Search NASA⌕ Search

SEARCH · Search NASA

Results for “interpretable machine learning”

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 649 records · Page 36
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Supporting Risk-informed Decision-making During Reactor Accidents

Uncertainty in severe accident evolution and outcome is driven by event bifurcations that represent distinctive challenges to defensive layers and tend to promote the emergence of discrete classes of core damage and accident risk. This discrete set of "attractor" states arise from the complex networks of competing physical phenomena and conditional event cascades occurring as the overall system degrades – a process that yields increasing degrees of freedom and accident progression pathways. Characterization of these event spaces has proven elusive to more traditional data interrogation methods, but proves tractable by application of more advanced data collection and machine learning approaches. Through application of these approaches we demonstrate a conceptual framework that enables real-time/robust, risk-informed decision-making support to improve accident mitigation and encourage “graceful exits” during low probability, extreme events limiting accident consequences. In this analysis, we simulated over 8,000 short-term station blackout (STSBO) accidents with the state-of-the-art integral severe accident code, MELCOR, and demonstrate the potential for ML approaches to predict simulation outcomes. We chose to pair ML tools with interpretable and mechanistic event trees for the considered STSBO accident space to predict the likelihood of future event paths along the tree. In addition to the current state of the system, we use information from recent trajectories of temperature, pressure, and other physical features, combining both the current state and past trajectories to forecast future event paths. Finally, we simulate the random injection of variable amounts of water to quantify the efficacy of available actions at reducing risks along the many branches in the event tree. We identify scenarios and windows of opportunity to mitigate risk as well as scenarios in which such actions are unlikely to alter the accident end-state.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems

We report faults in Heating, Ventilation, and Air Conditioning (HVAC) systems of buildings result in significant energy waste in building operation. With fast-growing sensing data availability and advancement in computing, computational modeling has demonstrated strong capability to detect and diagnose HVAC system faults, hence, ensuring efficient building operation. This paper comprehensively reviews the state-of-the-art computing-based fault detection and diagnosis (FDD) for HVAC systems. Overall, the reviewed computing-based FDD methods are classified as two major approaches: knowledge-based and data-driven approaches. We then identify multiple important topics, including data availability, training data size, data quality, approach generality, capability, interpretability, and required modeling efforts, along with corresponding metrics to summarize the most updated FDD development. Generally, the knowledge-based approaches are further divided as physics-based modeling, Diagnostic Bayesian Network, and performance indicator-based methods while data-driven approaches include supervised learning, unsupervised learning, and regression and statistics-based methods. State-of-the-art FDD development, remaining challenges, and future research directions are further discussed to push forward FDD in practice. Availability of fault data, capability of existing methods to deal with complex fault situations (such as simultaneous faults), modeling interpretability for data-driven methods, and required engineering efforts for physics-based methods are identified as remaining challenges in FDD development. Improving modeling fidelity and reducing modeling efforts are essential for applying physics-based methods in real buildings. Meanwhile, addressing fault data availability, increasing algorithm adaptability, and handling multiple faults are essential to further enhance the applicability of data-driven FDD approaches.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

Revealing Local Structures through Machine-Learning-Fused Multimodal Spectroscopy

Atomistic structures of materials offer valuable insights into their functionality. Determining these structures remains a fundamental challenge in materials science, especially for systems with defects. While both experimental and computational methods exist, each has limitations in resolving nanoscale structures. Core-level spectroscopies, such as X-ray absorption (XAS) or electron energy-loss spectroscopies (EELS), have been used to determine the local bonding environment and structure of materials. Recently, machine learning (ML) methods have been applied to extract structural and bonding information from XAS/EELS data. However, frameworks relying solely on a single data stream, defined as characterization data derived from a single element using one technique, are often insufficient because multiple local environments can yield similar spectral features, making it challenging to differentiate between competing structural hypotheses. Here, in this work, we address this challenge by integrating multimodal ab initio simulations, experimental data acquisition, and ML techniques for structure characterization. Our goal is to determine local structures and properties using EELS and XAS data from multiple elements and edges. To showcase our approach, we use various lithium nickel manganese cobalt (NMC) oxide compounds which are used for lithium ion batteries, including those with oxygen vacancies and antisite defects, as the sample material system. We successfully inferred local element content, ranging from lithium to transition metals, with quantitative agreement with experimental data. Beyond local element inference, we find that ML model based on multimodal spectroscopic data is able to determine whether local defects such as oxygen vacancy and antisites are present, a task which is impossible for single mode spectra or other experimental techniques. Furthermore, our framework is able to provide physical interpretability, bridging spectroscopy with the local atomic and electronic structures.

