Search NASA⌕ Search

SEARCH · Search NASA

Results for “INTERPRETATION”

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 433 records · Page 24
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Generation of random geological models using multi-randomization for machine learning

Generating high-fidelity geological models is essential for advancing machine learning (ML) methods in automated seismic interpretation. For instance, seismic images paired with corresponding fault labels are foundational for ML-based fault detection from seismic migration sections. While several open-access datasets of random geological models exist, open-source tools specifically designed to produce large volumes of such models for ML applications remain scarce. To address this gap, we present RGM (Random Geological Model), an open-source software package for efficiently generating 2D and 3D synthetic geological models tailored for ML workflows. RGM supports the creation of diverse model components, including medium property distributions (P-/S-wave velocities and density), seismic reflectivity images (i.e., synthetic migration sections), relative geological time, and discrete fault attributes such as probability, dip, strike, rake, and displacement. It also accommodates the creation of complex geological features such as salt bodies and unconformities. The model generation algorithm employs a multi-randomization strategy, yielding an effectively infinite-dimensional model space that encompasses a wide range of geological scenarios and associated seismic features. Furthermore, RGM incorporates a method to generate synthetic elastic migration images using analytical elastic reflection coefficients combined with frequency-dependent scaling. This functionality enables the creation of training datasets for ML models that leverage elastic seismic images. RGM is implemented in modern object-oriented Fortran, allowing users to flexibly control statistical parameters governing model variability. We demonstrate the capability, performance, and geological realism of the package through comprehensive 2D and 3D examples.

58 GEOSCIENCES↗
DOE OSTI2025

Towards the next generation of Geospatial Artificial Intelligence

Geospatial Artificial Intelligence (GeoAI), as the integration of geospatial studies and AI, has become one of the fastest-developing research directions in spatial data science and geography. This rapid change in the field calls for a deeper understanding of the recent developments and envision where the field is going in the near future. In this work, we provide a quantitative analysis of the GeoAI literature from the spatial, temporal, and semantic aspects. We briefly discuss the history of AI and GeoAI by highlighting some pioneering work. Then we discuss the current landscape of GeoAI by selecting five representative subdomains including remote sensing, urban computing, Earth system science, cartography, and geospatial semantics. Finally, we highlight several unique future research directions of GeoAI which are classified into two groups: GeoAI method development challenges and GeoAI Ethics challenges. Topics include heterogeneity-aware GeoAI, knowledge-guided GeoAI, spatial representation learning, geo-foundation models, fairness-aware GeoAI, privacy-aware GeoAI, as well as interpretable and explainable GeoAI. We hope our review of GeoAI’s past, present, and future is comprehensive and can enlighten the next generation of GeoAI research.

58 GEOSCIENCES↗
DOE OSTI2025

Systematic feature design for cycle life prediction of lithium-ion batteries during formation

Optimization of the formation step in lithium-ion battery manufacturing is challenging due to limited physical understanding of solid-electrolyte interphase formation and the long testing time (∼100 days) for cells to reach the end of life. We propose a systematic feature-design framework that requires minimal domain knowledge for accurate cycle life prediction during formation. By only using two simple Q (V) features designed from our framework, extracted from formation data without any additional diagnostic cycles, we achieved an average of 9.87% error for cycle life prediction. Here, the physics-based investigation guided by the two designed features shows that the voltage ranges identified by our framework capture the effects of formation temperature and microscopic-particle resistance heterogeneity. By designing highly predictive, robust, and interpretable features, our approach can accelerate industrial battery formation research, leveraging the interplay between data-driven feature design and mechanistic understanding.

25 ENERGY STORAGE↗
DOE OSTI2026

Regulation compliant AI for fusion: explainable image-based feedback control of divertor detachment in DIII-D tokamak

While artificial intelligence (AI) has been promising for fusion control, its inherent black-box nature will make compliant implementation in regulatory environments a challenge. This study implements and validates a real-time AI-enabled linear and interpretable control system for successful divertor detachment control with the DIII-D lower divertor camera. Using D 2 gas, we demonstrate successful feedback divertor detachment control with a mean absolute difference of 2% from the target for both detachment and reattachment. This automatic training and linear processing framework can be extended to any image-based diagnostic for future fusion reactors.

