Search NASA⌕ Search

SEARCH · Search NASA

Results for “model interpretability”

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 145 records · Page 8

SRBench++: Principled Benchmarking of Symbolic Regression With Domain-Expert Interpretation

Symbolic regression searches for analytic expressions that accurately describe studied phenomena. The main promise of this approach is that it may return an interpretable model that can be insightful to users, while maintaining high accuracy. The current standard for benchmarking these algorithms is SRBench, which evaluates methods on hundreds of datasets that are a mix of real-world and simulated processes spanning multiple domains. At present, the ability of SRBench to evaluate interpretability is limited to measuring the size of expressions on real-world data, and the exactness of model forms on synthetic data. In practice, model size is only one of many factors used by subject experts to determine how interpretable a model truly is. Furthermore, SRBench does not characterize algorithm performance on specific, challenging sub-tasks of regression such as feature selection and evasion of local minima. In this work, we propose and evaluate an approach to benchmarking SR algorithms that addresses these limitations of SRBench by 1) incorporating expert evaluations of interpretability on a domain-specific task, and 2) evaluating algorithms over distinct properties of data science tasks. We evaluate 12 modern symbolic regression algorithms on these benchmarks and present an in-depth analysis of the results, discuss current challenges of symbolic regression algorithms and highlight possible improvements for the benchmark itself.

97 MATHEMATICS AND COMPUTING↗

An effective matrix model for dynamical end of the world branes in Jackiw-Teitelboim gravity

We study Jackiw-Teitelboim gravity with dynamical end of the world branes in asymptotically nearly AdS2 spacetimes. We quantize this theory in Lorentz signature, and compute the Euclidean path integral summing over topologies including dynamical branes. The latter will be seen to exactly match with a modification of the SSS matrix model. The resolution of UV divergences in the gravitational instantons involving the branes will lead us to understand the matrix model interpretation of the Wilsonian effective theory perspective on the gravitational theory. We complete this modified SSS matrix model nonperturbatively by extending the integration contour of eigenvalues into the complex plane. Furthermore, we give a new interpretation of other phases in such matrix models. We derive an effective W(Φ) dilaton gravity, which exhibits similar physics semiclassically. In the limit of a large number of flavors of branes, the effective extremal entropy S0,eff has the form of counting the states of these branes.

2D Gravity↗

Feedback, physics, and forecasts: The emerging paradigm of machine learning-driven battery research

Machine learning (ML) is reshaping how we understand, predict, and optimize electrochemical systems. In batteries, ML accelerates discovery across chemistry, design, and operation by transforming massive experimental and simulated datasets into predictive, interpretable models. This review consolidates a decade of progress in ML-driven battery innovation, from early-cycle feature extraction to operando image analysis and physics-informed modeling. We categorize approaches by data domain and physical fidelity, emphasizing interpretable ML for diagnostics, reinforcement learning for control, and multi-objective optimization for lifetime extension strategies. Additionally, we demonstrate how integrated models accelerate discovery, reduce testing time, and guide sustainable design. Economic analyses furthermore illustrate how these advances can lower cost per cycle and improve circularity. Together, these developments chart a path toward self-optimizing, sustainable battery technologies.

artificial intelligence↗

Interpretable Machine Learning Models for Autonomous Characterization of Analogue Ocean World Seawater Chemistry and Biosignature Potential Using Isotope Ratio Data

Background: Future missions to ocean worlds, such as Enceladus and Europa, will attempt to characterize the subsurface seawater chemistry and assess the potential for life. Such missions will be equipped with capabilities to precisely measure volatile isotopes in plumes, atmospheres, and exospheres. Motivation: While large isotopic fractionations can indicate a biological source, there are signatures resulting from abiotic geochemical processes that mimic isotopic biosignatures. While machine learning (ML) has the potential to disentangle competing effects and biotic mimicry, high-dimensional isotope ratio mass spectrometry (IRMS) data is likely to contain noise/irrelevant features and involve complex statistical interactions that make human inference and interpretation difficult. Further, ML predictions with as far-reaching implications as an extraterrestrial biosignature on an ocean world requires the use of interpretable models (i.e., not “black box” models) with physically and mathematically meaningful feature spaces along with false positive diagnostics. Methods: We use volatile CO2 IRMS data of analogue ocean world seawaters to validate an ML approach to provide biogeochemical context for biosignature detection. We employ a feature selection method called nearest-neighbor projected distance regression (NPDR) that detects statistical interactions and helps elucidate the mechanisms of the Random Forest classification models. Results: We train and validate predictive ML models on volatile CO2 IRMS data of analogue ocean world seawaters to predict major salt components (e.g., MgSO4, NaHCO3), pH, ionic strength, and the presence of biosignatures. Features derived from IRMS measurements are augmented with extracted time-series features. Our results show high test accuracy and interpretability, which is increased by interaction network visualization, sample-wise variable importance scores, and single-sample class probability estimates. We demonstrate an ML mission software solution that triggers autonomous data transmission and biogeochemical sample prediction.

