Search NASA⌕ Search

SEARCH · Search NASA

Results for “robust regression”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Integration of LIBS with Machine Learning for Real-Time Monitoring of Feedstock in H 2 Gasification Applications

This project, funded by the U.S. Department of Energy (DOE) – Office of Fossil Energy under Award Number DE-FE0032177, aimed to assess the feasibility of an integrated Laser-Induced Breakdown Spectroscopy (LIBS) system with advanced machine learning (ML) models for real-time characterization and potential control of hydrogen gasifiers running on waste materials as feedstocks. This was a multidisciplinary effort that encompassed the acquisition and standardized analysis of individual and blended feedstocks—comprising biomass, coal waste, and plastic waste, followed by the development of a dynamic LIBS bench system for material sample analysis and development of predictive ML models. Comprehensive laboratory testing enabled the creation of a robust elemental dataset that served as the foundation for ML model training. Techniques such as Random Forest, Gradient Boosting, Support Vector Regression, and Neural Networks were employed to predict key feedstock properties, including higher heating value (HHV), moisture content, thermal conductivity, and ash composition with high accuracy. The results were validated against experimental data and demonstrated strong potential for real-time application in gasifier control systems. The project concluded with a study on the integration of the LIBS+ML approach for gasifier control and a techno-economic analysis of the implementation of the approach into hydrogen (H 2 ) gasification systems. Dissemination of results was carried out at a DOE meeting. This work establishes a scalable framework for automated, in-line feedstock quality assessment, offering significant implications for process optimization and emissions reduction in hydrogen production.

01 COAL, LIGNITE, AND PEAT↗
NASA NTRS1992

Bone mineral density, muscle strength, and recreational exercise in men

Muscle strength has been shown to predict bone mineral density (BMD) in women. We examined this relationship in 50 healthy men who ranged in age from 28 to 51 years (average 38.3 years). BMD of the lumbar spine, proximal femur, whole body, and tibia were measured by dual-energy x-ray absorptiometry (Hologic QDR 1000W). Dynamic strength using one repetition maximum was assessed for the biceps, quadriceps, and back extensors and for the hip abductors, adductors, and flexors. Isometric grip strength was measured by dynamometry. Daily walking mileage was assessed by 9 week stepmeter records and kinematic analysis of video filming. Subjects were designated as exercisers and nonexercisers. Exercisers participated in recreational exercise at least two times each week. The results demonstrated that BMD at all sites correlated with back and biceps strength (p < 0.01 to p = 0.0001). Body weight correlated with tibia and whole-body BMD (p < 0.001); age negatively correlated with Ward's triangle BMD (p < 0.01). In stepwise multiple regressions, back strength was the only independent predictor of spine and femoral neck density (R2 = 0.27). Further, back strength was the most robust predictor of BMD at the trochanter, Ward's triangle, whole body, and tibia, although biceps strength, age, body weight, and leg strength contributed significantly to BMD at these skeletal sites, accounting for 35-52% of the variance in BMD. Exercisers and nonexercisers were similar for walking (3.97 versus 3.94 miles/day), age (37.8 versus 38.5) years, and weight (80.0 versus 77.7 kg). However, BMD and muscle strength were significantly greater in exercises than in nonexercisers.(ABSTRACT TRUNCATED AT 250 WORDS).

NASA Center ARC↗
NASA NTRSDate not supplied

Quantifying radiation quality for space relevant radiation types: Fitting excess risk models to three combined HZE-irradiated mouse datasets

