Search NASA⌕ Search

SEARCH · Search NASA

Results for “interpretable models”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Development of an L-Edge X-ray Absorbance Spectrometer for Monitoring Dissolver Solutions in H-Canyon

Savannah River National Laboratory has developed a monitor to measure plutonium and uranium concentrations in solutions of dissolved nuclear fuel. The monitor will be installed in the sample aisle location for the 6.3D Dissolver in the Savannah River Site’s H-Canyon and used in support of the electrolytic dissolution such as Fast Critical Assembly fuel. The monitor is based on the atomic absorbance of x-rays. Elements are differentiated by the appearance of absorbance features at specific energies of the x-ray spectrum that correspond to L-edge transitions of inner core electrons. Hence, the technique is called L-Edge X-Ray Absorbance Spectroscopy (L-XRAS). The technique is suitable for nuclear fuel processing due to its relative insensitivity to other components of the dissolver solution, such as nitric acid, transition metals (Fe, Cr, Ni, Mn) such as those from stainless steel, particulates, and catalysts and additives. The instrumentation consists of a commercially available x-ray source and detector, a sample cell designed to interface with the airlift sampler associated with H-Canyon Tank 6.3D, and a stainless steel enclosure. SRNL wrote instrument control software and developed chemometric models to interpret x-ray intensity spectra and estimate analyte concentrations and uncertainties in real time.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Are Marine Low Cloud Droplet Concentrations Buffered by Entrained Aitken‐Mode Aerosol (Final Technical Report)

During the summertime, the high-latitude oceans come to life with green phytoplankton, which gain their energy from sunlight and are food for sea creatures small and large. When the phytoplankton are eaten or die, sulfur-rich gases are released under the ocean surface and mix into the air. Observations suggest that, over the Southern Ocean, frequent storms lift this air high into the atmosphere while raining out particulates like salt. As a result, the sulfur-rich air then spawns high concentrations of small ‘Aitken-mode’ aerosol particles. We hypothesize that these particles work their way down into the marine boundary layer, where they can replenish the supply of cloud-condensation nuclei scavenged by frequent precipitation. Further, this process maintains high concentrations of liquid cloud droplets in austral summer, promoting more sunlight to be reflected to space. We call this ‘Aitken buffering’. The primary objective of this project has been to document and test what role Aitken-mode aerosols play in clouds over the Southern Ocean and elsewhere. This effort has included three main components: 1) developing a computer model that realistically simulates the aerosol processes and the small-scale turbulent air motions that move aerosols around and create the clouds, 2) using that model to interpret and extend these observations for process understanding, by allowing different factors that contribute to the aerosol budget, such as surface wind speed, precipitation, surface gas exchange, etc. to be separated, and 3) studying Aitken-mode aerosol and its variability with a focus over the Southern Ocean and Antarctica, using data from Atmospheric Radiation Measurement (ARM) sites and other available observations. Initial computer studies in more idealized conditions found that elevated concentrations of Aitken-mode aerosols above the clouds could help prevent the breakup of those clouds by acting as cloud-condensation nuclei after they were entrained into the cloudy boundary layer. Simulations of a day during the ACE-ENA field campaign showed that Aitken-mode aerosols could also prevent cloud breakup under more realistic conditions. A new method that extracts information about Aitken-mode aerosols from measurements of aerosols onto which cloud droplets can form finds that Aitken-mode aerosols do vary seasonally over the Southern Ocean, with a peak in summertime, as described above. Other work during this project has focused on understanding how patterns of water vapor, clouds and precipitation are coupled within low-lying clouds over the oceans, and also on how cloud droplets cluster within clouds and how the distribution of cloud droplet sizes change as dry air is mixed into clouds, with the latter studies also using observations from ACE-ENA.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Elucidating the Morphological Instability Mechanisms During Electrodeposition of Active Metals

The primary aim of this investigation is to elucidate the mechanisms by which a group of metals pertinent to battery technology exhibit unstable growth morphology during electrodeposition, which are crucial for the operational efficacy of batteries. The metals under consideration include alkali metals alongside zinc, all of which are characterized by high atomic mobility and reactivity with the electrolytes employed in battery systems. These materials represent promising electrode candidates for next-generation rechargeable batteries that are anticipated to deliver significantly enhanced energy density at a reduced cost. Nevertheless, the widespread occurrence of distinctly non-uniform morphologies, exemplified by the emergence of filamentous and moss-like structures, constitutes a significant impediment to their effective utilization, as it leads to accelerated capacity degradation and potential internal short circuits. This study addresses a critical question that has thus far garnered limited attention: Does the residual stress induced by the plating process play an instrumental role in inducing the morphological instability? Utilizing zinc as the primary model system, this project will be executed through three interconnected tasks: (1) the quantification of the relationship between plating stress and electroplating morphologies, (2) the three-dimensional imaging of the microstructure of the mossy structure at the nanoscale, and (3) the development of a mesoscale electroplating model to interpret empirical findings and generate additional predictive insights.

