Adaptive Modeling of the International Space Station Electrical Power System

Software simulations provide NASA engineers the ability to experiment with spacecraft systems in a computer-imitated environment. Engineers currently develop software models that encapsulate spacecraft system behavior. These models can be inaccurate due to invalid assumptions, erroneous operation, or system evolution. Increasing accuracy requires manual calibration and domain-specific knowledge. This thesis presents a method for automatically learning system models without any assumptions regarding system behavior. Data stream mining techniques are applied to learn models for critical portions of the International Space Station (ISS) Electrical Power System (EPS). We also explore a knowledge fusion approach that uses traditional engineered EPS models to supplement the learned models. We observed that these engineered EPS models provide useful background knowledge to reduce predictive error spikes when confronted with making predictions in situations that are quite different from the training scenarios used when learning the model. Evaluations using ISS sensor data and existing EPS models demonstrate the success of the adaptive approach. Our experimental results show that adaptive modeling provides reductions in model error anywhere from 80% to 96% over these existing models. Final discussions include impending use of adaptive modeling technology for ISS mission operations and the need for adaptive modeling in future NASA lunar and Martian exploration.

Thomas, Justin Ray↗
NASA NTRS2022

Using an Explainable Machine Learning Approach to Characterize Earth System Model Errors: Application of SHAP Analysis to Modeling Lightning Flash Occurrence

Computational models of the Earth System are critical tools for modern scientific inquiry. Effortstoward evaluating and improving errors in representations of physical and chemical processes inthese large computational systems are commonly stymied by highly nonlinear and complexerror behavior. Recent work has shown that these errors can be effectively predicted usingmodern Artificial Intelligence (A.I.) techniques. In this work, we go beyond these previousstudies to apply an interpretable A.I. technique to not only predict model errors but also movetoward understanding the underlying reasons for successful error prediction. We use XGBoostclassification trees and SHapley Additive exPlanations (SHAP) analysis to explore the errors inthe prediction of lightning occurrence in the NASA GEOS model, a widely used Earth SystemModel. This explainable error prediction system can effectively predict the model error andindicates that the errors are strongly related to convective processes and the characteristics ofthe land surface.

Artificial intelligence↗
DOE OSTI2024

Machine learning materials properties with accurate predictions, uncertainty estimates, domain guidance, and persistent online accessibility

One compelling vision of the future of materials discovery and design involves the use of machine learning (ML) models to predict materials properties and then rapidly find materials tailored for specific applications. However, realizing this vision requires both providing detailed uncertainty quantification (model prediction errors and domain of applicability) and making models readily usable. At present, it is common practice in the community to assess ML model performance only in terms of prediction accuracy (e.g. mean absolute error), while neglecting detailed uncertainty quantification and robust model accessibility and usability. Here, we demonstrate a practical method for realizing both uncertainty and accessibility features with a large set of models. We develop random forest ML models for 33 materials properties spanning an array of data sources (computational and experimental) and property types (electrical, mechanical, thermodynamic, etc). All models have calibrated ensemble error bars to quantify prediction uncertainty and domain of applicability guidance enabled by kernel-density-estimate-based feature distance measures. All data and models are publicly hosted on the Garden-AI infrastructure, which provides an easy-to-use, persistent interface for model dissemination that permits models to be invoked with only a few lines of Python code. We demonstrate the power of this approach by using our models to conduct a fully ML-based materials discovery exercise to search for new stable, highly active perovskite oxide catalyst materials.

domain of applicability↗
DOE OSTI2022

Using an Explainable Machine Learning Approach to Characterize Earth System Model Errors: Application of SHAP Analysis to Modeling Lightning Flash Occurrence

Abstract Computational models of the Earth System are critical tools for modern scientific inquiry. Efforts toward evaluating and improving errors in representations of physical and chemical processes in these large computational systems are commonly stymied by highly nonlinear and complex error behavior. Recent work has shown that these errors can be effectively predicted using modern Artificial Intelligence (A.I.) techniques. In this work, we go beyond these previous studies to apply an explainable A.I. technique to not only predict model errors but also move toward understanding the underlying reasons for successful error prediction. We use XGBoost classification trees and SHapley Additive exPlanations analysis to explore the errors in the prediction of lightning occurrence in the NASA Goddard Earth Observing System model, a widely used Earth System Model. This explainable error prediction system can effectively predict the model error and indicates that the errors are strongly related to convective processes and the characteristics of the land surface.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Self-diagnosis of model suitability for continuous measurements of stream-dissolved organic carbon derived from in situ UV–visible spectroscopy