Radiation health risks are predominantly derived from low linear energy transfer (LET) terrestrial exposures; however, space radiation includes exposure to high-LET and high-charge, high-energy (HZE) particles. Accurately quantifying the differences in radiation quality between the space and terrestrial radiation environments is important for assessing and predicting health risks for astronauts. Weil et al. 2009 and 2014 used two different inbred mouse strains to study differences in hepatocellular carcinoma (HCC) tumorigenesis after exposures to low- and high- LET radiation. More recently, Edmundson et al. 2020 provided valuable new tumor data in outbred mice that were exposed to low- and high-LET radiation. The present study aims to rigorously investigate a relative biological effectiveness (RBE) factor by leveraging the HCC tumor data from Weil et al. 2009, Weil et al. 2014, and Edmundson et al. 2020. The three experiments were similarly designed, allowing the raw data to be combined into a pooled dataset to estimate excess relative risk (ERR) and excess absolute risk (EAR) models using Bayesian Poisson regression. These effect estimates from the pooled data provide greater power to calculate a data driven RBE. Extensive sensitivity analyses test the robustness of RBE estimates to various model assumptions. The following questions will be explored through the sensitivity analyses: • Is the shape of the dose response different for low-LET radiation and HZE radiation, indicating that RBE is a function of dose? • Does attained age modify the effect estimates differently for low-LET radiation and HZE radiation, indicating RBE is a function of attained age? • Are the effect estimates and RBE estimates different for inbred mouse strains and outbred mouse strains? • Do assumptions about differences in ERR models and EAR models change the estimated RBE? Additional studies would be needed to validate the findings from these exploratory analyses.

Lori J. Chappell↗
NASA NTRS2026

Spatially Refined Satellite Gravimetry Captures Human Signatures in Global Terrestrial Water Storage Trends

Human activities have directly altered the water cycle through water management, aquifer pumping, agricultural irrigation, and land use change. Although satellite gravimetry has transformed global hydrological research, its coarse resolution limits attribution of freshwater change to human activities at many management-relevant scales. Here we assessed global terrestrial water storage (TWS) trends from April 2002 to November 2025 using “stacked” regression of Level-1B intersatellite ranging data, which leverages temporal information and variability to dramatically improve effective spatial resolution relative to standard approaches. We combined this refined product with rigorous uncertainty analysis, autocorrelation-robust geostatistical methods, and literature assessment to evaluate TWS trend associations with land and water use, climate variability, and glacial mass loss. We identified TWS trend hotspots exhibiting significant spatial associations with anthropogenic 40 drivers, including groundwater and surface-water irrigation, rainfed agriculture, deforestation, and reservoir impoundment. Across these regions, cumulative TWS losses (3,122 Gt) substantially exceeded gains (2,432 Gt). Compared with traditional regression of monthly mascons, our approach yielded regional trend magnitudes that are on average 33% larger, revealing that global freshwater depletion, particularly from groundwater pumping, is considerably more acute than previously estimated. Multivariate regression models show that humans account for a significant share of the spatial variability in TWS trends on every non-polar continent except Australia. We detected localized TWS gains linked to rainfed agriculture, surface water irrigation, and reservoir filling that were unresolved in earlier gravimetric studies. The methodology provides a foundation for future gravity missions to independently track decadal freshwater change with unprecedented spatial fidelity.

groundwater↗
DOE OSTI2026

A non-intrusive framework using acoustic signals and deep learning for boiling diagnostics in visual-limited environments

Accurate monitoring of boiling heat transfer is critical for safeguarding high-power systems operating in environments where conventional optical diagnostics are hindered by radiation fields or restricted visual accessibility. This study presents a non-intrusive framework that integrates hydroacoustic sensing with deep learning to infer near-wall boiling characteristics and enable predictive thermal assessment without visual access. In a prototypical subcooled flow-boiling facility representative of the Isotope Production Facility (IPF) at Los Alamos, hydrophones capture boiling-induced acoustic emissions that are transformed into background-removed Short-Time Fourier Transform (STFT) spectrograms. A convolutional neural network (CNN) then regresses heat flux, wall superheat, and key bubble parameters directly from these spectrograms. The CNN achieved predictive accuracy under nominal conditions and demonstrated robustness and generalization under acoustic noise for Signal-to-Noise Ratios (SNRs) down to approximately 0 dB. When integrated into an ANSYS CFX wall-boiling model, the acoustically inferred parameters reproduced boiling curve and critical heat flux (CHF) values consistent with image-based benchmarks. Furthermore, the model retained reliable performance under moderate variations in bulk temperature, flow rate, and hydrophone placement, confirming its generalizability across practical boundary conditions. These results demonstrate the feasibility of hydroacoustic-based deep learning as a viable path toward real-time, radiation-tolerant boiling diagnostics and predictive thermal safety assessment in inaccessible systems such as the IPF.

