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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Neural simulation-based inference of the neutron star equation of state directly from telescope spectra

Neutron stars provide a unique opportunity to study strongly interacting matter under extreme density conditions. The intricacies of matter inside neutron stars and their equation of state are not directly visible, but determine bulk properties, such as mass and radius, which affect the star's thermal X-ray emissions. However, the telescope spectra of these emissions are also affected by the stellar distance, hydrogen column, and effective surface temperature, which are not always well-constrained. Uncertainties on these nuisance parameters must be accounted for when making a robust estimation of the equation of state. In this study, we develop a novel methodology that, for the first time, can infer the full posterior distribution of both the equation of state and nuisance parameters directly from telescope observations. This method relies on the use of neural likelihood estimation, in which normalizing flows use samples of simulated telescope data to learn the likelihood of the neutron star spectra as a function of these parameters, coupled with Hamiltonian Monte Carlo methods to efficiently sample from the corresponding posterior distribution. Our approach surpasses the accuracy of previous methods, improves the interpretability of the results by providing access to the full posterior distribution, and naturally scales to a growing number of neutron star observations expected in the coming years.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Systematic characterization of unknown compounds via dimensionality reduction of time series

Analysis of ambient aerosols provides valuable insight into particle sources and formation chemistry. However, due to the complexity of atmospheric data and the dynamic nature of aerosol composition, a substantial fraction of data often become discarded by conventional analysis methods. Furthermore, a large fraction of chemical species within those data are unidentifiable due to a lack of matching spectral information, resulting in suboptimal characterization of chemical composition. Previous work has demonstrated techniques for cataloging analytes in a chromatographic dataset by deconvolution of mass spectra, but integration of these analytes throughout a large dataset remains time consuming. Here, we present a method to automatically identify an ion for quantitation for single-ion chromatogram based peak fitting and integration, enabling comprehensive integration of analytes with minimal user interaction. The resulting time series are clustered with a machine-learning based dimensionality reduction technique to systematically investigate the underlying characteristics of the categorized analytes and gain new insights into the chemical composition and physicochemical properties of the unidentifiable analytes. We apply these methods to existing atmospheric datasets collected in Manacapuru, Brazil during the GoAmazon2014/5 campaign to identify new analytes and interpret their variability and transformations in the atmosphere. The analysis results generate 408 time series from cataloged analytes of interest, and the clustering of those time series with spherical k-means results in 8 distinct clusters. We find the analytes form clusters based on their distinct physicochemical properties, demonstrating the method’s ability to systematically identify and selectively filter contaminants and instrumental analytes and characterize the unidentifiable analytes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

SSTDR and FDR Detection of Un-Energized and Energized Cable Anomalies Including Thermal Degradation Using Machine Learning

