Search NASA⌕ Search

SEARCH · Search NASA

Results for “SHAP”

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

Charting the chemical space of Zintl phases with graph neural networks and bonding insights

A large number of Zintl phases have been discovered by solid-state chemists driven by empirical knowledge, chemical intuition and in some cases, through serendipitous accidents. These discoveries have only scratched the surface, given the vast compositional and structural diversity that Zintl phases can accommodate. The large chemical space of Zintl phases, as well as intermetallic compounds in general, remain under-explored. Here, we use graph neural networks and the upper bound energy minimization approach to efficiently scan a large chemical space of >90 000 hypothetical Zintl phases and accurately discover 1810 new thermodynamically stable phases with 90% precision, as validated with first-principles calculations. We show that our approach is more than 2× more accurate in predicting DFT stability than M3GNet (40% precision) on the same dataset. Using a random forest model and SHAP analysis, we demonstrate the critical role of ionic bonding in the thermodynamic stability of Zintl phases. Our results not only expand the known chemical landscape of Zintl phases but also highlight the efficacy of machine learning frameworks combined with domain knowledge in uncovering chemically meaningful insights across complex intermetallics.

36 MATERIALS SCIENCE↗
DOE OSTI2023

How can a diverse set of integral and semi-integral measurements inform identification of discrepant nuclear data?

Nuclear data are used for a variety of applications, including criticality safety, reactor performance, and material safeguards. Despite the breadth of use-cases, the effective neutron multiplication factor, keff, of ICSBEP critical assemblies are primarily used for nuclear data validation; these are sensitive to specific energy regions and nuclides and are unable to uniquely constrain nuclear data. As a consequence, general-purpose nuclear data libraries, such as ENDF/B-VIII.0, may have deficiencies that, while not apparent in criticality applications, negatively impact other applications, such as non-destructive analysis of special nuclear material and neutron diagnosed subcritical experiments. Recent work by the Experiments Underpinned by Computational Learning for Improvements in Nuclear Data (EUCLID) project developed a machine learning tool, RAFIEKI, which uses random forests and the SHAP metric to determine which nuclear data contribute most to predicted bias between measured and simulated responses (e.g. keff). This paper contrasts RAFIEKI analysis applied to keff only against RAFIEKI analysis with keff paired with either LLNL pulsed sphere measurements or subcritical benchmarks. Two examples show that a) including pulsed sphere measurements substantially increases 9Be nuclear data importance to bias between 2 and 15 MeV, and b) including subcritical benchmarks has the potential for disentangling compensating errors between 240Pu (n,el) and (n,il) cross-sections between 0.1 and 10 MeV. These results show that RAFIEKI analysis applied to response sets that include, but go beyond, keff can aid nuclear data evaluators in identifying issues in nuclear data.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Exploring the Effects of Population and Employment Characteristics on Truck Flows: An Analysis of NextGen NHTS Origin-Destination Data

Truck transportation remains the dominant mode of US freight transportation because of its advantages, such as the flexibility of accessing pickup and drop-off points and faster delivery. Because of the massive freight volume transported by trucks, understanding the effects of population and employment characteristics on truck flows is critical for better transportation planning and investment decisions. The US Federal Highway Administration published a truck travel origin-destination data set as part of the Next Generation National Household Travel Survey program. This data set contains the total number of truck trips in 2020 within and between 583 predefined zones encompassing metropolitan and nonmetropolitan statistical areas within each state and Washington, DC. In this study, origin-destination-level truck trip flow data was augmented to include zone-level population and employment characteristics from the US Census Bureau. Census population and County Business Patterns data were included. The final data set was used to train a machine learning algorithm-based model, Extreme Gradient Boosting (XGBoost), where the target variable is the number of total truck trips. Shapley Additive ExPlanation (SHAP) was adopted to explain the model results. Results showed that the distance between the zones was the most important variable and had a nonlinear relationship with truck flows.