42 ENGINEERING↗
DOE OSTI2026

Calibration and Rapid-Adoption Forecasting Techniques

CRAFT (Calibration and Rapid-Adoption Forecasting Techniques) CRAFT is a Python-based project for processing, analyzing, and modeling atmospheric or environmental data. It uses machine learning techniques, specifically Random Forest Regression, to create emulators for various environmental variables such as gross primary production and soil water content. It then uses these emulators to robustly test the parameter space of mechanistic models to provide posterior estimations of the free parameters.

Robins, Zachary↗
DOE OSTI2026

HydraGNN v5.0

HydraGNN v5.0 expands the code base into a more portable, scalable, and flexible framework for scientific graph learning, with particular strength in atomistic machine-learning interatomic potentials and large-scale distributed training. The release adds Fully Sharded Data Parallel (FSDP) support alongside existing DDP and DeepSpeed paths, including FSDP-aware checkpointing and optimizer integration, and introduces a configurable multi-precision training workflow supporting FP32, BF16, and FP64 across GPUs and Intel XPUs. For atomistic modeling, HydraGNN v5.0 strengthens its MLIP capabilities through dynamic graph construction at every forward pass, energy-conserving force prediction via automatic differentiation, and per-atom energy loss formulations, while extending EGNN models to properly handle periodic boundary conditions. The release also broadens model expressiveness through graph-level attribute conditioning, adds new multi-task and model-parallel extensions such as MACE support and encoder/decoder branch optimization, and expands application coverage with integrated examples for datasets including OC25, Nabla2-DFT, QCML, Open Polymers 2026, and OPF. In parallel, HydraGNN v5.0 improves production readiness through performance optimizations for large-scale runs, stratified sampling and linear-regression preprocessing utilities, and tested installation scripts for DOE supercomputers including Frontier, Aurora, Perlmutter, and Andes. Overall, the release advances HydraGNN as a robust software platform for scalable graph neural networks across materials science, chemistry, and scientific machine learning workflows

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗
DOE OSTI2025

EVALUATION OF HRA METHODOLOGIES FOR APPLICATION IN SDP WORK

This study critically evaluates human reliability analysis (HRA) methodologies applicable to regulatory probabilistic safety assessment (PSA) model, with a particular focus on their role in supporting the significance determination process (SDP) in nuclear safety assessment. Firstly, three widely utilized HRA methods – IDHEAS-ECA, SPAR-H, and ASEP/THERP – were qualitatively and quantitatively assessed. Qualitative assessments were conducted using attributes from the NEA/CSNI/R(2015)1 report, while quantitative evaluations employed regression and correlation analyses to compare predicted human error probabilities (HEPs) against empirical data. Results reveal distinct strengths, for example, IDHEAS-ECA’s robust predictive accuracy and K-HRA’s alignment with operational practices. In addition, dependency analysis and recovery analysis were critically evaluated. For dependency analysis, the methods’ handling of inter-task dependencies and their impact on HEPs were examined, while recovery analysis highlighted strategies for mitigating failure events. Furthermore, strategies were proposed to evaluate performance-shaping factors under conditions of reduced human performance, such as stress, fatigue, or cognitive overload, addressing specific challenges faced in SDP evaluations. Human errors from KINS’s operational performance information system event reports were evaluated as a case study. This study identifies gaps and provides actionable insights to ensure their validity and applicability in SDP HRA applications. This paper is a part of research conducted by KINS, and it should be noted that this result does not represent the regulatory position of KINS.

