SEARCH · Search NASA

Results for “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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7

All sources NASA NTRS DOE OSTI

DOE OSTI2026

L-VISP: LSTM Visualization for Interpretable Symptom Prediction in Patient Cohorts

Symptom modelling in head and neck cancer is challenged by the complexity of heterogeneous patient data, leading to an interest in deep learning approaches. Although Long Short-Term Memory Networks (LSTMs) have shown great results in patient risk prediction, their low interpretability requires data modellers to collaborate with clinical experts to validate the results. We present L-VISP, a human–machine solution that uses visual analytics for LSTM modelling in clinical research. L-VISP uses custom visual encodings to make multiple LSTM variants interpretable, supporting a full range of analysis, from understanding model operations and evaluating performance to interpreting results in a clinical context. We evaluate L-VISP with data modellers and a clinical oncologist and present the takeaways from this multidisciplinary collaboration.

LSTM modeling↗

DOE OSTI2020

The weakly nonlinear response and nonaffine interpretation of the Johnson–Segalman/Gordon–Schowalter model

We derive new analytical solutions for the non-affine Johnson-Segalman/Gordon-Schowalter (JS/GS) constitutive equation with a general relaxation kernel in medium-amplitude oscillatory shear (MAOS) deformation. The results show time-strain separable (TSS) nonlinearity, therefore providing new physically-meaningful interpretation to the heuristic TSS nonlinear parameter in MAOS. The upper-convected, lower-convected, and corotational Maxwell models are all subsets of the results presented here. The model assumes that the microscale elements causing stress in the material slip compared to the continuum deformation. We introduce a visualization of the non-affine deformation field that acts on stress-generating elements to reinforce the hysical interpretation of the JS/GS class of models. Lastly, a case study is presented where previously published results, from fitting TSS models to MAOS data, can be re-interpreted based on the concept of non-affine motion of the JS/GS framework.

36 MATERIALS SCIENCE↗

DOE OSTI2020

Interpreting and reporting 40 Ar/ 39 Ar geochronologic data

The 40Ar/39Ar dating method is among the most versatile of geochronometers, having the potential to date a broad variety of K-bearing materials spanning from the time of Earth’s formation into the historical realm. Measurements using modern noble-gas mass spectrometers are now producing 40Ar/39Ar dates with analytical uncertainties of ~1%, thereby providing precise time constraints for a wide range of geologic and extraterrestrial processes. Analyses of increasingly smaller subsamples have revealed age dispersion in many materials, including some minerals used as neutron fluence monitors. Accordingly, interpretive strategies are evolving to address observed dispersion in dates from a single sample. Moreover, inferring a geologically meaningful “age” from a measured “date” or set of dates is dependent on the geological problem being addressed and the salient assumptions associated with each set of data. We highlight requirements for collateral information that will better constrain the interpretation of 40Ar/39Ar data sets, including those associated with single-crystal fusion analyses, incremental heating experiments, and in situ analyses of microsampled domains. To ensure the utility and viability of published results, we emphasize previous recommendations for reporting 40Ar/39Ar data and the related essential metadata, with the amendment that data conform to evolving standards of being findable, accessible, interoperable, and reusable (FAIR) by both humans and computers. Our examples provide guidance for the presentation and interpretation of 40 Ar/ 39 Ar dates to maximize their interdisciplinary usage, reproducibility, and longevity.

58 GEOSCIENCES↗

DOE OSTI2024

Advancing subsurface analysis: Integrating computer vision and deep learning for the near real-time interpretation of borehole image logs in the Illinois Basin-Decatur Project

The accurate quantification and mapping of subsurface natural fracture systems using borehole imaging logs are critical for the success of CO 2 sequestration in geologic formations, optimization of engineered geothermal systems, and hydrocarbon production enhancement. However, traditional interpretation processes suffer from time-consuming procedures and human bias. To address these challenges and expedite fracture analysis, we investigated the application of integrated computer vision and DL workflows to automate image log analysis. Specifically, the design of our workflow was crafted to swiftly detect fractures and baffles by using actual electrical resistivity of borehole wall from microresistivity imaging device alongside their binary representation. This novel approach significantly reduces computational time while providing invaluable insights. By incorporating conventional logging and microseismic data, we present a regional subsurface natural fracture mapping technique. Through the minimization of human bias in image log analysis, our automated workflow achieves reduced fracture interpretation time and costs while ensuring robust and reproducible results. We demonstrated the efficacy of our approach by applying the workflow to the Illinois Basin-Decatur Project site. The automated workflow successfully identified major fractured zones, multiple baffles, and an interbedded layer with a high resolution of 0.01 ft or 0.12 in. (0.3 cm) and can be upscaled to any desired resolution. Validation through microseismic and image log interpretations allows for accurate and near-real-time mapping of fractures and baffles, significantly enhancing CO 2 pressure forecasting and postinjection site care. Our approach stands out due to its robustness, consistency, and reduced computational cost compared with alternative feature extraction technologies. It presents exciting possibilities for advancing CO 2 sequestration and engineered geothermal efforts by offering comprehensive and efficient fracture mapping solutions. This technology can contribute significantly to the optimization of CO 2 sequestration projects, facilitating sustainable environmental practices, and combating climate change.