Application of high-frequency monitoring of dissolved organic carbon (DOC) is difficult in instances where training datasets are challenging to develop (e.g., remote locations) and the relationship between optical features and DOC concentration changes due to environmental or landscape shifts (e.g., climate or land-use change). We developed and compared three partial least squares (PLS) models using in situ water level measurements, conductivity, and UV–Vis spectral attenuation to predict DOC. Two site-specific models were developed using data from a hillslope-dominated forest or a low-relief wetland-pond-dominated stream catchment. The third model, using data from both sites, exhibited the best performance (DOC range = 4–15.5 mg C L −1 , mean = 8.38 mg C L −1 , training RMSE = 0.34 mg C L −1 , internal validation RMSE = 0.50 mg C L −1 , external validation RMSE = 2.43 mg C L −1 ). We further demonstrate using PLS model statistics to monitor performance and elucidate when and how models should be updated. These statistics, Hotelling's T 2 and squared prediction errors, are useful consistency checks for the predictions made and detect underlying inconsistencies that, if undetected, can reduce the robustness of DOC prediction. For example, via the T 2 statistic, we identified the summer–autumn transition as a period when DOC composition differed from what was represented in the training dataset. We also determined that elevated SUVA 254 values contributed to the overall bias observed in predictions made during the subsequent year as part of the external validation. This enabled the application of a bias correction that reduced the RMSE from 2.43 to 0.89 mg C L −1 . The method presented here could be applied to future monitoring programs enabling model updates to monitor DOC fluxes accurately from optical datasets (e.g., attenuance or fluorescence) in the face of developing datasets in remote locations or environmental change. In conclusion, implementation of this approach may also identify possible regime shifts or landscape and hydrologic change associated with climate and other environmental changes relevant to terrestrial to aquatic fluxes.

UV-VIS spectroscopy↗
DOE OSTI2026

Parametric reduced order models for graded lattice structures

Graded lattice structures, characterized by smoothly varying mechanical properties, hold significant promise for optimizing material distribution in advanced engineering applications. However, accurately modeling these structures poses substantial computational challenges due to the continuous geometric variations within their unit cells. Here, to address these challenges, this paper introduces a novel Efficient Reduced Order Model (EROM) that integrates the Matrix Discrete Empirical Interpolation Method (MDEIM) and Discrete Empirical Interpolation Method (DEIM) with polynomial regression to efficiently manage geometric parametrization in lattice structures. Unlike traditional reduced order models (ROMs) that require extensive precomputed libraries for each geometric configuration, our approach enables continuous geometric variations through a flexible algebraic formulation, significantly reducing computational costs while preserving high accuracy. The method constructs projection matrices for individual unit cells that can be efficiently assembled into global systems, leveraging the repetitive nature of lattice structures. Numerical studies demonstrate that our EROM achieves displacement errors below 1% and von Mises stress prediction errors below 4%, coupled with computational speedups exceeding two orders of magnitude compared to full-order simulations. The proposed method's modularity and scalability make it particularly suitable for design optimization and real-time simulation of functionally graded lattice structures, with applications spanning aerospace to biomedical engineering.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
NASA NTRS1965

Beam-swinging facilities for the Goonhilly satellite-communication aerial

The mode of satellite tracking adopted at the Goonhilly earth station is to steer the aerial primarily by means of predicted data computed from the satellite orbital parameters and to superimpose, during the passage of the satellite, corrections to remove any prediction errors or aberrations due the transmission path. Predictions have proved to be highly accurate for satellites having a high mass to projected area ratio orbiting at altitudes at which air drag is very small; hence the corrections are small and infrequent.