battery↗
DOE OSTI2025

Solving high-dimensional partial integral differential equations: The finite expression method

Partial integro-differential equations (PIDEs) have broad applications in the sciences, from electro-magnetism to options pricing. Here, in this paper, we introduce a new finite expression method (FEX) to solve PIDEs. This approach builds upon the original FEX and its inherent advantages with new advances: 1) A novel method of parameter grouping is proposed to reduce the number of coefficients in high-dimensional function approximation; 2) A Taylor series approximation method is implemented to significantly improve the computational efficiency and accuracy of the evaluation of the integral terms of PIDEs. The new FEX based method, denoted FEX-PG to indicate the addition of the parameter grouping (PG) step to the algorithm, provides both high accuracy and interpretable numerical solutions, with the outcome being an explicit equation that facilitates intuitive understanding of the underlying solution structures. These features are often absent in traditional methods, such as finite element methods (FEM) and finite difference methods, as well as in deep learning-based approaches. To benchmark our method against recent advances, we apply the new FEX-PG to solve benchmark PIDEs in the literature. In high-dimensional settings, FEX-PG exhibits strong and robust performance, achieving relative errors on the order of single precision machine epsilon, significantly outperforming existing approaches based on neural networks.

Combinatorial optimization↗
DOE OSTI2025

Multioutput Convolutional Neural Network for Improved Parameter Extraction in Time-Resolved Electrostatic Force Microscopy Data

Time-resolved scanning probe microscopy methods, like time-resolved electrostatic force microscopy (trEFM), enable imaging of dynamic processes ranging from ion motion in batteries to electronic dynamics in microstructured thin film semiconductors for solar cells. Reconstructing the underlying physical dynamics from these techniques can be challenging due to the interplay of cantilever physics with the actual transient kinetics of interest in the resulting signal. Previously, quantitative trEFM used empirical calibration of the cantilever or feed-forward neural networks trained on simulated data to extract the physical dynamics of interest. Both these approaches are limited by interpreting the underlying signal as a single exponential function, which serves as an approximation but does not adequately reflect many realistic systems. Here, we present a multi-branched, multi-output convolutional neural network (CNN) that uses the trEFM signal in addition to the physical cantilever parameters as input. The trained CNN accurately extracts parameters describing both single-exponential and bi-exponential underlying functions, and more accurately reconstructs real experimental data in the presence of noise. This article demonstrates an application of physics-informed machine learning to complex signal processing tasks, enabling more efficient and accurate analysis of trEFM.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Discovering nuclear models from symbolic machine learning

Numerous phenomenological nuclear models have been proposed to describe specific observables within different regions of the nuclear chart. However, developing a unified model that describes the complex behavior of all nuclei remains an open challenge. Here, we explore whether symbolic Machine Learning (ML) can rediscover traditional nuclear physics models or identify alternatives with improved simplicity, fidelity, and predictive power. To address this challenge, we developed a Multi-objective Iterated Symbolic Regression approach that handles symbolic regressions over multiple target observables, accounts for experimental uncertainties and is robust against high-dimensional problems. As a proof of principle, we applied this method to describe the nuclear binding energies and charge radii of light and medium mass nuclei. Our approach identified simple analytical relationships based on the number of protons and neutrons, providing interpretable models with precision comparable to state-of-the-art nuclear models. Additionally, we integrated this ML-discovered model with an existing complementary model to estimate the limits of nuclear stability. These results highlight the potential of symbolic ML to develop accurate nuclear models and guide our description of complex many-body problems.