computer vision↗
DOE OSTI2024

Automatic Loss Factor Modeling and Attribution on Unlabeled PV Energy Data

We present a novel approach for modeling the loss factors of photovoltaic power generation systems (PV systems). This method is a white-box machine learning model built on convex optimization that is fast, interpretable, and auditable. It takes as an input the measured daily energy produced by the system, over a multi-year period, and returns a multiplicative decomposition model of the daily energy signal and full attribution of the total energy loss to each feature. The methods section of this paper has two major components: (1) the description of the signal decomposition (SD) model, expressed in the SD framework, and (2) the attribution of total energy losses via Shapley values. We validate the method on synthetic and open-source data sets and compare to similar methods from the literature.

artificial intelligence↗
DOE OSTI2025

One-shot gas detection with transformer paired neural networks in Mako collected longwave infrared hyperspectral imagery

To date, careful data treatment workflows and statistical detectors are used to perform hyperspectral image (HSI) detection of any gas contained in a spectral library, which is often expanded with physics models to incorporate different spectral characteristics. In general, surrounding evidence or known gas-release parameters are used to provide confidence in or confirm detection capability, respectively. This makes quantifying detection performance difficult as it is nearly impossible to develop an absolute ground truth for gas target pixel presence in collected HSI. Consequently, developing and comparing new detection methods, especially machine learning (ML)-based methods, is susceptible to subjectivity in derived detection map quality. Here, in this work, we demonstrate the first use of transformer-based paired neural networks (PNNs) for one-shot gas target detection for multiple gases while providing quantitative classification and detection metrics for their use on labeled data. Terabytes of training data are generated from a database of long-wave infrared HSI obtained from historical Mako sensor campaigns over Los Angeles. By incorporating labels, singular signature representations, and a model development pipeline, we can tune and select PNNs to detect multiple gas targets that are not seen in training on a quantitative basis. We additionally assess our test set detections using interpretability techniques widely employed with ML-based predictors, but less common with detection methods relying on learned latent spaces.

Hyperspectral imaging↗
DOE OSTI2024

Towards verifiable cancer digital twins: tissue level modeling protocol for precision medicine

Cancer exhibits substantial heterogeneity, manifesting as distinct morphological and molecular variations across tumors, which frequently undermines the efficacy of conventional oncological treatments. Developments in multiomics and sequencing technologies have paved the way for unraveling this heterogeneity. Nevertheless, the complexity of the data gathered from these methods cannot be fully interpreted through multimodal data analysis alone. Mathematical modeling plays a crucial role in delineating the underlying mechanisms to explain sources of heterogeneity using patient-specific data. Intra-tumoral diversity necessitates the development of precision oncology therapies utilizing multiphysics, multiscale mathematical models for cancer. This review discusses recent advancements in computational methodologies for precision oncology, highlighting the potential of cancer digital twins to enhance patient-specific decision-making in clinical settings. We review computational efforts in building patient-informed cellular and tissue-level models for cancer and propose a computational framework that utilizes agent-based modeling as an effective conduit to integrate cancer systems models that encode signaling at the cellular scale with digital twin models that predict tissue-level response in a tumor microenvironment customized to patient information. Furthermore, we discuss machine learning approaches to building surrogates for these complex mathematical models. These surrogates can potentially be used to conduct sensitivity analysis, verification, validation, and uncertainty quantification, which is especially important for tumor studies due to their dynamic nature.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Explainable Machine Learning for Functional Data

Black-box machine learning models are recognized as useful tools for prediction applications, but the algorithmic complexity of some models causes interpretation challenges. Explainability methods have been proposed to provide insight into these models, but there is little research focused on supervised modeling with functional data inputs. We argue that, especially in applications of high consequence, it is important to explicitly model the functional dependence in a black-box analysis to not obscure or misrepresent patterns in explanations. As such, we propose the V ariable importance E xplainable E lastic S hape A nalysis (VEESA) pipeline for training supervised machine learning models with functional inputs. The pipeline is an analysis process that includes the data preprocessing, modeling, and post-hoc explanations. The preprocessing is done using elastic functional principal components analysis, which accounts for vertical and horizontal variability in functional data and, ultimately, allows for explanations in the original data space that identify the important functional variability without bias due to correlated variables. Here, we demonstrate the pipeline on two high-consequence applications: explosives classification for national security and inkjet printer identification in forensic science. The applications exhibit the VEESA pipeline’s ability to provide an understanding of the characteristics of the functional data useful for prediction. Code for implementing the pipeline is available in the veesa R package (and supplemental python code).