Uddin, Majbah↗
DOE OSTI2026

Explaining System-Level Prognostics with Established Machine Learning Methods

System-level prognostics is crucial for ensuring reliability and enabling predictive maintenance in complex systems with interconnected components. This study presents a framework that integrates data-driven methods to predict the remaining useful life (RUL) of a subsystem under multiple and concurrent faults within a nuclear power plant system with explainable artificial intelligence (XAI). A nuclear power plant (NPP) operation was simulated to model the degradation behavior of NPP components, and four machine learning models—Gradient Boosting Regressor (GBR), Support Vector Regressor (SVR), Fully Connected Neural Network (FCNN), and Long Short-Term Memory (LSTM)—were evaluated for prognostics with a novel system RUL parameter. The LSTM model demonstrated potential superior repeatability, while SHAP (SHapley Additive exPlanations) for explainability provided consistent and trustworthy global explanations. In contrast, LIME (Local Interpretable Model-agnostic Explanations) offered localized interpretability but showed reduced stability for sequential data. Key findings include the interplay between component-level degradation and system-wide performance, with LSTM effectively capturing these dynamics through sequence-level predictions. The XAI techniques enhanced transparency by identifying critical features influencing model predictions and aligning with domain knowledge. Furthermore, this framework has significant implications for improving trust and understanding in predictive maintenance, particularly in safety-critical industries like nuclear energy.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

The Role of Nuclear Data Sensitivities in Prompt α-Eigenvalue Predictions of Delayed Critical Benchmarks

Alpha (α) eigenvalues, which describe the logarithmic time derivative of the neutron population in a multiplying system, are integral to time-dependent behavior and diagnostic applications. However, uncertainties in the evaluated nuclear data can significantly impact the accuracy of transport simulations for such quantities. This work explores the use of machine learning models to predict two key outputs, α-eigenvalues and keff bias, using input features derived from α-eigenvalue sensitivities to nuclear data. The criticality safety benchmark models used in this study come from the International Handbook of Evaluated Criticality Safety Benchmark Experiments. Three models, random forest, XGBoost, and NGBoost, are trained on both energy-resolved and energy-summed α sensitivities. For the α-eigenvalue bias prediction, NGBoost achieved the highest R 2 (0.9476) using energy-resolved features, while XGBoost performed best using summed sensitivities. In contrast, when predicting the keff bias, all the models showed moderate predictive capability (best R 2 ≈ 0.72), as the mapping from the static α-sensitivities to the static keff bias was less direct. SHAP (SHapley Additive exPlanations) analysis was used to interpret the model predictions. Across both prediction tasks, the features associated with neutron capture [H-1 (n, γ)], uranium scattering reactions (such as 235 U elastic/inelastic), and actinide capture/fission reactions (such as 239 Pu and 234 U) were consistently identified as the most impactful. This highlights the key role of specific nuclear reactions and energy ranges in shaping both time-dependent and steady-state criticality behavior. These results demonstrated that α-sensitivities, despite being computed for time-dependent metrics, can provide valuable insights for predicting both α-eigenvalues and the keff bias. Moreover, machine learning models offer a promising pathway for uncovering important nuclear data dependencies and guiding future data evaluation efforts.

Nuclear data↗
DOE OSTI2025

Short-Term Energy and Meteorological Impacts on Thanksgiving CO2 in Salt Lake City

Abstract Long-term, high-frequency atmospheric CO2 measurements at multiple sites in the Salt Lake City (SLC), Utah, reveal that annual and monthly CO2 variability aligns with a priori estimates of emissions from anthropogenic and biological sources. In this study, we investigate whether short-term fluctuations in anthropogenic emissions, as captured in the Vulcan3 dataset for the United States, can be detected in atmospheric CO2 observations. Specifically, we focus on Thanksgiving holidays, when traffic and energy usage patterns differ from the rest of November. Onroad CO2 emissions exhibit a double peak during weekday morning and evening rush hours but remain relatively low on weekends and Thanksgiving. Interestingly, CO2 mole fractions during Thanksgiving were higher than the rest of November at all SLC monitoring sites, particularly from 2008 to 2013. This increase is partially attributed to elevated energy-related emissions — especially residential sources — and meteorological factors such as weak wind speeds, cold temperature, and a low planetary boundary layer height (PBLH).

 While CO₂ emissions and mole fraction patterns align over time, notable spatial differences exist. For instance, the near-highway site in Murray shows the highest CO₂ mole fractions despite low local emissions, suggesting pollution transport via highways and wind advection. Random Forest model-based SHapley Additive exPlanations (SHAP) analysis reveals that onroad emissions dominate CO2 contributions on weekdays and weekends, while energy-related emissions play a larger role during Thanksgiving, alongside meteorological drivers such as wind speed and PBLH. Across six urban cities, CO2 emissions display a consistent pattern: residential and commercial (onroad) emissions peak during Thanksgiving (weekday) with substantial (minimal) year-to-year variability. These findings highlight that urban CO₂ variability is driven by the combined influence of emissions and meteorology, underscoring the need for integrated mitigation strategies. Additionally, multi-site measurements are essential for accurate source attribution and the development of effective policy interventions. 