Geochemistry & Geophysics↗

DOE OSTI2018

HEP Software Foundation Community White Paper Working Group - Data Analysis and Interpretation

At the heart of experimental high energy physics (HEP) is the development of facilities and instrumentation that provide sensitivity to new phenomena. Our understanding of nature at its most fundamental level is advanced through the analysis and interpretation of data from sophisticated detectors in HEP experiments. The goal of data analysis systems is to realize the maximum possible scientific potential of the data within the constraints of computing and human resources in the least time. To achieve this goal, future analysis systems should empower physicists to access the data with a high level of interactivity, reproducibility and throughput capability. As part of the HEP Software Foundation Community White Paper process, a working group on Data Analysis and Interpretation was formed to assess the challenges and opportunities in HEP data analysis and develop a roadmap for activities in this area over the next decade. In this report, the key findings and recommendations of the Data Analysis and Interpretation Working Group are presented.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2022

Introduction to Special Section: Machine Learning for Image-based Geologic Interpretation

Image-based geological interpretation has been a labor-intensive and time-consuming process because it requires well-trained geoscientists to identify geological structures, features, and textures from various types of images. These images include scanning electron microscopic images, optical microscopic images, optical photos, resistivity images, seismic volumes, remote-sensing images, etc. With fast-evolving machine learning (ML) technology and computing power in recent decades, computers can achieve nearhuman-level to super-human-level performance with scalable high efficiency in the computer vision field. These technological revolutions facilitated image-based geological interpretation in petroleum exploration and production. For example, a fault picking method applied to 3-D seismic volume data using deep learning can achieve superior performance in comparison to conventional auto-picking methods. In addition, under the new normal of low oil prices, the petroleum industry seeks cost-effective strategies such as automating traditionally labor-intensive processes. Nevertheless, the potential of applying ML to geological image interpretation is still facing a few key challenges including data scarcity, data distribution, poor data and/or label quality, data leakage, learning algorithms, model architecture, training methodologies, testing and evaluation metrics, hyper-parameters optimization, model drift, production deployment, and the like.

58 GEOSCIENCES↗

DOE OSTI2019

Interpreting the Strain Tensor During Injection into a Reservoir

A suite of well tests was conducted to evaluate the feasibility of measuring and interpreting the strain tensor during injection. Water was injected at 1 liter/s for a few days to a few weeks into a well completed at a depth of 530 m in the Bartlesville sandstone in the North Avant Field in Oklahoma. The strain tensor was measured using strainmeters at a depth of 30m and a distance of 220m from the well. We used a Gladwin strainmeter, a state-of-the-art geodetic strainmeter, as well as novel borehole strainmeters developed for the project. After processing, the horizontal strains were tensile and the vertical strain was compressive during injection. The radial strain was less than the circumferential strain. Strain magnitudes increased during injection and recovered afterward. The strain rate was as fast as 100 nanostrain/d at the start of injection, and decreased to 10 nanostrain/d after a few days. The normal strain signals were approximately proportional to the log of time during the first few days of injection, and the semi-log slope was 50 to 75 nanostrain. Data from the Gladwin strainmeter were essentially identical to data from a strainmeter we developed using optical fiber sensors. Tilt was measured using two tiltmeters, but the tilts were erratic compared to the normal strain and were of limited value. Strain data were analyzed using a strain type-curve method, an analytical solution to a poroelastic inhomogeneity, and a stochastic inversion method. Poroelastic simulations explain the data well. Results from the interpretation methods are consistent with each other, and with independent information characterizing the area. The hydraulic diffusivity is approximately 0.5 m2/s and the permeability is between 100 and 500 mD, according to analysis of the strain signals. This is consistent with measurements of permeability from cores, and with analyses of pressure transients. The analyses indicate that Young’s modulus of the reservoir is between 2 and 6 GPa. Strain interpretations indicate the well intersects a permeable lens with a maximum dimension of 500 to 1,000 m. An isopach map of coarse-grained sand confirms a feature roughly 1,000 m in lateral extent. The results demonstrate that the strain signal measured at shallow (30m) depth can be used to infer properties and heterogeneities in an underlying reservoir or aquifer.