Nuclear structure↗
DOE OSTI2021

Explainable Artificial Intelligence in Endocrinological Medical Research

Artificial Intelligence (AI) has been a part of the medical community for decades in the form of Clinical Decision Support Systems (CDSS) to aide physicians in diagnosis and categorization of patients (1). Recent years have seen a shift from expert-derived models to the integration of machine learning (ML) algorithms to drive the output of these AI systems due to the ability of ML models to more accurately make predictions by exploiting higher dimensional and often complex data. In many cases ML models gain their advantage in accuracy by capture complex and often non-linear relationships between features being used to make the prediction. However, the hype and excitement around these methods are tempered by the clinical utility of often black-box solutions driven by skepticism of results that are difficult for practitioners to not only interpret but explain to their patients (1-3). This skepticism is not unfounded as multiple examples of black-box solutions identifying incidental correlates as the key predictors have highlighted the potential bias in a training set, or reward system, that a ML model may exploit; for example a model discerning wolves from huskies based on snow in the background rather than features of the dogs (1, 4, 5).

Endocrinological, artificial intelligence, diabete↗
DOE OSTI2026

HDSense: An efficient method for ranking observable sensitivity

Identifying which observables most effectively constrain model parameters can be computationally prohibitive when considering full likelihoods of many correlated observables. This is especially important for, e.g., hadronization models, where high precision is required to interpret the results of collider experiments. We introduce the High-Dimensional Sensitivity (HDSense) score, a computationally efficient metric for ranking observable sets using only one-dimensional histograms. Derived by profiling over unknown correlations in the Fisher information framework, the score balances total information content against redundancy between observables. We apply HDSense to rank a set observables in terms of their constraining power with respect to five parameters of the Lund string model of hadronization implemented in Pythia using simulated leptonic collider events at the $Z$ pole. Validation against machine-learning--based full-likelihood approximations demonstrates that HDSense successfully identifies near-optimal observable subsets. The framework naturally handles data from multiple experiments with different acceptances and incorporates detector effects. While demonstrated on hadronization models, the methodology applies broadly to generic parameter estimation problems where correlations are unknown or difficult to model.

Assi, Benoît [Cincinnati U.] (ORCID:00000003092433↗
DOE OSTI2022

Nonnegative canonical tensor decomposition with linear constraints: nnCANDELINC

Abstract There is an emerging interest for tensor factorization applications in big‐data analytics and machine learning. To speed up the factorization of extra‐large datasets, organized in multidimensional arrays (also known as tensors), easy to compute compression‐based tensor representations, such as, Tucker and tensor train formats, are used to approximate the initial large‐tensor. Further, tensor factorization is used to extract latent features that can facilitate discoveries of new mechanisms and signatures hidden in the data, where the explainability of the latent features is of principal importance. Nonnegative tensor factorization extracts latent features that are naturally sparse and parts of the data, which makes them easily interpretable. However, to take into account available domain knowledge and subject matter expertise, often additional constraints need to be imposed, which lead us to canonical decomposition with linear constraints (CANDELINC), a canonical polyadic decomposition with rank deficient factors. In CANDELINC, Tucker compression is used as a preprocessing step, which lead to a larger residual error but to more explainable latent features. Here, we propose a nonnegative CANDELINC (nnCANDELINC) accomplished via a specific nonnegative Tucker decomposition; we refer to as minimal or canonical nonnegative Tucker. We derive several results required to understand the specificity of nnCANDELINC, focusing on the difficulties of preserving the nonnegative rank of a tensor to its Tucker core and comparing the real valued to nonnegative case. Finally, we demonstrate nnCANDELINC performance on synthetic and real‐world examples.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Random Forest Prediction of Crystal Structure from Electron Diffraction Patterns

Transmission electron microscopy (TEM) diffraction patterns are regularly used to determine the structure of crystalline materials. Electron diffraction is the most common method to solve for unknown or partially known crystal structures, as it provides direct and interpretable feedback on the orientation of crystal grains under the beam [1]. However, it remains a challenge to determine the crystal structure of a new material or even a new phase of an existing material. Analysis of such materials commonly requires manual exploration and comparison with simulated diffraction patterns. This is often a time consuming process with no obvious start point when many similar structures are possible, and this method cannot be used to determine crystal structure or orientation from structures not included in the diffraction libraries. Therefore, we have developed a machine learning model to determine the crystal structure of a material from its electron diffraction pattern.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Prediction of Creep-Induced Strain Using a Symbolic Regression-Based Model