Ryoo, Ju-Mee (ORCID:0000000234256296)↗
DOE OSTI2023

Exploring the dependence of gas cooling and heating functions on the incident radiation field with machine learning

ABSTRACT Gas cooling and heating functions play a crucial role in galaxy formation. But, it is computationally expensive to exactly compute these functions in the presence of an incident radiation field. These computations can be greatly sped up by using interpolation tables of pre-computed values, at the expense of making significant and sometimes even unjustified approximations. Here, we explore the capacity of machine learning to approximate cooling and heating functions with a generalized radiation field. Specifically, we use the machine learning algorithm XGBoost to predict cooling and heating functions calculated with the photoionization code cloudy at fixed metallicity, using different combinations of photoionization rates as features. We perform a constrained quadratic fit in metallicity to enable a fair comparison with traditional interpolation methods at arbitrary metallicity. We consider the relative importance of various photoionization rates through both a principal component analysis (PCA) and calculation of SHapley Additive exPlanation (shap) values for our XGBoost models. We use feature importance information to select different subsets of rates to use in model training. Our XGBoost models outperform a traditional interpolation approach at each fixed metallicity, regardless of feature selection. At arbitrary metallicity, we are able to reduce the frequency of the largest cooling and heating function errors compared to an interpolation table. We find that the primary bottleneck to increasing accuracy lies in accurately capturing the metallicity dependence. This study demonstrates the potential of machine learning methods such as XGBoost to capture the non-linear behaviour of cooling and heating functions.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Interpretable Data-Driven Probabilistic Power System Load Margin Assessment with Uncertain Renewable Energy and Loads

The increasing uncertainties caused by the high-penetration of stochastic renewable generation resources poses a significant threat to the power system voltage stability. To address this issue, this paper proposes a probabilistic deep kernel learning enabled surrogate model to extract the hidden relationship between uncertain sources, i.e., wind power and loads, and load margin for probabilistic load margin assessment (PLMA). Unlike other deep learning approaches, a kernel SHAP provides the sensitivity analysis as well as interpretability of the inputs to outputs influences. This allows identifying the critical factors that affect load margin so that corrective control can be initiated for stability enhancement. Numerical results carried out on the IEEE 118-bus power system demonstrate the accuracy and efficiency of the proposed data-driven PLMA scheme.

deep kernel learning↗
DOE OSTI2024

Topological Interpretability for Deep Learning

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based decision systems is an increasing concern, especially in high-risk systems such as criminal justice or medical diagnosis, where incorrect inferences may have tragic consequences. Despite their successes in providing solutions to problems involving real-world data, deep learning (DL) models cannot quantify the certainty of their predictions. These models are frequently quite confident, even when their solutions are incorrect. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text by employing techniques from topological and geometric data analysis. We create a graph of a model's feature space and cluster the inputs into the graph's vertices by the similarity of features and prediction statistics. We then extract subgraphs demonstrating high-predictive accuracy for a given label. These subgraphs contain a wealth of information about features that the DL model has recognized as relevant to its decisions. We infer these features for a given label using a distance metric between probability measures, and demonstrate the stability of our method compared to the LIME and SHAP interpretability methods. This work establishes that we may gain insights into the decision mechanism of a DL model. This method allows us to ascertain if the model is making its decisions based on information germane to the problem or identifies extraneous patterns within the data.

Spannaus, Adam↗
DOE OSTI2023

Gamma-ray Spectrum Explanations (GRSE) v0.1

This code repository provides tools for producing various types of machine learning model explanations trained on gamma-ray spectra. It includes implementations of saliency mapping, Grad-CAM, LIME, and Kernel SHAP, including improvements and clarifications to some of the approaches that are specific to their use with gamma-ray spectral data. These tools are in support of the manuscript M.S. Bandstra et al., "Explaining machine-learning models for gamma-ray detection and identification," under review at PLOS ONE.

Bandstra, Mark↗
DOE OSTI2025

Data Agnostic Feature-Target Analysis & Ranking Machine Learning Pipeline (DAFTAR-ML) v0.1.0

DAFTAR-ML is a specialized machine-learning pipeline that identifies relevant features based on their relationship to a target variable. Many ML pipelines focus solely on prediction, and feature ranking is often absent or lacks robust statistical methods. DAFTAR-ML performs its tasks with this outcome in mind. Model training is robust, using nested cross-validation and hyperparameter tuning. Instead of relying on native feature-importance scores, it employs SHAP (SHapley Additive exPlanations) to quantify feature importance. The pipeline also produces comprehensive results, including publication-quality visualizations.