Historically, cables are initially qualified for nuclear power plant use for 40 years. As plants extend their operating license to 60 and 80 years, continued use of these cables must shift to a performance-based approach since it is cost prohibitive to completely replace cables that are likely still capable of performing their design function. A variety of cable tests are available and are commonly applied during outages when the cables can be taken out of service. Frequency domain reflectometry (FDR) is one of these test methods that is being more broadly accepted and used because it not only detects anomalies along the cable with a low-voltage signal that does not stress the cable insulation, but the technique also locates the anomalies. This supports follow-up local inspection and local repair or partial replacement of a damaged cable segment. Currently, FDR testing is only applied to cables that are taken out of service since the test instrument would be damaged by operational voltages. A related technology that has found some acceptance in the aircraft and rail industry is spread spectrum time domain reflectometry (SSTDR). This technology has been implemented with a custom commercial instrument by LiveWire Innovation that is designed to operate on live cables up to 1000 volts and with a bandwidth of 48 MHz. Initial evaluation by the Pacific Northwest National Laboratory (PNNL) of the Live Wire system indicated that a broader bandwidth (BW) SSTDR may be better for many kinds of flaws. This led PNNL to develop an SSTDR laboratory instrument suitable for tests up to 500 MHz bandwidth. Testing on energized cables is also desirable for online monitoring systems so an inductive clamshell coupler was developed that allows energized cables to be tested up to at least 5 kV and likely higher voltage levels. Dielectric spectroscopy and tan delta testing plus various laboratory destructive tests were included in this data acquisition campaign directed to feed a machine learning (ML) study. With these kinds of developments, online energized cable tests may be possible with industrial adoption of such hardware advances but it will be completely impractical to have highly skilled data analysts continually examine these complex signals for indications of damage or compromised conditions. If online testing is to be implemented in new test hardware, it must be accompanied by software that can interpret the signals and alert plant operators of changing or degraded conditions. The thermally aged, shielded cable investigated here was separately treated for ML analysis. Visual analysis of electrical data showed generally increasing peaks where the cable entered and exited the oven. These peaks were not exactly aligned with expected locations, but these differences were attributed to velocity of propagation calibration errors. Only supervised ML was applied to the thermally aged data as this data was only available shortly before the committed publication date of this report. The supervised ML was structured to divide the 0 to 70-day responses as ‘normal’ from 0 to 35 days or ‘anomalous’ from 36 to 70 days, based on cable tensile elongation at break (EAB) insulation characterization. Using 80% of the data for training and 20% for testing, the supervised ML predicted normal versus anomalous was 70% accurate. Important conclusions include: • Accuracy to predict the presence of cable damage is improved from the 2023 effort by more training data. Weighted accuracies for comparisons among the instruments ranged from 67 to 89 % for unsupervised ML and 71 to 99% for supervised ML. • Based on the synthetic data tests, the unsupervised models are more generalizable to unseen anomalies. The Multi-Layer Perceptron classifier (MLP) model reported as high as 99.7% accuracy on the test data, but this dropped to 58.3% when tested on the synthetic data. In contrast, the unsupervised Pointwise model only achieved 89.7% accuracy on the experimental data but reported 78.3% accuracy on the synthetic data. • The best anomaly indicators are higher frequency (400 MHz BW) FDR data. Other tests may be interesting but for this study, this was the best predicter.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Data-Enabled Fusion Technology (Final Scientific/Technical Report)

Advancing Scientific Understanding in Fusion Energy and Machine Learning This research represented a significant step forward in machine learning (ML) applications for fusion energy experiments. The project integrated advanced data-driven modeling, optimization techniques, and artificial intelligence to enhance the predictive capabilities and operational efficiency of plasma-based fusion systems. Specifically, tasks focused on ML-enhanced diagnostics, operator guidance tools, and predictive modeling helped improve the ability to interpret complex fusion experiments. Key areas of advancement included: 1) data-driven plasma control, i.e., using ML algorithms to optimize experimental conditions and classify plasma behaviors based on historical data; 2) spectroscopy and diagnostics, i.e., applying AI models to extract previously inaccessible insights from experimental spectroscopy data; and 3) configuration mapping and operator guidance, i.e., developing a predictive framework to assist scientists in identifying the most effective experimental parameters, reducing reliance on manual adjustments. By refining these ML-driven techniques, the project contributed to the broader scientific community’s understanding of plasma dynamics and fusion energy viability. Technical Effectiveness and Economic Feasibility The methods investigated demonstrated high technical effectiveness, as reflected in milestones assessing the predictive accuracy, performance, and optimization of fusion configurations. The development of an Operator Guidance Tool (OGT), for example, led to more precise control of plasma conditions by learning from experimental data and offering real-time adjustments. From an economic standpoint, DeFT provided: 1) the ability to reduce trial-and-error experimentation, which lowered operational costs; 2) improved data interpretation methods, which enabled more efficient resource allocation in large-scale fusion research projects; and 3) the automation of key diagnostic tasks, which reduced manual labor and human error, increasing overall efficiency. 13 The final assessments of predictive models and optimization strategies demonstrated that these approaches were scalable and could be implemented across multiple fusion energy research programs. Public Benefit and Societal Impact This project contributed directly to the broader goal of achieving sustainable and commercially viable fusion energy, which had profound implications for clean energy production and climate change mitigation. The integration of AI-driven solutions into fusion research: 1) sped up scientific discovery, accelerating progress towards achieving energy breakthroughs; 2) reduced the cost of experimentation, making fusion research more accessible; and 3) provided a framework for future AI applications in high-energy physics, benefiting adjacent fields like space exploration, material science, and renewable energy. Additionally, by fostering collaborations between AI researchers and plasma physicists, this project promoted interdisciplinary innovation that could lead to broader applications beyond fusion research.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Neutrino interaction vertex reconstruction in DUNE with Pandora deep learning