Murdoch, Larry↗

DOE OSTI2024

Towards interpretable Cryo-EM: disentangling latent spaces of molecular conformations

Molecules are essential building blocks of life and their different conformations (i.e., shapes) crucially determine the functional role that they play in living organisms. Cryogenic Electron Microscopy (cryo-EM) allows for acquisition of large image datasets of individual molecules. Recent advances in computational cryo-EM have made it possible to learn latent variable models of conformation landscapes. However, interpreting these latent spaces remains a challenge as their individual dimensions are often arbitrary. The key message of our work is that this interpretation challenge can be viewed as an Independent Component Analysis (ICA) problem where we seek models that have the property of identifiability. That means, they have an essentially unique solution, representing a conformational latent space that separates the different degrees of freedom a molecule is equipped with in nature. Thus, we aim to advance the computational field of cryo-EM beyond visualizations as we connect it with the theoretical framework of (nonlinear) ICA and discuss the need for identifiable models, improved metrics, and benchmarks. Moving forward, we propose future directions for enhancing the disentanglement of latent spaces in cryo-EM, refining evaluation metrics and exploring techniques that leverage physics-based decoders of biomolecular systems. Moreover, we discuss how future technological developments in time-resolved single particle imaging may enable the application of nonlinear ICA models that can discover the true conformation changes of molecules in nature. The pursuit of interpretable conformational latent spaces will empower researchers to unravel complex biological processes and facilitate targeted interventions. This has significant implications for drug discovery and structural biology more broadly. More generally, latent variable models are deployed widely across many scientific disciplines. Thus, the argument we present in this work has much broader applications in AI for science if we want to move from impressive nonlinear neural network models to mathematically grounded methods that can help us learn something new about nature.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Perspectives and Challenges in Bolide Infrasound Processing and Interpretation: A Focused Review with Case Studies

Infrasound sensing plays a critical role in the detection and analysis of bolides, offering passive, cost-effective global monitoring capabilities. Key objectives include determining the timing, location, and yield of these events. Achieving these goals requires a robust approach to detect, analyze, and interpret rapidly moving elevated sources such as bolides (also re-entry). In light of advancements in infrasonic methodologies, there is a need for a comprehensive overview of the characteristics that distinguish bolides from other infrasound sources and methodologies for bolide infrasound analysis. This paper provides a focused review of key considerations and presents a unified framework to enhance infrasound processing approaches specifically tailored for bolides. Three representative case studies are presented to demonstrate the practical application of infrasound processing methodologies and deriving source parameters while exploring challenges associated with bolide-generated infrasound. These case studies underscore the effectiveness of infrasound in determining source parameters and highlight interpretative challenges, such as variations in signal period measurements across different studies. Future research should place emphasis on improving geolocation and yield accuracy. This can be achieved through rigorous and systematic analyses of large, statistically significant samples of such events, aiming to resolve interpretative inconsistencies and explore the causes for variability in signal periods and back azimuths. The topic described here is also relevant to space exploration involving planetary bodies with atmospheres, such as Venus, Mars, and Titan.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2014

Near Infrared Spectroscopy Calibration for Wood Chemistry: Which Chemometric Technique Is Best for Prediction and Interpretation?

This paper addresses the precision in factor loadings during partial least squares (PLS) and principal components regression (PCR) of wood chemistry content from near infrared reflectance (NIR) spectra. The precision of the loadings is considered important because these estimates are often utilized to interpret chemometric models or selection of meaningful wavenumbers. Standard laboratory chemistry methods were employed on a mixed genus/species hardwood sample set. PLS and PCR, before and after 1st derivative pretreatment, was utilized for model building and loadings investigation. As demonstrated by others, PLS was found to provide better predictive diagnostics. However, PCR exhibited a more precise estimate of loading peaks which makes PCR better for interpretation. Application of the 1st derivative appeared to assist in improving both PCR and PLS loading precision, but due to the small sample size, the two chemometric methods could not be compared statistically. This work is important because to date most research works have committed to PLS because it yields better predictive performance. But this research suggests there is a tradeoff between better prediction and model interpretation. Future work is needed to compare PLS and PCR for a suite of spectral pretreatment techniques.