Melie, Tina [Lawrence Berkeley National Laboratory↗
DOE OSTI2024

Remote Sensing and GIS data at 1km-grid over Chesapeake Bay used in “He et al. 2024, Effects of spatial variability in vegetation phenology, climate, landcover, biodiversity, topography, and soil property on soil respiration across a coastal ecosystem”

The package contains the data layers used in “He et al. 2024, Effects of spatial variability in vegetation phenology, climate, landcover, biodiversity, topography, and soil property on soil respiration across a coastal ecosystem”. The study aims to use multi-source remote sensing and GIS datasets to investigate the spatial heterogeneity and identify spatial zones with similar environmental characteristics and understand the primary driving factors affecting soil respiration within sub-ecosystems of the coastal ecosystem. We employed unsupervised hierarchical clustering analysis to identify spatial regions with distinct environmental characteristics, then determined the main driving factors using Random Forest regression and SHapley Additive exPlanations (SHAP). Spatial data layers include soil respiration, kernel Normalized Difference Vegetation Index (kNDVI) computed from Harmonized Landsat 8 and Sentinel-2 time series, climate variables from the Daymet dataset, land cover, biodiversity, topographical metrics, soil property, and tidal elevation.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Integrating Experiments and Well Logs to Predict Caney Shale Static Mechanical Properties During Production with Supervised Machine Learning

Caney shale is one of the emerging oil reservoirs in Oklahoma. Understanding the impact of effective stress on its mechanical properties is critical for predicting hydraulic fracture geometry and overall hydrocarbon production. The objective of our study is to evaluate the impact of effective stress on the dynamic Young’s modulus using ultrasonic velocity measurements for Caney shale samples. A triaxial cell was utilized to measure ultrasonic (P-wave and S-wave) velocities for ten downhole Caney shale samples under various effective stresses to indirectly assess the impact of pore pressure change. The dynamic Young’s moduli estimated from these measurements were integrated with available conventional well logs (excluding sonic logs) and triaxial test results from Benge et al. (2021) to predict the static Young’s modulus using Random Forest (RF) and Extreme Gradient Boosting (XGBoost) models. The results showed that the estimated dynamic Young’s moduli from ultrasonic measurements were higher than the corresponding static Young’s modulus of cores from the same vertical well at similar depths. With increasing effective stress, the dynamic Young’s modulus increased for all samples. The estimated dynamic-to-static correction factor tended to be higher in zones of high neutron porosity (PHIN) and low density compared to other zones. Finally, SHapley Additive exPlanations (SHAP) for RF and XGBoost models identified depth, gamma ray (GR), and PHIN as key features for predicting the static Young’s modulus. This study enhances our understanding of the dynamic and static Young’s moduli for the Caney shale interval, as a function of effective stress and conventional well logs. The findings from this study can improve predictions of production throughout the well's lifespan by offering insights into the mechanical property degradation resulting from pore pressure depletion.

Kholy, Sherif M.↗
DOE OSTI2025

Simultaneous prediction of structural properties in epitaxially–grown GaN with quantum and conventional multi–output learning algorithms

Hundreds of GaN thin film crystal plasma–assisted molecular beam epitaxy synthesis experiment records spanning two decades were organized into a dataset correlating the growth experiment design parameters with discrete, binary determinations of crystallinity and surface morphology. Conventional data science techniques as well as both quantum and classical multi–output supervised machine learning algorithms were implemented to investigate the relationships between the operating parameter data and the structural figures of merit. Correlation coefficients, decision tree nodes, p–values, and SHAP values all support substrate temperature and gallium effusion cell conditions as being statistically significant for simultaneously influencing GaN crystallinity and surface morphology. Here, a conventional deep neural network learned best from the data, followed by a quantum–classical hybrid gradient boosting algorithm. When combined with calculations of uncertainty intervals based on VennAbers predictors, machine learning predictions of both structural properties show good agreement with results reported in published experimental literature.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Discovery of Innovative Polymers for Next-Generation Gas-Separation Membranes using Interpretable Machine Learning

Polymer membranes perform innumerable separations with far-reaching environmental implications. Despite decades of research on membrane technologies, design of new membrane materials remains a largely Edisonian process. To address this shortcoming, we demonstrate a generalizable, accurate machine-learning (ML) implementation for the discovery of innovative polymers with ideal separation performance. Specifically, multitask ML models are trained on available experimental data to link polymer chemistry to gas permeabilities of He, H2, O2, N2, CO2, and CH4. Here, we interpret the ML models and extract chemical heuristics for membrane design, through Shapley Additive exPlanations (SHAP) analysis. We then screen over nine million hypothetical polymers through our models and identify thousands of candidates that lie well above current performance upper bounds. Notably, we discover hundreds of never-before-seen ultrapermeable polymer membranes with O2 and CO2 permeability greater than 104 and 105 Barrer, respectively. These hypothetical polymers are capable of overcoming undesirable trade-off relationship between permeability and selectivity, thus significantly expanding the currently limited library of polymer membranes for highly efficient gas separations. High-fidelity molecular dynamics simulations confirm the ML-predicted gas permeabilities of the promising candidates, which suggests that many can be translated to reality.