geochemistry↗

Rapid calculation of terrain parameters for radiation modeling from digital elevation data

Digital elevation models are now widely used to calculate terrain parameters to determine incoming solar and longwave radiation for use in surface climate models, interpretation of remote-sensing data, and parameters in hydrologic models. Because of the large number of points in an elevation grid, fast algorithms are useful to save computation time. A description is given of rapid methods for calculating slope and azimuth, solar illumination angle, horizons, and view factors for radiation from sky and terrain. Calculation time is reduced by fast algorithms and lookup tables.

Dozier, Jeff↗

Machine Learning Correlation of Electron Micrographs and ToF-SIMS for the Analysis of Organic Biomarkers in Mudstone

The spatial distribution of organics in geological samples can be used to determine when and how these organics were incorporated into the host rock. Mass spectrometry (MS) imaging can rapidly collect a large amount of data, but ions produced are mixed without discrimination, resulting in complex mass spectra that can be difficult to interpret. Here, we apply unsupervised and supervised machine learning (ML) to help interpret spectra from time-of-flight-secondary ion mass spectrometry (ToF-SIMS) of an organic-carbon-rich mudstone of the Middle Jurassic of England (UK). It was previously shown that the presence of sterane molecular biomarkers in this sample can be detected via ToF-SIMS (Pasterski, M. J. et al., Astrobiology 2023, 23, 936). We use unsupervised ML on scanning electron microscopy–electron dispersive spectroscopy (SEM-EDS) measurements to define compositional categories based on differences in elemental abundances. We then test the ability of four ML algorithms─k-nearest neighbors (KNN), recursive partitioning and regressive trees (RPART), eXtreme gradient boost (XGBoost), and random forest (RF)─to classify the ToF-SIM spectra using (1) the categories assigned via SEM-EDS, (2) organic and inorganic labels assigned via SEM-EDS, and (3) the presence or absence of detectable steranes in ToF-SIMS spectra. In terms of predictive accuracy and balanced accuracy, KNN was the best performing model and RPART the worst. The feature importance, or the specific features of the ToF-SIM spectra used by the models to make classifications, cannot be determined for KNN, preventing posthoc model interpretation. Nevertheless, the feature importance extracted from the other models was useful for interpreting spectra. In conclusion, we determined that some of the organic ions used to classify biomarker containing spectra may be fragment ions derived from kerogen which is abundant in this mudstone sample.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Higgs searches beyond the Standard Model

While the existence of a Higgs boson with a mass near 125 GeV has been clearly established, the detailed structure of the entire Higgs sector is yet unclear. Besides the Standard Model interpretation, various possibilities for extended Higgs sectors are being considered. The minimal supersymmetric extension (MSSM) features two Higgs doublets resulting in five physical Higgs bosons, which are subject to direct searches. Alternatively, more generic Two-Higgs Doublet models (2HDM) are used for the interpretation of results. The Next-to-Minimal Supersymmetric Model (NMSSM) has a more complex Higgs sector with seven physical states. Also exotic Higgs bosons decaying to invisible final states are considered. This article summarizes recent findings based on results from collider experiments.

,NMSSM↗

Higgs Searches Beyond the Standard Model

While the existence of a Higgs boson with a mass near 125 GeV has been clearly established, the detailed structure of the entire Higgs sector is yet unclear. Besides the Standard Model interpretation, various possibilities for extended Higgs sectors are being considered. The minimal supersymmetric extension (MSSM) features two Higgs doublets resulting in five physical Higgs bosons, which are subject to direct searches. Alternatively, more generic Two-Higgs Doublet models (2HDM) are used for the interpretation of results. The Next-to-Minimal Supersymmetric Model (NMSSM) has a more complex Higgs sector with seven physical states. Also exotic Higgs bosons decaying to invisible final states are considered. This article summarizes recent findings based on results from collider experiments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Scalable Topological Data Analysis and Visualization for Evaluating Data-Driven Models in Scientific Applications

With the rapid adoption of machine learning techniques for large-scale applications in science and engineering comes the convergence of two grand challenges in visualization. First, the utilization of black box models (e.g., deep neural networks) calls for advanced techniques in exploring and interpreting model behaviors. Second, the rapid growth in computing has produced enormous datasets that require techniques that can handle millions or more samples. Although some solutions to these interpretability challenges have been proposed, they typically do not scale beyond thousands of samples, nor do they provide the high-level intuition scientists are looking for. Here, we present the first scalable solution to explore and analyze high-dimensional functions often encountered in the scientific data analysis pipeline. By combining a new streaming neighborhood graph construction, the corresponding topology computation, and a novel data aggregation scheme, namely topology aware datacubes, we enable interactive exploration of both the topological and the geometric aspect of high-dimensional data. Following two use cases from high-energy-density (HED) physics and computational biology, we demonstrate how these capabilities have led to crucial new insights in both applications.