Elastic Shape Analysis↗
DOE OSTI2025

Artificial Intelligence and Machine Learning Applications in Modern Power Systems

Machine learning (ML) and artificial intelligence (AI) algorithms offer valuable tools for the analysis and interpretation of large datasets. These tools have the capability to uncover insights that may not be readily apparent within these datasets. In recent years, the integration of ML and AI has become increasingly prevalent in various applications within the power system domain. One of the earliest instances of machine learning in power systems can be traced back to demand forecasting, where artificial neural networks were employed for short-term load forecasting. In contemporary power systems, an abundance of high-resolution geospatial and temporal data is generated at various time intervals, ranging from sub-seconds (Phasor Measurement Units or PMUs) to seconds (Supervisory Control and Data Acquisition or SCADA), minutes (Process Information or PI), and extending to days, months, and years. These datasets contain valuable information concerning system reliability and performance. This information holds the potential to offer critical insights into system operations, as well as solutions for predicting and mitigating contingencies to prevent cascading outages. Despite the immense power of machine learning tools, system operators, planners, and utilities often exhibit hesitancy in fully embracing AI-enabled system operations and planning. This cautious approach persists, even as numerous diverse applications of machine learning continue to emerge in the realm of power systems. In this chapter, our focus will delve deep into ML and AI applications tailored for power systems. These applications aim to furnish system operators with enhanced situational awareness and augment their decision-making capabilities, especially during challenging operating conditions. Specific areas of interest encompass root cause analyses of electricity market datasets and the strategic selection of representative samples from vast power system databases for training ML/AI models. Finally, the chapter will conclude with a short discussion on the future of ML/AI in power systems and possible directions that the industry is moving towards.

power system applications, machine learning (ML), ↗
DOE OSTI2024

Mechanism of Antiferroelectricity in Polycrystalline ZrO 2

The size and electric field dependent induction of polarization in antiferroelectric ZrO 2 is the key to several technological applications that are unimaginable a decade ago. However, the lack of a deeper understanding of the mechanism hinders progress. Molecular dynamics simulations of polycrystalline ZrO 2 , based on machine-learned interatomic forces with near ab initio quality, shed light on the fundamental mechanism of the size effect on the transition fields. Stress in the oxygen sublattice is the most important factor. The so constructed interatomic forces allow the calculation of the transition fields as a function of the ZrO 2 film thickness and predict the ferroelectricity at large thickness. The simulation results are validated with electrical and piezo response force microscopy measurements. The results allow a clear interpretation of the properties of the double-hysteresis loops as well as the construction of the free energy landscape of ZrO 2 grains.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Detection and Signal Processing for Near-Field Nanoscale Fourier Transform Infrared Spectroscopy

Researchers from a broad spectrum of scientific and engineering disciplines are increasingly using scattering-type near-field infrared spectroscopic techniques to characterize materials non-destructively with nanoscale spatial resolution. However, a sub-optimal understanding of a technique's implementation can complicate data interpretation and act as a barrier to entering the field. Here the key detection and processing steps involved in producing scattering-type near-field nanoscale Fourier transform infrared spectra (nano-FTIR) are outlined. The self-contained mathematical and experimental work derives and explains: i) how normalized complex-valued nano-FTIR spectra are generated, ii) why the real and imaginary components of spectra qualitatively relate to dispersion and absorption respectively, iii) a new and generally valid equation for spectra which can be used as a springboard for additional modeling of the scattering processes, and iv) an algebraic expression that can be used to extract an approximation to the sample's local extinction coefficient from nano-FTIR. The algebraic model for weak oscillators is validated with nano-FTIR and attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectra on samples of polystyrene and Kapton and further provides a pedagogical pathway to cementing some of the technique's key qualitative attributes.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Innovative Symmetrical Electrolyte Architecture Enables Ultra-Flat and Thermal Resilient Protonic Ceramic Electrochemical Cells

Protonic ceramic electrochemical cells (PCECs) represent a promising class of solid‐state energy conversion devices capable of high‐efficiency hydrogen production and power generation. However, the practical deployment of planar PCECs is fundamentally constrained by severe structural deformation and mechanical failure during fabrication, stemming from asymmetric shrinkage between the thin electrolyte and the thick NiO‐based support layer. Here, in this work, a functionally integrated, symmetry‐engineered double‐sided electrolyte (DE) design is unveiled, which not only suppresses thermally induced curvature but also unlocks significant gains in electrochemical performance and stability. This architecture intrinsically balances shrinkage dynamics across the cell bilaterally, enabling the fabrication of ultra‐flat 5 × 5 cm 2 cells with sub‐100 µm thickness variation. A numerical solid mechanics simulation is introduced to investigate and interpret this achievement. Beyond structural advantages, the DE configuration enhances the cell operational stability, delivering a low open‐circuit voltage degradation of 9.5 mV/100 h across 80 thermal cycles. This work establishes a compelling paradigm wherein architectural symmetry directly translates to both mechanical fidelity and functional enhancement, offering a promising route toward PCECs scale‐up.