25 ENERGY STORAGE↗
DOE OSTI2025

Fundamental Studies of Soiling and Cementation of PV Cover Glass Materials: Addressing Reliability with Advanced X-ray Scattering/Spectroscopy and First Principles Modeling (Final Technical Report)

Accumulation of soils and other particulate matter on the front cover glass of solar photovoltaic (PV) modules results in transmission losses that detrimentally affect the power output of PV installations. The conventional solution to this problem is manual abrasive scrubbing of modules, which entails significant water usage and manpower. To further combat this issue, there is a concerted effort within the PV industry to develop anti-soiling (AS) coatings to mitigate power losses due to soiling of PV modules, which can exceed 35% in some cases. However, relatively little is known about the fundamental physical and chemical mechanisms that enable anti-soiling behavior. In this project, a combination of advanced X-ray analysis tools and first principles computational modeling has employed to understand the physical and chemical interactions between environmental soils and PV cover glass materials. The specific objectives were: 1) investigate soiling interactions and cementation behavior of relevant PV materials, including bare glass, conventional antireflective (AR) coatings, and a commercial AS coating, using a library of representative particulate soils, and 2) utilize first principles computational spectroscopy modeling to interpret the experimental X-ray spectroscopy measurements and determine the detailed surface chemistry changes that occur on these surfaces in the presence of soiling and cementation.

14 SOLAR ENERGY↗
DOE OSTI2026

Microscopic Scattering Approach to In-Gap States

We develop a microscopic scattering formalism to describe Yu-Shiba-Rusinov (YSR) states due to a single Cr adatom on the Bi-terminated surface of beta Bi2Pd, by combining ab initio Wannier functions with a real-space Green's function approach in the Bogoliubov-de Gennes formalism[1]. Our framework reproduces key scanning tunneling spectroscopy features, including a single particle-hole asymmetric YSR peak and isotropic dIdV maps around the impurity. Decomposing the YSR states reveals contributions from four nearly degenerate C4v representations, with energy broadening masking their individual signatures. Spin-orbit coupling induces partial spin polarization, while the spatial asymmetry between particle and hole components arises from Cr d-Bi p hybridization. These results highlight the importance of realistic band structures and microscopic modeling for interpreting STM data for magnetic in-gap states on superconductors. Further advances examining layered 2D material surfaces, such as NbSe2, will be described[2]. For this system the superconducting properties are obtained from a full anisotropic Eliashberg calculation of the superconducting order parameter along with the charge density wave gap. Additional features associated with proposals to measure the dynamics of these individual YSR states will be presented. [1] arXiv:2507.08740 [2] arXiv:2507.11856

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
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 OSTI2024

Catalytic Resonance Theory: Forecasting the Flow of Programmable Catalytic Loops

Chemical transformations on catalyst surfaces occur through series and parallel reaction pathways. These complex networks and their behavior can be most simply evaluated through a three-species surface reaction loop (A* to B* to C* to A*) that is internal to the overall chemical reaction. Application of an oscillating dynamic catalyst to this reactive loop has been shown to exhibit one of three types of behavior: (1) a positive net flux of molecules about the loop in the clockwise direction, (2) a negative net flux of molecules about the loop in the counterclockwise direction, or (3) negligible flux of molecules about the loop at the limit cycle of reaction. Three-species surface loops were simulated with microkinetic modeling to assess the reaction loop behavior resulting from a catalytic surface oscillating between two or more catalyst surface energy states. Selected input parameters for the simulations spanned an 11-dimensional parameter space using 127 688 different parameter combinations. Their converged limit cycle solutions were analyzed for their loop turnover frequencies, the majority of which were found to be approximately zero. Classification and regression machine learning models were trained to predict the sign and magnitude of the loop turnover frequency and successfully performed above accessible baselines. Notably, the classification models exhibited a baseline weighted F1 score of 0.49, whereas trained models achieved weighted F1 scores of 0.94 and 0.96 when trained on the parameters used to define the simulations and derived rate constants, respectively. The trained models successfully predicted catalytic loop behavior, and interpretation of these models revealed all input parameters to be important for the prediction and performance of each model.