Material creep under high-temperature conditions limits the lifetime and safety of structural systems such as advanced nuclear reactors. Conventional creep testing is slow and often produces inconsistent results across nominally identical experiments, making lifetime prediction uncertain. Here, to address these challenges, this work develops a data-driven symbolic regression (SR) model that consolidates results from duplicate creep tests and predicts the remaining strain-time curve of an ongoing experiment. The method uses piece-wise multi-objective SR with physical constraints to generate analytic, interpretable functions describing transient creep strain. Applied to Inconel Alloy 617 data, the approach achieved relative mean absolute errors of 1.0–9.5%, providing closed-form predictions of strain evolution. These results demonstrate a first step toward reducing the duration and cost of long-term creep testing while retaining physically interpretable model forms.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2026

Latent Twins

Over the past decade, scientific machine learning has transformed the development of mathematical and computational frameworks for analyzing, modeling, and predicting complex systems. From inverse problems to numerical partial differential equations (PDEs), dynamical systems, and model reduction, these advances have pushed the boundaries of what can be simulated. Yet they have often progressed in parallel, with representation learning and algorithmic solution methods evolving largely as separate pipelines. With Latent Twins, we propose a unifying mathematical framework that creates a hidden surrogate in latent space for the underlying equations. Whereas digital twins mirror physical systems in the digital world, Latent Twins mirror mathematical systems in a learned latent space governed by operators. Through this lens, classical modeling, inversion, model reduction, and operator approximation all emerge as special cases of a single principle. We establish the fundamental approximation properties of Latent Twins for both ordinary differential equations (ODEs) and PDEs and demonstrate the framework across three representative settings: (i) canonical ODEs, capturing diverse dynamical regimes; (ii) a PDE benchmark using the shallow-water equations, contrasting Latent Twin simulations with deep operator network and forecasts with a four-dimensional variational method baseline; and (iii) a challenging real-data geopotential reanalysis dataset, reconstructing and forecasting from sparse, noisy observations. Latent Twins provide a compact, interpretable surrogate for solution operators that evaluate across arbitrary time gaps in a single-shot, while remaining compatible with scientific pipelines such as assimilation, control, and uncertainty quantification. Looking forward, this framework offers scalable, theory-grounded surrogates that bridge data-driven representation learning and classical scientific modeling across disciplines.

Latent Twins↗
DOE OSTI2024

Atomistic origin of the entropy of melting from inelastic neutron scattering and machine learned molecular dynamics

The latent heat, L, is central to melting, but its atomic origin remains elusive. It is proportional to the entropy of fusion, ΔS fus = L/T m (T m is the melting temperature), which depends on changes of atom configurations, atom vibrations, and thermal electron excitations. Here, we combine inelastic neutron scattering and machine-learned molecular dynamics to separate ΔS fus into these components for Ge, Si, Bi, Sn, Pb, and Li. When the vibrational entropy of melting, ΔS vib , is zero, ΔS fus ≃ 1.2 kB per atom. This result provides a baseline for ΔSconfig and nearly coincides with “Richard’s Rule” of melting. The ΔSfus deviates from this value for most elements, however, and we show that this deviation originates with extra ΔS vib and extra ΔS config . These two components are correlated for positive and negative deviations from Richard’s rule – the extra ΔS config is consistently ~ 80% of ΔS vib . Our results, interpreted with potential energy landscape theory, imply a correlation between the change in the number of basins and the change in the inverse of their curvature for the melting of pure elements.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Data-Driven Kinetic Reaction Networks for Separation Chemistry

Understanding complex, multistep chemical reactions at the molecular level is a major challenge whose solution would greatly benefit the design and optimization of numerous chemical processes. The separation of rare-earth (4f) and actinide (5f) elements is an example where improving our chemical understanding is important for designing and optimizing new chemistries, even with a limited number of observations. Here, in this work, we leverage data-driven artificial intelligence and machine-learning approaches to develop kinetic reaction networks that describe the liquid–liquid extraction mechanism of uranium using N,N-di-2-ethylhexyl-isobutyramide (DEHiBA). Specifically, we compare and contrast the properties of two classes of models: (1) purely data-driven models that are regularized using chemistry-agnostic, L1 regression and (2) chemistry-informed models that are regularized using relative reaction energies provided by quantum mechanical calculations. We observe that purely data-driven models are unbiased, simple, and accurate in their predictions of experimental measurements when provided with sufficient data but are difficult to fully constrain and interpret. In contrast, chemistry-informed models exhibit significantly improved chemical interpretability and consistency, providing a detailed description of the separation process while achieving high accuracy through ensemble averaging. Overall, the dominant species predicted to be extracted into the organic phase is UO 2 (NO 3 ) 2 (DEHiBA) 2 , agreeing with experimental slope analysis, thermodynamic modeling, EXAFS, and crystal structures. This work demonstrates that leveraging the fundamental structure of the problem can lead to efficient learning schemes that provide both accurate predictions and chemical insights at a low computational cost.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Combining artificial intelligence and physics-based modeling to directly assess atomic site stabilities: from sub-nanometer clusters to extended surfaces