99 - GENERAL AND MISCELLANEOUS↗
NASA NTRS2004

Neural network uncertainty assessment using Bayesian statistics: a remote sensing application

Neural network (NN) techniques have proved successful for many regression problems, in particular for remote sensing; however, uncertainty estimates are rarely provided. In this article, a Bayesian technique to evaluate uncertainties of the NN parameters (i.e., synaptic weights) is first presented. In contrast to more traditional approaches based on point estimation of the NN weights, we assess uncertainties on such estimates to monitor the robustness of the NN model. These theoretical developments are illustrated by applying them to the problem of retrieving surface skin temperature, microwave surface emissivities, and integrated water vapor content from a combined analysis of satellite microwave and infrared observations over land. The weight uncertainty estimates are then used to compute analytically the uncertainties in the network outputs (i.e., error bars and correlation structure of these errors). Such quantities are very important for evaluating any application of an NN model. The uncertainties on the NN Jacobians are then considered in the third part of this article. Used for regression fitting, NN models can be used effectively to represent highly nonlinear, multivariate functions. In this situation, most emphasis is put on estimating the output errors, but almost no attention has been given to errors associated with the internal structure of the regression model. The complex structure of dependency inside the NN is the essence of the model, and assessing its quality, coherency, and physical character makes all the difference between a blackbox model with small output errors and a reliable, robust, and physically coherent model. Such dependency structures are described to the first order by the NN Jacobians: they indicate the sensitivity of one output with respect to the inputs of the model for given input data. We use a Monte Carlo integration procedure to estimate the robustness of the NN Jacobians. A regularization strategy based on principal component analysis is proposed to suppress the multicollinearities in order to make these Jacobians robust and physically meaningful.

Neural Networks (Computer)↗
DOE OSTI2024

Elliptically-Contoured Tensor-variate Distributions with Application to Image Learning

Statistical analysis of tensor-valued data has largely used the tensor-variate normal (TVN) distribution that may be inadequate for data arising from distributions with heavier or lighter tails. We study a general family of elliptically contoured (EC) TV distributions and derive its characterizations, moments, marginal, and conditional distributions. We describe procedures for maximum likelihood estimation from data that are (1) uncorrelated draws from an EC distribution, (2) from a scale mixture of the TVN distribution, and (3) from an underlying but unknown EC distribution, for which we extend Tyler’s robust estimator. A detailed simulation study highlights the benefits of choosing an EC distribution over the TVN for heavier-tailed data. We develop TV classification rules using discriminant analysis and EC errors and show that they better predict cats and dogs from images in the Animal Faces-HQ dataset than the TVN-based rules. A novel tensor-on-tensor regression and TV analysis of variance (TANOVA) framework under EC errors is also demonstrated to better characterize gender, age, and ethnic origin than the usual TVN-based TANOVA in the celebrated labeled faces of the wild dataset.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Enhancing fire emissions inventories for acute health effects studies: integrating high spatial and temporal resolution data

Daily fire progression information is crucial for public health studies that examine the relationship between population-level smoke exposures and subsequent health events. Issues with remote sensing used in fire emissions inventories (FEI) lead to the possibility of missed exposures that impact the results of acute health effects studies. This paper provides a method for improving an FEI dataset with readily available information to create a more robust dataset with daily fire progression. High temporal and spatial resolution burned area information from two FEI products are combined into a single dataset, and a linear regression model fills gaps in daily fire progression. The combined dataset provides up to 71% more PM 2.5 emissions, 69% more burned area, and 367% more fire days per year than using a single source of burned area information. The FEI combination method results in improved FEI information with no gaps in daily fire emissions estimates. The combined dataset provides a functional improvement to FEI data that can be achieved with currently available data.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
DOE OSTI2025

Leveraging Artificial Intelligence to Predict Novel Eutectic Alloys

The goal of this project was to train an artificial neural network (ANN) to predict the fractional composition and melting point of eutectic alloys using fundamental atomic properties as inputs. The fundamental properties considered include atomic number, atomic weight, atomic radius, valence electron concentration, electronegativity, and electron affinity. The project involved several phases, starting with data preparation, where phase diagram data was harvested from the ASM International database. Approximately 1300 binary eutectics were collected and cleaned to ensure relevance and accuracy. A regression model was selected for training, utilizing a rectified linear unit as the activation function. Various model configurations were evaluated for predictive accuracy, with validation techniques employed to ensure robustness. The model demonstrated predictive capabilities above random guessing and was able to achieve up to 11% accuracy under certain conditions. An ablative test identified atomic radius and valence electron concentration as critical inputs for model performance. Incorporating the melting point of atomic constituents improved accuracy significantly, although ultimately the model’s predictive capability still fell short of the 80% target. This report details the methodology, results, and implications of the research, contributing to the understanding of employing artificial intelligence to predict the phase transition behavior of eutectic alloys.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Machine learning without a processor: Emergent learning in a nonlinear analog network

Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic contrastive local learning networks (CLLNs) offer potentially fast, efficient, and fault-tolerant hardware for analog machine learning, but existing implementations are linear, severely limiting their capabilities. These systems differ significantly from artificial neural networks as well as the brain, so the feasibility and utility of incorporating nonlinear elements have not been explored. Here, we introduce a nonlinear CLLN—an analog electronic network made of self-adjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR (exclusive or) and nonlinear regression, without a computer. We find our decentralized system reduces modes of training error in order (mean, slope, curvature), similar to spectral bias in artificial neural networks. The circuitry is robust to damage, retrainable in seconds, and performs learned tasks in microseconds while dissipating only picojoules of energy across each transistor. This suggests enormous potential for fast, low-power computing in edge systems like sensors, robotic controllers, and medical devices, as well as manufacturability at scale for performing and studying emergent learning.

Science & Technology - Other Topics↗
DOE OSTI2026

When does global attention help: a unified empirical study on atomistic graph learning

Graph neural networks (GNNs) are widely used as surrogates for costly experiments and first-principles simulations to study the behavior of compounds at atomistic scale, and their architectural complexity is constantly increasing to enable the modeling of complex physics. While most recent GNNs combine more traditional message passing neural networks (MPNNs) layers to model short-range interactions with more advanced graph transformers (GTs) with global attention mechanisms to model long-range interactions, it is still unclear when global attention mechanisms provide real benefits over well-tuned MPNN layers due to inconsistent implementations, features, or hyperparameter tuning. We introduce the first unified, reproducible benchmarking framework–built on HydraGNN–that enables seamless switching among four controlled model classes: MPNN, MPNN with chemistry/topology encoders, GPS-style hybrids of MPNN with global attention, and fully fused localglobal models with encoders. Using seven diverse open-source datasets for benchmarking across regression and classification tasks, we systematically isolate the contributions of message passing, global attention, and encoder-based feature augmentation. Our study shows that encoder-augmented MPNNs form a robust baseline, while fused localglobal models yield the clearest benefits for properties governed by long-range interaction effects. We further quantify the accuracycompute trade-offs of attention, reporting its overhead in memory. Together, these results establish the first controlled evaluation of global attention in atomistic graph learning and provide a reproducible testbed for future model development.

Equivariant graph neural networks↗
NASA NTRS2000

Cascade Optimization Strategy with Neural Network and Regression Approximations Demonstrated on a Preliminary Aircraft Engine Design

A preliminary aircraft engine design methodology is being developed that utilizes a cascade optimization strategy together with neural network and regression approximation methods. The cascade strategy employs different optimization algorithms in a specified sequence. The neural network and regression methods are used to approximate solutions obtained from the NASA Engine Performance Program (NEPP), which implements engine thermodynamic cycle and performance analysis models. The new methodology is proving to be more robust and computationally efficient than the conventional optimization approach of using a single optimization algorithm with direct reanalysis. The methodology has been demonstrated on a preliminary design problem for a novel subsonic turbofan engine concept that incorporates a wave rotor as a cycle-topping device. Computations of maximum thrust were obtained for a specific design point in the engine mission profile. The results (depicted in the figure) show a significant improvement in the maximum thrust obtained using the new methodology in comparison to benchmark solutions obtained using NEPP in a manual design mode.