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

Evaluation of historical precipitation interannual variability in CMIP6 over the United States

Interannual precipitation variability profoundly influences society via its effects on agriculture, water resources, infrastructure, and disaster risks. In this study, we use daily in situ precipitation observations from the global historical climatology network-daily (GHCN-D) to assess the ability of 21 Coupled Model Intercomparison Project Phase 6 (CMIP6) models, including the 50-member fifth-generation Canadian Earth System Model single model initial-condition large ensemble (CanESM5_SMILE), to realistically simulate historical interannual precipitation variability trends within 17 regions of the contiguous United States (CONUS). We assess how accurately the CMIP6 simulations align with observational data across annual, summer, and winter periods, focusing on four key hydrometeorological metrics, including interannual precipitation variability, relative interannual precipitation variability (coefficient of variation), annual mean precipitation, and annual wet day frequency. Our findings reveal that CMIP6 ensemble members generally reproduce the spatial patterns of observed trends in annual mean precipitation. In most regions, models agree well with the signs of observed changes in annual mean precipitation, though discrepancies in trend magnitude are evident. Further, observed trends in winter mean precipitation broadly exhibit a spatial pattern similar to that of the observed annual mean. However, analysis of the CanESM5_SMILE shows that trends in precipitation variability may primarily be the result of model-simulated internal variability, suggesting caution in interpreting multi-model single-realization ensemble results. Challenges in accurately simulating interannual precipitation variability underscore the need for ongoing model refinement and validation to enhance climate projections, especially in regions vulnerable to extreme precipitation events.

54 ENVIRONMENTAL SCIENCES↗
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

Interpretable, extensible linear and symbolic regression models for charge density prediction using a hierarchy of many-body correlation descriptors

Here, density functional theory (DFT) is routinely used to make electronic structure predictions for high-throughput screening of materials and molecules for technologically relevant areas, like the identification of better catalysts, electronic materials, and drug discovery. However, the DFT formalism is limited by (a) its poor (quadratic-to-quartic) scaling, and (b) the need to perform repeated eigenvalue computations of the electronic Hamiltonian as part of its self-consistent field (SCF) iteration procedure to obtain the converged ground state electron density, ρ (r). Approaches that directly predict ρ (r) of a structure with high accuracy can accelerate conventional SCF calculations and can also be used in linearly scaling methods such as orbital-free DFT. To this end, we present a procedure to predict the ground state electron density of molecular and periodic three-dimensional systems directly from the atomic structure with a particular emphasis on physical interpretability. In our framework, ρ (r) is modeled using many-body correlation descriptors that accurately capture the effects of local atomic arrangements in the neighborhood of a grid point. Our use of a linear regression scheme to fit to charge density data enables transparent analysis of the relative contributions of various types of local atomic correlations. By systematically including increasingly complex correlations, our model is shown to accurately predict ρ (r) for a variety of chemically and electronically diverse systems — amorphous Ge, Al(001) slab, crystalline Ga 2 O 3 , molecular benzene, and polyethylene. We then demonstrate a symbolic regression-based protocol to construct easily computable, interpretable features from lower-order correlations that significantly improves our electron density predictions with effectively no increase in the computational cost.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Enabling Strong Neutrino Self-Interaction with an Unparticle Mediator

Recent explorations of the cosmic microwave background and the large-scale structure of the universe have indicated a preference for sizable neutrino self-interactions, much stronger than what the standard model offers. When interpreted in the context of simple particle-physics models with a light, neutrinophilic scalar mediator, some of the hints are already in tension with the combination of terrestrial, astrophysical, and cosmological constraints. We take a novel approach by considering neutrino self-interactions through a mediator with a smooth, continuous spectral density function. We consider Georgi’s unparticle with a mass gap as a concrete example and point out two useful effects for mitigating two leading constraints. (i) The Unparticle is “broadband’—it occupies a wide range of masses which allows it to pass the early universe constraint on effective number of extra neutrinos ( Δ N eff ) even if the mass gap lies below the MeV scale. (ii) Scattering involving unparticles is less resonant, which lifts the constraint set by IceCube based on a recent measurement of ultra-high-energy cosmogenic neutrinos. Our analysis shows that an unparticle mediator can open up ample parameter space for strong neutrino self-interactions of interest to cosmology and serves a well-motivated target for upcoming experiments. Published by the American Physical Society 2025