08 - HYDROGEN↗
DOE OSTI2025

Multiple Twinning in Nacre and Aragonite

Twinning occurs when two crystals share a coherent interface along which their lattices are mirror symmetric. Here, twinning is investigated in biogenic and geologic aragonite (CaCO 3 ) in columnar nacre from the red abalone Haliotis rufescens, sheet nacre from the black-lip pearl oyster Pinctada margaritifera, and geologic aragonite. All samples exhibit the expected single (110) twins, characterized by a 116.2° rotation of the aragonite a-axis. Surprisingly, multiple twins—double, triple, quadruple—are also observed, each involving successive 116.2° rotations of the a-axis around the c-axis. Multiple twinning is concomitant but distinct from the well-known cyclic twinning of aragonite. Multiple twinning is most prevalent in columnar nacre, reaching up to quadruple twins, most frequently occurring between nacre tablets in the same column, whereas sheet nacre and geologic aragonite exhibit up to triple twins. The frequency of twins decreases with increasing twin multiple, consistent with a physical rather than biological origin. This interpretation is supported by observations in geologic aragonite and by simulations of columnar nacre growth, which incorporate only nucleation rate, growth rate, and basic geometric constraints, yet they reproduce the observed twinning behavior in columnar nacre, reinforcing the conclusion that multiple twinning arises from physical growth mechanisms.

Schmidt, Connor A. [Univ. of Wisconsin, Madison, W↗
DOE OSTI2025

The Anisotropic Adsorption of De Novo Allosteric Two‐Component Protein Fibers on Mica Surfaces

Protein adsorption at solid–liquid interfaces underlies many biomedical and materials applications, yet the mechanisms governing adsorption of proteins and their assemblies remain poorly understood. Here we investigate de novo–designed proteins that self-assemble into three fibrillar morphologies — small (S), large (L), and helical (H)—on muscovite mica. S-fibers are metastable, forming first but diminishing as L- and H-fibers develop and deposit. Adsorption of both fibers and monomers depends on fiber morphology and solvent environment, which is modulated by the substrate. The anisotropic surface features of the fiber types—long axis of S- and L-fibers and helical grooves of H-fibers—correlate with specific crystallographic directions on mica (001). S- and L-fibers align along the unique lattice axis, while the substrate-facing groove of H-fibers preferentially aligns along the remaining symmetry-related directions. Increasing potassium chloride (KCl) concentrations to molar levels alters adsorption, decreasing monomer coverage relative to fibers. These observations, interpreted through the effect of interfacial interface, indicate that ion-mediated modulation of hydration layers governs electrostatic interactions and alignment. This study reveals how coupling between protein topography, substrate crystallography, and hydration structure dictates selective adsorption and orientation of protein assemblies, offering insights for rational biomolecular material design.

AFM↗
DOE OSTI2026

Atomic‐Scale Surface Imaging of Bulk Epitaxial CsPbBr 3 Perovskite Single Crystals on Mica Using Light Assisted Scanning Tunneling Microscopy at Low‐Temperature (80 K)

Epitaxial single-crystalline CsPbBr 3 perovskite films on mica, prepared ex situ, are explored using a low-temperature scanning tunneling microscope (STM) by probing the unoccupied electronic states of their surface in ultra-high vacuum (UHV) at 80 K. Light-assisted STM measurements under a broadband illumination with visible light were employed to enhance and stabilize surface conductivity. STM imaging across the surface of macroscopic bulk CsPbBr 3 films reveals large flat terraces characterized by a specific type of surface reconstruction, consisting of parallel rows of U-shaped atomic nanostructures. These structures are spaced by 12 Å and exhibit an internal feature size of 5.1 Å. Density functional theory (DFT) calculations reproduce the experimental observations and reveal a competition between different orthorhombic CsPbBr 3 (110) surface reconstructions: a Cs-rich structure, identified as the most energetically stable, and three alternative Pb–Br-rich reconstructions, which are slightly higher in energy yet remain consistent with the STM data. Additional analyses that explicitly account for the mica substrate exclude the cubic CsPbBr 3 phase and other orthorhombic surface orientations, while showing that variations in the mica surface termination do not alter the preferred CsPbBr 3 (110) reconstruction. In conclusion, this combined approach thereby confirms our assignment and resolves previous STM interpretations of CsPbBr 3 .