09 BIOMASS FUELS↗

DOE OSTI2016

A NEW NONPLANETARY INTERPRETATION OF THE MICROLENSING EVENT OGLE-2013-BLG-0723

Recently, the discovery of a Venus-mass planet orbiting a brown-dwarf host in a binary system was reported from the analysis of the microlensing event OGLE-2013-BLG-0723. We reanalyze the event considering the possibility of other interpretations. From this, we find a new solution where the lens is composed of two bodies, in contrast to the three-body solution of the previous analysis. The new solution better explains the observed light curve than the previous solution with Δ χ {sup 2} ∼ 202, suggesting that the new solution is a correct model for the event. From the estimation of the physical parameters based on the new interpretation, we find that the lens system is composed of two low-mass stars with ∼0.2 M {sub ⊙} and ∼0.1 M {sub ⊙} and located at a distance of ∼3 kpc. The fact that the physical parameters correspond to those of the most common lens population located at a distance with a large lensing probability further supports the likelihood of the new interpretation. Considering that two dramatically different solutions can approximately explain the observed light curve, the event suggests the need for carefully testing all possible lens-system geometries.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2018

A stochastic sampling approach to zircon eruption age interpretation

The accessory mineral zircon is widely used to constrain the timing of igneous processes such as magma crystallisation or eruption. However, zircon U-Pb ages record zircon crystallisation, which is not an instantaneous process. Zircon saturation calculations link zircon crystallisation, temperature, and melt fraction, allowing for the estimation of zircon crystallisation distributions as a function of time or temperature. Such distributions provide valuable prior information, enabling Bayesian estimates of magma eruption time and allowing for comparison of the relative accuracy of common weighted-mean and youngest-zircon age interpretations with synthetic datasets. We find that both traditional interpretations carry a risk of underestimating the uncertainty in eruption age; a low mean square of weighted deviates (MSWD) does not guarantee the accuracy of weighted-mean interpretations. In the absence of independent confirmation that crystallisation timescale is short relative to analytical uncertainties, a Bayesian approach frequently provides the most accurate results and is least likely to underestimate uncertainty. Finally, since U-Pb zircon studies now routinely resolve geological age dispersion due to increasing analytical precision, such considerations are increasingly critical to future progress in resolving rates and dates of Earth processes.

58 GEOSCIENCES↗

DOE OSTI2020

Panel Session 110B: US DOE High-Level Radioactive Waste (HLW) Interpretation

This panel focused on the US DOE High-Level radioactive Waste (HLW) definition interpretation. Discussion integrated topics such as the issuance of the HLW interpretation Federal Registration Notice, the status of the draft Environmental Assessment that analyzes the treatment and commercial disposal of up to 10,000-gallons of SRS Defense Waste Processing Facility recycle wastewater in South Carolina, and the path forward. Panelists with presentations: Status on the Environmental Assessment for the Commercial Disposal of Defense Waste Processing Facility Recycle Wastewater from SRS (Theresa Kliczewski); Enhancing Stakeholder Engagement on the HLW interpretation (Kara Colton, Rick McLeod); Technical Aspects of Potential Disposal of SRS DWPF Recycle Wastewater (Kent Rosenberger)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2025

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

Decoding visual experiences from fMRI offers a powerful avenue to understand human perception and develop advanced brain-computer interfaces. However, current progress often prioritizes maximizing reconstruction fidelity while overlooking interpretability, an essential aspect for deriving neuroscientific insight. To address this gap, we propose MoRE-Brain, a neuro-inspired framework designed for high-fidelity, adaptable, and interpretable visual reconstruction. MoRE-Brain uniquely employs a hierarchical Mixture-of-Experts architecture where distinct experts process fMRI signals from functionally related voxel groups, mimicking specialized brain networks. The experts are first trained to encode fMRI into the frozen CLIP space. A finetuned diffusion model then synthesizes images, guided by expert outputs through a novel dual-stage routing mechanism that dynamically weighs expert contributions across the diffusion process. MoRE-Brain offers three main advancements: First, it introduces a novel Mixture-of-Experts architecture grounded in brain network principles for neuro-decoding. Second, it achieves efficient cross-subject generalization by sharing core expert networks while adapting only subject-specific routers. Third, it provides enhanced mechanistic insight, as the explicit routing reveals precisely how different modeled brain regions shape the semantic and spatial attributes of the reconstructed image. Extensive experiments validate MoRE-Brain’s high reconstruction fidelity, with bottleneck analyses further demonstrating its effective utilization of fMRI signals, distinguishing genuine neural decoding from over-reliance on generative priors. Consequently, MoRE-Brain marks a substantial advance towards more generalizable and interpretable fMRI-based visual decoding.