Foroughi-Abari, Saeid (ORCID:0000000294061896)↗
DOE OSTI2024

Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications

Abstract Robust quantification of predictive uncertainty is a critical addition needed for machine learning applied to weather and climate problems to improve the understanding of what is driving prediction sensitivity. Ensembles of machine learning models provide predictive uncertainty estimates in a conceptually simple way but require multiple models for training and prediction, increasing computational cost and latency. Parametric deep learning can estimate uncertainty with one model by predicting the parameters of a probability distribution but does not account for epistemic uncertainty. Evidential deep learning, a technique that extends parametric deep learning to higher-order distributions, can account for both aleatoric and epistemic uncertainties with one model. This study compares the uncertainty derived from evidential neural networks to that obtained from ensembles. Through applications of the classification of winter precipitation type and regression of surface-layer fluxes, we show evidential deep learning models attaining predictive accuracy rivaling standard methods while robustly quantifying both sources of uncertainty. We evaluate the uncertainty in terms of how well the predictions are calibrated and how well the uncertainty correlates with prediction error. Analyses of uncertainty in the context of the inputs reveal sensitivities to underlying meteorological processes, facilitating interpretation of the models. The conceptual simplicity, interpretability, and computational efficiency of evidential neural networks make them highly extensible, offering a promising approach for reliable and practical uncertainty quantification in Earth system science modeling. To encourage broader adoption of evidential deep learning, we have developed a new Python package, Machine Integration and Learning for Earth Systems (MILES) group Generalized Uncertainty for Earth System Science (GUESS) (MILES-GUESS) ( https://github.com/ai2es/miles-guess ), that enables users to train and evaluate both evidential and ensemble deep learning. Significance Statement This study demonstrates a new technique, evidential deep learning, for robust and computationally efficient uncertainty quantification in modeling the Earth system. The method integrates probabilistic principles into deep neural networks, enabling the estimation of both aleatoric uncertainty from noisy data and epistemic uncertainty from model limitations using a single model. Our analyses reveal how decomposing these uncertainties provides valuable insights into reliability, accuracy, and model shortcomings. We show that the approach can rival standard methods in classification and regression tasks within atmospheric science while offering practical advantages such as computational efficiency. With further advances, evidential networks have the potential to enhance risk assessment and decision-making across meteorology by improving uncertainty quantification, a longstanding challenge. This work establishes a strong foundation and motivation for the broader adoption of evidential learning, where properly quantifying uncertainties is critical yet lacking.

Schreck, John S.↗
DOE OSTI2026

Search for higgsinos in compressed mass spectra using low-momentum tracks in pp collisions at s=13 TeV with the ATLAS detector

This paper presents two searches for the electroweak production of higgsinos with compressed mass spectra using 140 fb−1 of s=13$$ \sqrt{s}=13 $$ TeV proton-proton collision data collected by the ATLAS experiment at the Large Hadron Collider. Events are required to feature an energetic jet, large missing transverse momentum, and at least one low-momentum charged particle that serves as a candidate higgsino decay product. In the first search, targeting higgsino mass splittings in the range of 0.3–1 GeV, the higgsinos are expected to predominantly decay into pions that are identified as low-momentum charged particles with large transverse impact parameters due to the long higgsino lifetime (cτ ≈ ?(0.1–10 mm)), and neural networks are used to discriminate between signal and background processes. The second search targets larger mass splittings in the range of 1–3 GeV, where the higgsinos are expected to decay promptly into low-momentum leptons, one of which is identified by dedicated low-momentum electron or muon taggers based on neural networks utilising tracking and calorimeter information. No significant excess above the Standard Model prediction is observed in either search and the results are interpreted within simplified models, to set lower limits on the masses of the higgsino-like charginos and neutralinos. Together, these searches exclude chargino masses below 126 GeV at 95% confidence level for mass splittings between the chargino and lightest neutralino in the range of 0.3–2 GeV. This represents the first ATLAS constraints in a portion of this parameter space and surpasses the limits previously set by other experiments.

Aad, G↗
DOE OSTI2024

Integrating multi-modal remote sensing, deep learning, and attention mechanisms for yield prediction in plant breeding experiments