36 MATERIALS SCIENCE↗
DOE OSTI2024

Visualizing the Internal Nanocrystallinity of Calcite Due to Nonclassical Crystallization by 3D Coherent X–Ray Diffraction Imaging

The internal crystallinity of calcite is investigated for samples synthesized using two approaches: precipitation from solution and the ammonium carbonate diffusion method. Scanning electron microscopy (SEM) analyses reveal that the calcite products precipitated using both approaches have a well–defined rhombohedron shape, consistent with the euhedral crystal habit of the mineral. The internal structure of these calcite crystals is characterized using Bragg coherent diffraction imaging (BCDI) to determine the 3D electron density and the atomic displacement field. BCDI reconstructions for crystals synthesized using the ammonium carbonate diffusion approach have the expected euhedral shape, with internal strain fields and few internal defects. In contrast, the crystals synthesized by precipitation from solution have very complex external shapes and defective internal structures, presenting null electron density regions and pronounced displacement field distributions. These heterogeneities are interpreted as multiple crystalline domains, created by a nonclassical crystallization mechanism, where smaller nanoparticles coalescence into the final euhedral particles. The combined use of SEM, X–ray diffraction (XRD), and BCDI allows for structurally differentiating calcite crystals grown with different approaches, opening new opportunities to understand how grain boundaries and internal defects alter calcite reactivity.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Wide‐Field Bond Quality Evaluation Using Frequency Domain Thermoreflectance with Deep Neural Network Feature Reconstruction

Heterogeneous integration of microelectronic components provides a pathway to improve circuit/component performance; however, this comes with assembly challenges, in particular due to complex interfaces via subsurface bump bonds. The ability of these bonds to transmit electrical signals and conduct heat to the carrier substrate limits component performance. In this work, hyperspectral frequency‐domain thermoreflectance (FDTR) imaging is demonstrated as a robust technique for evaluating the quality of subsurface indium bump bonds in a surrogate microelectronic sample. By performing microscale FDTR imaging with coarse motion image stitching, thermal phase maps that cover a 4 mm by 4 mm field‐of‐view with subsurface feature sensitivity at depths greater than 50 µm are obtained. The resulting FDTR hyperspectral data contains more than three million pixels and reveal the quality of subsurface microbump arrays. Wide‐field analysis of bonded versus gap regions is enabled by deep neural network feature reconstruction, that after training, rapidly provides an interpretable representation of bond quality. Utility of noisy higher frequency FDTR phase maps, i.e., near the computationally predicted sensing depth limit, results in an average prediction error of 11%. Taken together, FDTR with neural network‐based analysis demonstrates subsurface bond monitoring at length scales relevant for heterogeneously integrated microelectronics.

FDTR↗
DOE OSTI2024

Suppressed Lone Pair Electrons Explain Unconventional Rise of Lattice Thermal Conductivity in Defective Crystalline Solids

Manipulating thermal properties of materials can be interpreted as the control of how vibrations of atoms (known as phonons) scatter in a crystal lattice. Compared to a perfect crystal, crystalline solids with defects are expected to have shorter phonon mean free paths caused by point defect scattering, leading to lower lattice thermal conductivities than those without defects. While this is true in many cases, alloying can increase the phonon mean free path in the Cd-doped AgSnSbSe 3 system to increase the lattice thermal conductivity from 0.65 to 1.05 W m –1 K –1 by replacing 18% of the Sb sites with Cd. It is found that the presence of lone pair electrons leads to the off-centering of cations from the centrosymmetric position of a cubic lattice. X-ray pair distribution function analysis reveals that this structural distortion is relieved when the electronic configuration of the dopant element cannot produce lone pair electrons. Furthermore, a decrease in the Grüneisen parameter with doping is experimentally confirmed, establishing a relationship between the stereochemical activity of lone pair electrons and the lattice anharmonicity. The observed “harmonic” behavior with doping suggests that lone pair electrons must be preserved to effectively suppress phonon transport in these systems.

36 MATERIALS SCIENCE↗