The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep Underground Neutrino Experiment, which will operate four large-scale liquid argon time projection chambers at the far detector site in South Dakota, producing high-resolution images of charged particles emerging from neutrino interactions. While these high-resolution images provide excellent opportunities for physics, the complex topologies require sophisticated pattern recognition capabilities to interpret signals from the detectors as physically meaningful objects that form the inputs to physics analyses. A critical component is the identification of the neutrino interaction vertex. Subsequent reconstruction algorithms use this location to identify the individual primary particles and ensure they each result in a separate reconstructed particle. A new vertex-finding procedure described in this article integrates a U-ResNet neural network performing hit-level classification into the multi-algorithm approach used by Pandora to identify the neutrino interaction vertex. The machine learning solution is seamlessly integrated into a chain of pattern-recognition algorithms. The technique substantially outperforms the previous BDT-based solution, with a more than 20% increase in the efficiency of sub-1 cm vertex reconstruction across all neutrino flavours.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

LCLS Big Data Handling – How I Learned to Stop Worrying and Love the Data Deluge

Advanced data and computing systems are vital to Linac Coherent Light Source (LCLS) operations, data interpretation and overall scientific productivity. The transition to MHz-era operation marks a fundamental change in scale that requires new infrastructure and architectures to link LCLS to the required scale of computing needed for scientific interpretation. The LCLS-II Data System meets big data challenges by implementing configurable data reduction that can adapt to multiple science areas, real-time analysis frameworks to provide visualization and fast feedback, and the ability to transfer data to local and remote computational facilities for near real time analysis at the appropriate scale. Feature extracted information generated in the data analysis pipeline - at the edge, local compute, or remote High-Performance Computing (HPC) resources - can be used to steer experiments and inform user decisions during beam time. Artificial Intelligence and Machine Learning (AI/ML) techniques present new opportunities to rapidly analyse large datasets and direct experiments, but create new challenges in scaling, adaptability, complexity, and trustworthiness. We describe how the LCLS-II Data System architecture addresses its data-driven challenges in the areas of data acquisition, data processing, data management, and workflow orchestration to decrease the overall time-to-science and provide a vision for future developments.

artificial intelligence↗
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 OSTI2025

Improved loss functions for machine-learned atomic potentials

Machine learning (ML) has become an invaluable tool across a wide array of domains in science as researchers find new ways to leverage its predictive power. This is especially true in chemistry, where ML is used to fit chemical properties or desirable attributes to the local structure of molecules and materials. In the pursuit of greater accuracy, it is relatively simple to increase the size or complexity of such models, although this often requires simultaneously seeking larger datasets in order to both fit and interpret the larger number of parameters. However, it is equally important to assess the quality and relative importance of the data and how these factors impact the training process. We, therefore, investigate the impact of using different loss functions for training neural network potentials (NNPs), as the loss function defines the error and parameter gradients used to train the NNP. In particular, we test the mean-squared error and Huber loss functions and, using insight from these functions, derive a new loss function based on the Asinh function, which yields significant improvement in the accuracy and generality of NNPs. We show that by discounting/minimizing errors and anomalies in the optimization process, both the Huber and Asinh loss functions improve the training of NNPs, leading to a final potential with a greater effective dimensionality.