Hopkins, Dale A.↗
NASA NTRS2006

Ozone Observations by the Gas and Aerosol Measurement Sensor during SOLVE II

The Gas and Aerosol Measurement Sensor (GAMS) was deployed aboard the NASA DC-8 aircraft during the second SAGE III Ozone Loss and Validation Experiment (SOLVE II). GAMS acquired line-of-sight (LOS) direct solar irradiance spectra during the sunlit portions of ten science flights of the DC-8 between 12 January and 4 February 2003. Differential line-of-sight (DLOS) optical depth spectra are produced from the GAMS raw solar irradiance spectra. Then, DLOS ozone number densities are retrieved from the GAMS spectra using a multiple linear regression spectral fitting technique. Both the DLOS optical depth spectra and retrieved ozone data are compared with coincident measurements from two other solar instruments aboard the DC-8 platform to demonstrate the robustness and stability of the GAMS data. The GAMS ozone measurements are then utilized to evaluate the quality of the Wulf band ozone cross sections, a critical component of the SAGE III aerosol, water vapor, and temperature/pressure retrievals. Results suggest the ozone cross section compilation of Shettle and Anderson currently used operationally in SAGE III data processing may be in error by as much as 10-20% in theWulf bands, and their lack of reported temperature dependence is a significant deficiency. A second, more recent, cross section database compiled for the SCIAMACHY satellite mission appears to be of much better quality in the Wulf bands, but still may have errors as large as 5% near the Wulf band absorption peaks, which is slightly larger than their stated uncertainty. Additional laboratory measurements of the Wulf band cross sections should be pursued to further reduce their uncertainty and better quantify their temperature dependence.

Pitts, M. C.↗
NASA NTRS2013

Statistical Issues in Galaxy Cluster Cosmology

The number and growth of massive galaxy clusters are sensitive probes of cosmological structure formation. Surveys at various wavelengths can detect clusters to high redshift, but the fact that cluster mass is not directly observable complicates matters, requiring us to simultaneously constrain scaling relations of observable signals with mass. The problem can be cast as one of regression, in which the data set is truncated, the (cosmology-dependent) underlying population must be modeled, and strong, complex correlations between measurements often exist. Simulations of cosmological structure formation provide a robust prediction for the number of clusters in the Universe as a function of mass and redshift (the mass function), but they cannot reliably predict the observables used to detect clusters in sky surveys (e.g. X-ray luminosity). Consequently, observers must constrain observable-mass scaling relations using additional data, and use the scaling relation model in conjunction with the mass function to predict the number of clusters as a function of redshift and luminosity.

Galaxy↗
DOE OSTI2024

Reduced-Order Modeling of Multigroup Neutron Cross Sections for High-Temperature Gas-cooled Reactors

Abstract – Deterministic neutronics calculations rely on multigroup neutron cross section libraries, which consist of databases of tabulated values, used to calculate the neutron cross sections through multivariate linear interpolation. However, interpolation of the multidimensional cross section data becomes memory inefficient and time consuming as the number of tabulations increases, significantly slowing down the neutronics calculation, especially in the case of microscopic cross section libraries where every isotope (on the order of hundreds) has its own set of specific reactions and cross sections. In order to address this challenge, this work constructs efficient and robust reduced-order models (ROMs) of the multi-group cross sections to support the Griffin simulation of high-temperature gas-cooled reactors (HTGRs). The first part of the study investigates the linearity of the multigroup cross section data across isotopes, reaction types, and energy groups on pre-generated datasets for the purpose of dimensionality reduction. Secondly, a down-selection of ROM techniques is presented on representative classical machine learning (ML) techniques, including variants of linear regression, kernel-based methods, tree-based algorithms, and artificial neural networks. The selection criteria jointly consider the memory efficiency, predictive accuracy, prediction speed, and scalability in comparison to the multidimensional interpolation. Among all the ML techniques, deep neural networks (DNNs) have proven to be the best selection with sufficient accuracy, high robustness, good memory efficiency, great scalability, and superior flexibility. DNNs have been trained for all isotopes in this work and systematic Griffin testing is ongoing to ensure the feasibility of this ROM technique for predicting cross section and reducing memory requirements without a significant sacrifice in computational performance.

42 - ENGINEERING↗