97 MATHEMATICS AND COMPUTING↗

A best-practice guide to predicting plant traits from leaf-level hyperspectral data using partial least squares regression

Partial least squares regression (PLSR) modelling is a statistical technique for correlating datasets, and involves the fitting of a linear regression between two matrices. One application of PLSR enables leaf traits to be estimated from hyperspectral optical reflectance data, facilitating rapid, high-throughput, non-destructive plant phenotyping. This technique is of interest and importance in a wide range of contexts including crop breeding and ecosystem monitoring. The lack of a consensus in the literature on how to perform PLSR means that interpreting model results can be challenging, applying existing models to novel datasets can be impossible, and unknown or undisclosed assumptions can lead to incorrect or spurious predictions. We address this lack of consensus by proposing best practices for using PLSR to predict plant traits from leaf-level hyperspectral data, including a discussion of when PLSR is applicable, and recommendations for data collection. Further, we provide a tutorial to demonstrate how to develop a PLSR model, in the form of an R script accompanying this manuscript. This practical guide will assist all those interpreting and using PLSR models to predict leaf traits from spectral data, and advocates for a unified approach to using PLSR for predicting traits from spectra in the plant sciences.

54 ENVIRONMENTAL SCIENCES↗

Advanced geophysical underground coal gasification monitoring

Underground Coal Gasification (UCG) produces less surface impact, atmospheric pollutants and greenhouse gas than traditional surface mining and combustion. Therefore, it may be useful in mitigating global change caused by anthropogenic activities. Careful monitoring of the UCG process is essential in minimizing environmental impact. In this paper, we first summarize monitoring methods that have been used in previous UCG field trials. We then discuss in more detail a number of promising advanced geophysical techniques. These methods – seismic, electromagnetic, and remote sensing techniques – may provide improved and cost-effective ways to image both the subsurface cavity growth and surface subsidence effects. Active and passive seismic data have the promise to monitor the burn front, cavity growth, and observe cavity collapse events. Electrical resistance tomography (ERT) produces near real time tomographic images autonomously, monitors the burn front and images the cavity using low-cost sensors, typically running within boreholes. Interferometric synthetic aperture radar (InSAR) is a remote sensing technique that has the capability to monitor surface subsidence over the wide area of a commercial-scale UCG operation at a low cost. It may be possible to infer cavity geometry from InSAR (or other surface topography) data using geomechanical modeling. The expected signals from these monitoring methods are described along with interpretive modeling for typical UCG cavities. They are illustrated using field results from UCG trials and other relevant subsurface operations.

01 COAL, LIGNITE, AND PEAT↗

Streaming Generalized Canonical Polyadic Tensor Decompositions

In this paper, we develop a method which we call OnlineGCP for computing the Generalized Canonical Polyadic (GCP) tensor decomposition of streaming data. GCP differs from traditional canonical polyadic (CP) tensor decompositions as it allows for arbitrary objective functions which the CP model attempts to minimize. This approach can provide better fits and more interpretable models when the observed tensor data is strongly non-Gaussian. In the streaming case, tensor data is gradually observed over time and the algorithm must incrementally update a GCP factorization with limited access to prior data. In this work, we extend the GCP formalism to the streaming context by deriving a GCP optimization problem to be solved as new tensor data is observed, formulate a tunable history term to balance reconstruction of recently observed data with data observed in the past, develop a scalable solution strategy based on segregated solves using stochastic gradient descent methods, describe a software implementation that provides performance and portability to contemporary CPU and GPU architectures and integrates with Matlab for enhanced usability, and demonstrate the utility and performance of the approach and software on several synthetic and real tensor data sets.