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

Measurements and interpretations of W ± Z production cross-sections in pp collisions at $\sqrt{s}=13$ TeV with the ATLAS detector

Measurements of integrated and differential cross-sections for W ± Z production in proton-proton collisions are presented. The data collected by the ATLAS detector at the Large Hadron Collider from 2015 to 2018 at a centre-of-mass energy of $\sqrt{s}=13$ TeV are used, corresponding to an integrated luminosity of 140 fb −1 . The W ± Z candidate events are reconstructed using leptonic decay modes of the gauge bosons into electrons or muons. The integrated cross-section per lepton flavour for the production of W ± Z is measured in the detector fiducial region with a relative precision of 4%. The measured value is compared with the Standard Model prediction at a precision of up to next-to-next-to-leading-order in QCD and next-to-leading-order in electroweak. Cross-sections for W + Z and W − Z production and their ratio are presented. The W ± Z production is also measured differentially as functions of various kinematic variables, including new observables sensitive to CP-violation effects. All measurements are compared with state-of-the-art Standard Model predictions from fixed-order calculations or Monte Carlo generators based on next-to-leading-order matrix elements interfaced with parton showers. An effective field theory interpretation of the measurements is performed, considering both CP-conserving and CP-violating dimension-6 operators modifying the W ± Z production. In the absence of observed deviations from the Standard Model, limits on CP-conserving Wilson coefficients are extracted using the transverse mass of the W ± Z system. For CP-violating coefficients a machine learning approach is used to construct an observable with enhanced sensitivity to CP-violation effects.

hadron-hadron scattering↗
DOE OSTI2025

Physical Interpretation of Early Battery Life Prediction Models

Early battery life prediction models are most useful for R&D if they help us understand the early changes in battery electrochemical response that correspond with long-term degradation and failure. Linear regression models such as Fused lasso and Partial Least Squares can fit coefficients directly to high-dimensional electrochemical data like capacity-voltage and ΔV–state-of-charge, i.e., Q(V) and ΔV(SOC) curves, learning coefficients that can be physically interpreted. We leverage the ISU-ILCC battery aging data set to learn high-dimensional coefficients for early battery life prediction from traditional slow-rate capacity check data, demonstrating learning on Q(V), d Q· d V −1 , and ΔV(SOC) curves. A thorough study on the dependence of coefficient values on train/test size and data preprocessing methods is made, demonstrating the reliability of high-dimensional regression approaches unless very small amounts of data are used for model training. For this data set, coefficients from Q(V) and d Q· d V −1 models highlight changes in electrode stoichiometry due to lithium loss, while ΔV(SOC) coefficients highlight changes in positive electrode diffusivity due to particle cracking as well as electrode stoichiometry shifts. By directly interpreting the coefficients of a regression model, we make physical insights into battery degradation mechanisms without requiring the assumptions of traditional battery data analysis methods.

25 ENERGY STORAGE↗
DOE OSTI2024

Tandem Predictions for HPC Jobs

At the core of the predictive analytics applied to High Performance Computing (HPC), the most prominent tasks are the prediction of job runtimes and the prediction of job queue times, both of which have the potential for informing HPC users during their every-day decision making. Accurate runtime predictions can help users better choose so-called wallclock times at job submission, decreasing the odds of their jobs waiting in queues longer than necessary. The accurate and timely queue time predictions offered for the available partitions can inform the favorable selection of partitions for running jobs. This potential is well understood as we see in the abundance of research studies that propose solutions for these tasks, including the work published in the last several years. These tasks are seemingly receptive to the Machine Learning (ML) solutions, considering that there is no shortage of training data where HPC centers over time run millions and millions of jobs. However, we study the existing research literature, as well as look for examples in the toolchains supported on the exemplar HPC facilities, and, surprisingly, do not find any practical solutions that are ready to be adopted. We interpret this as a manifestation of the shortage of UX/UI efforts that support HPC analytics and also as a sign that the research has not come to the consensus on solving these tasks. In this study, we aim to shed new light on the long-running task of job queue time prediction by exploring the utility of runtime predictions in improving prediction accuracy and, actually, predicting these two metrics together, in tandem. In other words, we show how runtime predictions become valuable input in the queue time modeling. We challenge the existing approaches to feature engineering for the queue time prediction and describe promising results we obtained for a large dataset of HPC jobs from a supercomputer at the National Renewable Energy Laboratory.