COMMUNICATIONS SATELLITE↗
NASA NTRS2019

Quantifying the Storm Time Thermospheric Neutral Density Variations Using Model and Observations

Accurate determination of thermospheric neutral density holds crucial importance for satellited rag calculations. The problem is twofold and involves the correct estimation of the quiet time climatology and storm time variations. In this work, neutral density estimations from two empirical and threephysics based models of the ionosphere thermosphere are compared with the neutral densities along the Challenging MicroSatellite Payload satellite track for six geomagnetic storms. Storm time variations are extracted from neutral density by (1) subtracting the mean difference between model and observation (bias),(2) setting climatological variations to zero, and (3) multiplying model data with the quiet time ratio between the model and observation. Several metrics are employed to evaluate the model performances. We find that the removal of bias or climatology reveals actual performance of the model in simulating the storm time variations. When bias is removed, depending on event and model, storm time errors in neutral density can decrease by an amount of 113% or can increase by an amount of 12% with respect to error in models with quiet time bias. It is shown that using only average and maximum values of neutral density to determine the model performances can be misleading since a model can estimate the averages fairly well but may not capture the maximum value or vice versa. Since each of the metrics used for determining model performances provides different aspects of the error, among these, we suggest employing mean absolute error, prediction efficiency, and normalized root mean square error together as a standard set ofmetrics for the neutral density.

Eyiguler, E. Ceren Kalafatoglu↗
NASA NTRS2019

CASPEr: an Approach to Characterize the Performance of Onboard Airplane Energy State and Automation Mode Prediction Functions

The Commercial Aviation Safety Team (CAST) has identified a set of safety enhancements to mitigate the risks of loss of control in-flight (LOCI) accidents and incidents involving commercial transport airplanes. In support of this, NASA has been developing technologies intended to enhance flight crew awareness of airplane systems, attitude, and energy state. This report describes preliminary ideas for a methodology to assess the goodness of onboard airplane energy state and automation mode prediction functions. The methodology is intended to contribute to the goal of moving these prediction technologies to the readiness level required for transition to industry and reduce the technology certification risks. In addition, this report describes a simulation-based approach named CASPEr (Characterization of Airplane State Prediction Error) to characterize the performance of these predictive functions over a wide range of operational conditions. The first exploratory version of this approach is described. The bulk of the report documents the initial results of tests to characterize the performance of an airplane trajectory prediction function. Future reports will give additional performance characterization results for this function and a complete description of the proposed methodology to assess such functions.

Torres-Pomales, Wilfredo↗
NASA NTRS2013

Simultaneous Estimation of Model State Variables and Observation and Forecast Biases Using a Two-Stage Hybrid Kalman Filter

In this paper, we present a two-stage hybrid Kalman filter to estimate both observation and forecast bias in hydrologic models, in addition to state variables. The biases are estimated using the discrete Kalman filter, and the state variables using the ensemble Kalman filter. A key issue in this multi-component assimilation scheme is the exact partitioning of the difference between observation and forecasts into state, forecast bias and observation bias updates. Here, the error covariances of the forecast bias and the unbiased states are calculated as constant fractions of the biased state error covariance, and the observation bias error covariance is a function of the observation prediction error covariance. In a series of synthetic experiments, focusing on the assimilation of discharge into a rainfall-runoff model, it is shown that both static and dynamic observation and forecast biases can be successfully estimated. The results indicate a strong improvement in the estimation of the state variables and resulting discharge as opposed to the use of a bias-unaware ensemble Kalman filter. Furthermore, minimal code modification in existing data assimilation software is needed to implement the method. The results suggest that a better performance of data assimilation methods should be possible if both forecast and observation biases are taken into account.

Data Assimilation↗
DOE OSTI2023

Regional Medium-Term Hourly Electricity Demand Forecasting Based on LSTM

This paper aims to forecast high-resolution (hourly) aggregated load for a certain region in the medium term (a few days to over a year). One region is defined as some places with similar climate characteristics because the climate influences people's daily lifestyles and hence the electric usage. We decom- pose the electric usage records into two parts: base load and seasonal load. Considering both temperature and time factors, different deep learning methods are adopted to characterize them. The first goal of our approach is to predict the peak load which is critical for power system planning. Furthermore, our proposed forecast method can provide the depiction of the hourly load profile to provide customized load curves for high- level real-time applications. The proposed method is tested on real-world historical data collected by CAISO, BPA, and PACW. The experimental results show that trained by three years of data, our method could reduce the prediction error for one-year lead hourly load below 5% MAPE, and predict the occurrence of the peak load for next year in CAISO with an error within three days. Furthermore, as a byproduct, an interesting observation on the impact of COVID-19 on human life was made and discussed based on these case studies.

deep learning↗