97 MATHEMATICS AND COMPUTING↗

Space Shuttle Main Engine structural analysis and data reduction/evaluation. Volume 6: Primary nozzle diffuser analysis

The primary nozzle diffuser routes fuel from the main fuel valve on the Space Shuttle Main Engine (SSME) to the nozzle coolant inlet mainfold, main combustion chamber coolant inlet mainfold, chamber coolant valve, and the augmented spark igniters. The diffuser also includes the fuel system purge check valve connection. A static stress analysis was performed on the diffuser because no detailed analysis was done on this part in the past. Structural concerns were in the area of the welds because approximately 10 percent are in areas inaccessible by X-ray testing devices. Flow dynamics and thermodynamics were not included in the analysis load case. Constant internal pressure at maximum SSME power was used instead. A three-dimensional, finite element method was generated using ANSYS version 4.3A on the Lockheed VAX 11/785 computer to perform the stress computations. IDEAS Supertab on a Sun 3/60 computer was used to create the finite element model. Rocketdyne drawing number RS009156 was used for the model interpretation. The flight diffuser is denoted as -101. A description of the model, boundary conditions/load case, material properties, structural analysis/results, and a summary are included for documentation.

Foley, Michael J.↗

Interpretable boosted-decision-tree analysis for the Majorana Demonstrator

The Majorana Demonstrator is a leading experiment searching for neutrinoless double-beta decay with high purity germanium detectors (HPGe). Machine learning provides a new way to maximize the amount of information provided by these detectors, but the data-driven nature makes it less interpretable compared to traditional analysis. An interpretability study reveals the machine's decision-making logic, allowing us to learn from the machine to feedback to the traditional analysis. In this work, we have presented the first machine learning analysis of the data from the Majorana Demonstrator; this is also the first interpretable machine learning analysis of any germanium detector experiment. Two gradient boosted decision tree models are trained to learn from the data, and a game-theory-based model interpretability study is conducted to understand the origin of the classification power. By learning from data, this analysis recognizes the correlations among reconstruction parameters to further enhance the background rejection performance. By learning from the machine, this analysis reveals the importance of new background categories to reciprocally benefit the standard Majorana analysis. This model is highly compatible with next-generation germanium detector experiments like LEGEND since it can be simultaneously trained on a large number of detectors.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Evaluation of usefulness of Skylab EREP S-190 and S-192 imagery in multistage forest surveys

The author has identified the following significant results. A high-flight U-2 imagery (1:120,000) volume interpretation model was developed which could be used to explain 50% of the volume variation occurring on the ground. Two interpreters interpreted 40 GLO land sections with known timber volume in terms of eight variables that could be estimated from the imagery. A multiple regression study was performed to relate the interpreted variables to the ground volumes. It was found that the best model consisted of two basic variables and their squares, namely: (1) the percentage of large trees, and (2) the crown density of the conifers on the parcel. The multiple correlation coefficient was 0.694 for this model.

Langley, P. G.↗

A methodology for decay heat characterization in molten salt reactors

Accurate decay heat prediction in molten salt reactors (MSRs) faces dual challenges: complex operational uncertainties and the need for interpretable models compatible with engineering workflows. This work presents a hybrid machine learning and segmented polynomial methodology that addresses both requirements through three key innovations. First, a modular data architecture encodes MSR-specific operational parameters (power density: 1-100 W cm -3 , humidity: 0-0.1 wt %, air ingress: 0-0.1 mol %) with uncertainty-aware temporal discretization spanning 15 orders of magnitude. Second, region-optimized machine learning models achieve 92.3 % root mean square error (RMSE) reduction over conventional polynomials while maintaining physical interpretability through automated piecewise equation generation. Third, dual front-end interfaces accelerate safety analyses — a Jupyter environment enables researchers to explore 10,000+ parameter combinations via interactive widgets, while a Streamlit web application reduces design iteration cycles through production-grade visualization tools. Operational deployment demonstrates prediction times of only a couple hundred milliseconds for 10 4 years decay profiles, enabling real-time optimization of spent fuel container designs.

42 - ENGINEERING↗

Including frameworks of public health ethics in computational modelling of infectious disease interventions

Decisions on public health interventions to control infectious diseases are often informed by computational models. Interpreting the predicted outcomes of a public health decision requires not only high-quality modelling but also an ethical framework for assessing the benefits and harms associated with different options. The design and specification of ethical frameworks matured independently of computational modelling, so many values recognized as important for ethical decision-making are missing from computational models. We demonstrate a proof-of-concept approach to incorporate multiple public health values into the evaluation of a simple computational model for vaccination against a pathogen such as SARS-CoV-2. By examining a bounded space of alternative prioritizations of three values relevant to public health ethics (aggregate clinical burden, equity in clinical burden, equity in adverse effects from vaccination), we identify value trade-offs, where the outcomes of optimal strategies differ depending on the ethical framework. This work demonstrates an approach to incorporating diverse values into decision criteria used to evaluate outcomes of models of infectious disease interventions.

"Mathematical Biology"↗