HPC↗
DOE OSTI2025

Tandem Predictions for HPC Jobs: Preprint

At the core of the predictive analytics applied to High Performance Computing (HPC), the most prominent tasks are the prediction of job runtimes and the prediction of job queue times, both of which have the potential for informing HPC users during their every-day decision making. Accurate runtime predictions can help users better choose so-called wallclock times at job submission, decreasing the odds of their jobs waiting in queues longer than necessary. The accurate and timely queue time predictions offered for the available partitions can inform the favorable selection of partitions for running jobs. This potential is well understood as we see in the abundance of research studies that propose solutions for these tasks, including the work published in the last several years. These tasks are seemingly receptive to the Machine Learning (ML) solutions, considering that there is no shortage of training data where HPC centers over time run millions and millions of jobs. However, we study the existing research literature, as well as look for examples in the toolchains supported on the exemplar HPC facilities, and, surprisingly, do not find any practical solutions that are ready to be adopted. We interpret this as a manifestation of the shortage of UX/UI efforts that support HPC analytics and also as a sign that the research has not come to the consensus on solving these tasks. In this study, we aim to shed new light on the long-running task of job queue time prediction by exploring the utility of runtime predictions in improving prediction accuracy and, actually, predicting these two metrics together, in tandem. In other words, we show how runtime predictions become valuable input in the queue time modeling. We challenge the existing approaches to feature engineering for the queue time prediction and describe promising results we obtained for a large dataset of HPC jobs from a supercomputer at the National Renewable Energy Laboratory.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Data Summarization and Inference at Scale

This is the final report for the DOE ASCR grant SC-0022260, Data Summarization and Inference at Scale, PI: Alex Pothen, Purdue University. The goal of the project was to solve data-intensive and compute-intensive problems in the physical sciences, engineering, information science, data science, etc. by designing and implementing new algorithms that could work with a subset of the data. The four subgoals were: (a) The solution of problems where the data is too large to be stored in the memory of a computer. In this streaming model of computation, the data arrives as a stream of elements to the computer, each element is processed as it arrives, and a decision is made to discard the data or to store it; only a small subset of the data proportional to the size of the output solution is stored, and when all the data has been streamed, a solution to the problem is computed from the stored subset. (b) The use of machine learning methods to compute solutions to data-intensive problems. The use of GPUs is critical to obtain high performance on machine learning tasks, but their memory sizes are smaller relative to that of CPUs. For large-scale problems, the data is sampled many times, and small samples are used with repetition, for robustness, to compute solutions to inference tasks. This sampling reduces the memory required to solve the problem, but attention is needed to avoid slow convergence to the solutions, and reduced accuracy of inference. We propose submodular optimization, Large Language Models, and physics-informed neural networks to enable GPU computations here. (c) Modeling and visualization of high-dimensional data using interpretable features. Clinical proteomic data sets from immunology for the detection of cancer and other diseases are temporal and high-dimensional, and algorithms for visualizing these data sets using clinically interpretable features are lacking. We propose methods that compute distances based on the optimal transportation problem and graph edit distances to address this problem. We also propose the use of optimal transport-based distances, spatial statistics, and network structure to classify image data sets, We apply these algorithms to electron micrographs of the peripheral nervous system in the digestive tract. (d) The design of data-intensive algorithms on emerging architectures, specifically, noisy, intermediate-scale quantum (NISQ) devices. Quantum computers offer the possibility of exploring large solution spaces due to the principle of superposition, but current quantum computers are limited by few qubits, short coherence times due to noise, poor interconections among the qubits, etc. We propose the use of the divide and conquer paradigm to solve large-scale problems, wherein collections of small subproblems are solved on the quantum devices, and the solutions to the subproblems are integrated into a solution for the original problem on a classical computer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing

We demonstrate a multi-fidelity (MF) machine learning ensemble framework for the inverse design of photonic surfaces, trained on a dataset of 11,759 samples that we fabricate using high throughput femtosecond laser processing. The MF ensemble combines an initial low fidelity model for generating design solutions, with a high fidelity model that refines these solutions through local optimization. The combined MF ensemble can generate multiple disparate sets of laser-processing parameters that can each produce the same target input spectral emissivity with high accuracy (root mean squared errors < 2%). SHapley Additive exPlanations analysis shows transparent model interpretability of the complex relationship between laser parameters and spectral emissivity. Finally, the MF ensemble is experimentally validated by fabricating and evaluating photonic surface designs that it generates for improved efficiency energy harvesting devices. Our approach provides a powerful tool for advancing the inverse design of photonic surfaces in energy harvesting applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Divide and conquer: separating the two probabilities in seismic phase picking

There are two fundamental probabilities in the seismic phase picking process—the probability of the existence of a seismic phase (detection probability) and the probability associated with the phase arrival time estimation (timing probability). The nearly ubiquitous approach in developing deep learning phase picking models is to use a kernel, such as a truncated Gaussian, to mask the labelled phase arrival time and train a segmentation model. Once a model is trained, the times of the peaks in the output are taken as phase arrival times (picks), and the height of the peaks are taken as ‘probability’ of the picks. Here, we show that this ‘probability’ represents neither the detection nor the timing probability because this approach forces the output to follow the shape of the kernel. We introduce an approach using two models to estimate these two distinct probabilities. We use a binary classifier with a calibrated confidence to address the detection probability and a multiclass classifier to obtain a probability mass function to address the timing probability. This new approach can make the deep learning-based phase picking process more interpretable and provide options to logically control seismic monitoring workflows.

58 GEOSCIENCES↗
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↗
DOE OSTI2025

SA-GAT-SR: self-adaptable graph attention networks with symbolic regression for high-fidelity material property prediction

Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches, particularly Graph Neural Networks (GNNs) for materials science. These methods have emerged as powerful tools for high-throughput prediction of material properties, offering a compelling enhancement and alternative to traditional first-principles calculations. While the community has predominantly focused on developing increasingly complex and universal models to enhance predictive accuracy, such approaches often lack physical interpretability and insights into materials behavior. Here, we introduce a novel computational paradigm—Self-Adaptable Graph Attention Networks integrated with Symbolic Regression (SA-GAT-SR)—that synergistically combines the predictive capability of GNNs with the interpretative power of symbolic regression. Our framework employs a self-adaptable encoding algorithm that automatically identifies and adjust attention weights so as to screen critical features from an expansive 180-dimensional feature space while maintaining O(n) computational scaling. The integrated SR module subsequently distills these features into compact analytical expressions that explicitly reveal quantum-mechanically meaningful relationships, achieving 23 × acceleration compared to conventional SR implementations that heavily rely on first-principle calculations-derived features as input. This work suggests a new framework in computational materials science, bridging the gap between predictive accuracy and physical interpretability, offering valuable physical insights into material behavior.

36 MATERIALS SCIENCE↗
DOE OSTI2025

A Beginner's Guide to Power and Energy Measurement and Estimation for Computing and Machine Learning

Concerns about the environmental footprint of machine learning are increasing. While studies of energy use and emissions of ML models are a growing subfield, most ML researchers and developers still do not incorporate energy measurement as part of their work practices. While measuring energy is a crucial step towards reducing carbon footprint, it is also not straightforward. This paper introduces the main considerations necessary for making sound use of energy measurement tools and interpreting energy estimates, including the use of at-the-wall versus on-device measurements, sampling strategies and best practices, common sources of error, and proxy measures. It also contains practical tips and real-world scenarios that illustrate how these considerations come into play. It concludes with a call to action for improving the state of the art of measurement methods and standards for facilitating robust comparisons between diverse hardware and software environments.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