Wei, Yuxiang [Georgia Institute of Technology]↗

DOE OSTI2025

SPARTA: A flux adjustment methodology to interpret complex experiments

For the accurate determination of reactivity from a detector count rate, correction of spatial effects is of prime importance. This spatial correction is often provided using simulation methodologies, but this may introduce a bias if the result of the experiment is also used as input data for the simulation. Here, this work presents a flux adjustment methodology able to infer experimental reactivity and correction of spatial effects without the need for a simulation. It can process the signal from a complex experiment such as a heat balance measurement in the TREAT reactor, where control rods are continuously adjusted to maintain a constant power. In the present work, this methodology successfully computed the reactivity and the local spatial variation of the flux of a generated signal. It also proved to be robust against noise and errors on kinetic parameters and provides a credible interpretation of a heat balance experiment in TREAT. Efficiency of flux adjustment methods for complex experiment enable a better experiment interpretation less reliant on nuclear data evaluation.

73 - NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2024

Analyzing the impact of design factors on solar module thermomechanical durability using interpretable machine learning techniques

Solar modules in utility-scale systems are expected to maintain decades of lifetime to rival conventional energy sources. However, cyclic thermomechanical loading often degrades their long-term performance, highlighting the importance of effective design to mitigate thermal expansion mismatches between module materials. Given the complex composition of solar modules, isolating the impact of individual components on overall durability remains a challenging task. In this work, we analyze a comprehensive data set that comprises bill-of-materials (BOM) and thermal cycling power loss from 251 distinct module designs to identify the predominant design factors and their impacts on the thermomechanical durability of modules. The methodology of our analysis combines machine learning modeling (random forest) and Shapley additive explanation (SHAP) to correlate design factors with power loss and interpret the model’s decision-making. The interpretation reveals that silicon type (monocrystalline or polycrystalline), encapsulant thickness, busbar numbers, and wafer thickness predominantly influence the degradation. With lower power loss of around 0.6% on average in the SHAP analysis, monocrystalline cells present better durability than polycrystalline cells. This finding is further substantiated by statistical testing on our raw data set. The SHAP analysis also demonstrates that while thicker encapsulants lead to reduced power loss, further increasing their thickness over around 0.6 to 0.7 mm does not yield additional benefits, particularly for the front side one. In addition, other important BOM features such as the number of busbars are analyzed. This study provides a blueprint for utilizing explainable machine learning techniques in a complex material system and can potentially guide future research on optimizing the design of solar modules.

14 SOLAR ENERGY↗

DOE OSTI2026

Interpretable and flexible non-intrusive reduced-order models using reproducing kernel Hilbert spaces

This paper develops an interpretable, non-intrusive reduced-order modeling technique using regularized kernel interpolation. Existing non-intrusive approaches approximate the dynamics of a reduced-order model (ROM) by solving a data-driven least-squares regression problem for low-dimensional matrix operators. Our approach instead leverages regularized kernel interpolation, which yields an optimal approximation of the ROM dynamics from a user-defined reproducing kernel Hilbert space. We show that our kernel-based approach can produce interpretable ROMs whose structure mirrors full-order model structure by embedding judiciously chosen feature maps into the kernel. The approach is flexible and allows a combination of informed structure through feature maps and closure terms via more general nonlinear terms in the kernel. We also derive a computable a posteriori error bound that combines standard error estimates for intrusive projection-based ROMs and kernel interpolants. In conclusion, the approach is demonstrated in several numerical experiments that include comparisons to operator inference using both proper orthogonal decomposition and quadratic manifold dimension reduction.

Data-driven model reduction↗

DOE OSTI2026

Learning interpretable surface elasticity properties from bulk properties via neural network equation learners

Surface elasticity is central to understanding the mechanics and stability of surfaces and interfaces. It is characterized by quantities such as surface tension, residual surface stress, and surface stiffness. However their analytical expressions are typically difficult to derive from atomistic data, and depend strongly on modeling choices. This work presents a neural network-based equation learner which combines customized activation functions and connection-based pruning to discover parsimonious, closed-form equations for surface elasticity from atomistic simulations. Applying the method to seven face-centered cubic (FCC) metals, our equation learner uncovers interpretable equations that describe both low-Miller index and high-Miller index surface properties, capturing long-tail property distributions accurately. The discovered expressions are decoupled into two components: a universal, geometry-driven orientation function, and material-specific baseline coefficients. We find that lower-order properties such as surface tension are fundamentally geometry dependent, while higher-order properties such as surface stress and elasticity show more complex geometry and material dependence. We also relate material dependent coefficients to bulk properties, forming a clear map from bulk material properties to surface elasticity. Overall, this approach demonstrates that interpretable neurosymbolic machine learning can bridge the gap between atomistic simulations and physical laws, enabling the discovery of generalizable structure–property relationships for materials science phenomena such as surface elasticity.

Equation learning↗