Yang, Jason↗
DOE OSTI2021

Application of a machine learning algorithm (XGBoost) to offline RHIC luminosity optimization

The operation parameter optimization in 2020 RHIC low energy run is difficult. First, the RHIC luminosity is affected by many RHIC operation parameters, as well as affected by many Low Energy RHIC electron Cooling (LEReC) operation parameters. Second, the luminosity signal in this run is noisy and not sensitive to these parameter changes, especially when these parameters are very close to their optimized values. It is not easy to distinguish the effects of one parameter from all other operation parameters separately. Therefore, it is difficult to optimize the luminosity by varying these parameters one by one. To find a way for luminosity optimization, we analyze some operation parameters via a machine learning algorithm - XGBoost. After constructing a black-box surrogate model from XGBoost and plotting their partial dependency plots (PDF) and SHAP value plots for different operation parameters, we can find the effects of an individual parameter on the RHIC luminosity and optimize it accordingly.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Evaluating large scale aqueous organic redox flow battery performance with a hybrid numerical and machine learning framework

Aqueous organic redox flow battery (AORFB) is a promising cost-competitive technology for large-scale energy storage. Among existing work, the dihydroxyphenazine (DHP)-based AORFB has demonstrated high energy density and low-capacity degradation in 10 cm$^2$ cells during lab tests. However, its commercial-scale performance in more complex environments remains unknown, posing a barrier to commercialization. To address this gap, this work presents a comprehensive performance evaluation of a 780 cm$^2$ DHP-based AORFB by combining a physics-based numerical model, machine learning (ML)-based surrogate models, and ML-derived sensitivity quantification. Specifically, we first select 12 key battery parameters that include 10 physicochemical and 2 operation quantities, then select 6 performance metrics that include energy efficiency (EE), discharging capacity, charging energy, and power losses due to concentration, activation, and ohmic over-potentials. With such selection, 12800 combinations of the 12 parameters are subsequently generated using the Latin Hypercube Sampling method. Such combinations, together with 38 pre-defined State of Charge, are then integrated to a validated AORFB model developed in COMSOL to compute the performance metrics. With both input parameters and performance metrics, 60 deep neural network (DNN) surrogate models are then trained to approximate the relationship between the 10 physicochemical quantities and 6 performance metrics at each flow rate and current density. Sensitivity scores are then calculated based on the DNN models. Two additional sensitivity analysis tools, i.e., MARS, and SHAP, are also used to cross-validate the sensitivity scores from the DNN. The results demonstrate that 1) the standard potential ranks first in controlling EE and charging energy, 2) the membrane conductivity is most critical for power loss and EE, and 3) specific area and reaction rate control activation power loss.

25 ENERGY STORAGE↗
DOE OSTI2024

TCR-H: explainable machine learning prediction of T-cell receptor epitope binding on unseen datasets

Artificial-intelligence and machine-learning (AI/ML) approaches to predicting T-cell receptor (TCR)-epitope specificity achieve high performance metrics on test datasets which include sequences that are also part of the training set but fail to generalize to test sets consisting of epitopes and TCRs that are absent from the training set, i.e., are ‘unseen’ during training of the ML model. We present TCR-H, a supervised classification Support Vector Machines model using physicochemical features trained on the largest dataset available to date using only experimentally validated non-binders as negative datapoints. TCR-H exhibits an area under the curve of the receiver-operator characteristic (AUC of ROC) of 0.87 for epitope ‘hard splitting’ (i.e., on test sets with all epitopes unseen during ML training), 0.92 for TCR hard splitting and 0.89 for ‘strict splitting’ in which neither the epitopes nor the TCRs in the test set are seen in the training data. Furthermore, we employ the SHAP (Shapley additive explanations) eXplainable AI (XAI) method for post hoc interrogation to interpret the models trained with different hard splits, shedding light on the key physiochemical features driving model predictions. TCR-H thus represents a significant step towards general applicability and explainability of epitope:TCR specificity prediction.

60 APPLIED LIFE SCIENCES↗