The performance of functional materials is dictated by chemical and structural properties of individual atomic sites. In catalysts, for instance, the thermodynamic stability of constituting atomic sites is a key descriptor from which more complex properties, such as molecular adsorption energies and reaction rates, can be derived. In this study, we present a widely applicable machine learning (ML) approach to instantaneously compute the stability of individual atomic sites in structurally and electronically complex nano-materials. Conventionally, we determine such site stabilities using computationally intensive first-principles calculations. With our approach, we predict the stability of atomic sites in sub-nanometer metal clusters of 3–55 atoms with mean absolute errors in the range of 0.11–0.14 eV. To extract physical insights from the ML model, we introduce a genetic algorithm (GA) for feature selection. This algorithm distills the key structural and chemical properties governing the stability of atomic sites in size-selected nanoparticles, allowing for physical interpretability of the models and revealing structure–property relationships. The results of the GA are generally model and materials specific. In the limit of large nanoparticles, the GA identifies features consistent with physics-based models for metal–metal interactions. By combining the ML model with the physics-based model, we predict atomic site stabilities in real time for structures ranging from sub-nanometer metal clusters (3–55 atom) to larger nanoparticles (147 to 309 atoms) to extended surfaces using a physically interpretable framework. Finally, we present a proof of principle showcasing how our approach can determine stable and active nanocatalysts across a generic materials space of structure and composition.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Quantitative and interpretable order parameters for phase transitions from persistent homology

Here, we apply modern methods in computational topology to the task of discovering and characterizing phase transitions. As illustrations, we apply our method to four two-dimensional lattice spin models: the Ising, square ice, XY, and fully frustrated XY models. In particular, we use persistent homology, which computes the births and deaths of individual topological features as a coarse-graining scale or sublevel threshold is increased, to summarize multiscale and high-point correlations in a spin configuration. We employ vector representations of this information called persistence images to formulate and perform the statistical task of distinguishing phases. For the models we consider, a simple logistic regression on these images is sufficient to identify the phase transition. Interpretable order parameters are then read from the weights of the regression. This method suffices to identify magnetization, frustration, and vortex-antivortex structure as relevant features for phase transitions in our models. We also define “persistence” critical exponents and study how they are related to those critical exponents usually considered.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Status of 1eNp0π Charged-Current Electron Neutrino Cross Section on Argon in the NuMI Beam at ICARUS

The Short-Baseline Neutrino (SBN) Program is designed to probe short-baseline neutrino anomalies, including the LSND electron neutrino excess and the MiniBooNE low-energy excess. Essential to interpreting these anomalies and to the success of future experiments like DUNE, is the precise measurement of neutrino-argon interaction cross sections. The program utilizes two liquid argon time projection chamber (LArTPC) detectors: the Short-Baseline Near Detector (SBND) located 110 meters downstream from the Booster Neutrino Beam (BNB) target, and the ICARUS detector positioned 600 meters downstream. Additionally, the ICARUS detector lies off-axis to the NuMI beamline, providing a unique, high-statistics flux of electron neutrinos and sensitivity to energies that overlap with the DUNE spectrum. To analyze the data from these detectors, we have begun employing a machine-learning-based reconstruction algorithm referred to as “Scalable Particle Imaging with Neural Embeddings” (SPINE). SPINE has shown improvement in the ability to reconstruct the properties of final state particles in the detector, like the particle ID and momentum, with the potential to enhance the quality of measurements achievable within the SBN Program e.g., the resolution on kinematics used in differential cross section extraction. This poster presents progress toward measuring the electron neutrino argon interaction cross section in the 1eNp0π topology using the NuMI beam, highlighting the impact of SPINE through the ability to select signal events across a wide kinematic range without sacrificing background rejection power.

Carber, Dan [Colorado State U.] (ORCID:00090006451↗