In both plant breeding and crop management, interpretability plays a crucial role in instilling trust in AI-driven approaches and enabling the provision of actionable insights. The primary objective of this research is to explore and evaluate the potential contributions of deep learning network architectures that employ stacked LSTM for end-of-season maize grain yield prediction. A secondary aim is to expand the capabilities of these networks by adapting them to better accommodate and leverage the multi-modality properties of remote sensing data. In this study, a multi-modal deep learning architecture that assimilates inputs from heterogeneous data streams, including high-resolution hyperspectral imagery, LiDAR point clouds, and environmental data, is proposed to forecast maize crop yields. The architecture includes attention mechanisms that assign varying levels of importance to different modalities and temporal features that, reflect the dynamics of plant growth and environmental interactions. The interpretability of the attention weights is investigated in multi-modal networks that seek to both improve predictions and attribute crop yield outcomes to genetic and environmental variables. This approach also contributes to increased interpretability of the model's predictions. The temporal attention weight distributions highlighted relevant factors and critical growth stages that contribute to the predictions. The results of this study affirm that the attention weights are consistent with recognized biological growth stages, thereby substantiating the network's capability to learn biologically interpretable features. Accuracies of the model's predictions of yield ranged from 0.82-0.93 R 2 ref in this genetics-focused study, further highlighting the potential of attention-based models. Further, this research facilitates understanding of how multi-modality remote sensing aligns with the physiological stages of maize. The proposed architecture shows promise in improving predictions and offering interpretable insights into the factors affecting maize crop yields, while demonstrating the impact of data collection by different modalities through the growing season. By identifying relevant factors and critical growth stages, the model's attention weights provide valuable information that can be used in both plant breeding and crop management. The consistency of attention weights with biological growth stages reinforces the potential of deep learning networks in agricultural applications, particularly in leveraging remote sensing data for yield prediction. To the best of our knowledge, this is the first study that investigates the use of hyperspectral and LiDAR UAV time series data for explaining/interpreting plant growth stages within deep learning networks and forecasting plot-level maize grain yield using late fusion modalities with attention mechanisms.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

VERITAS : A density-functional theory-based multiband kinetic model for understanding x-ray spectroscopy of dense plasmas

X-ray spectroscopy has long been a powerful diagnostic tool for hot, dilute plasmas, providing insights into plasma conditions by measuring line shifts and broadenings of atomic transitions. The technique critically depends on the accuracy of atomic physics models used to interpret spectroscopic measurements for inferring plasma properties such as free-electron density and temperature. Over the past decades, the atomic and plasma physics communities have developed robust atomic physics models to account for various processes in hot, dilute classical plasmas. While these models have been successful in that regime, their applicability becomes uncertain when interpreting x-ray spectroscopy experiments of above-solid-density plasmas. Given that finite-temperature density-functional theory (DFT) offers a more accurate description of dense plasma environments, we present the development of a DFT-based multi-band kinetic model, VERITAS, designed to improve the interpretation of x-ray spectroscopic measurements in high-density plasmas produced by laser-driven spherical implosions. This work details the VERITAS model and its application to both time-integrated and time-resolved x-ray spectra from implosion experiments on OMEGA. The advantages and limitations of the VERITAS model will also be discussed, along with potential directions for advancing x-ray spectroscopy of dense and superdense plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

A structured framework for predicting sustainable aviation fuel properties using liquid-phase FTIR and machine learning

Sustainable aviation fuels have the potential to improve efficiency, reduce emissions, and enhance energy security. To help identify viable sustainable aviation fuels and accelerate research, machine learning models have been developed to predict relevant physicochemical properties. However, many models have limited applicability, leverage data from complex analytical techniques with confined spectral ranges, or use feature decomposition methods that offer limited interpretability. Using liquid-phase Fourier Transform Infrared (FTIR) spectra, this study presents a structured method for creating accurate and interpretable property prediction models for neat molecules, aviation fuels, and blends. Liquid FTIR spectra can be collected quickly and consistently, offering high reliability, sensitivity, and component specificity using less than 2 ml of sample. The method first decomposes FTIR spectra into fundamental building blocks using non-negative matrix factorization (NMF) to enable scientific analysis of FTIR spectra attributes and fuel properties. The NMF features are then used to create five ensemble models for predicting final boiling point, flash point, freezing point, density at 15°C, and kinematic viscosity at -20°C. All models were trained using experimental property data from neat molecules, aviation fuels, and blends. The models accurately predict key properties across a broad range of neat molecules and representative fuels and blends, while enabling interpretation of relationships between compositional elements, such as functional groups or chemical classes, and their resulting properties. This demonstrates strong potential to support sustainable aviation fuel research and development. The models and data are available on an interactive web tool.

Fourier transform infrared spectroscopy↗
DOE OSTI2026

A human-in-the-loop explanation framework for morphologically transparent AI predictions from whole-slide images

Deep learning models enable the prediction of clinical endpoints from whole-slide images (WSIs), but many such models function as “black boxes”, lacking transparency about whether and which histomorphological patterns drive their predictions, hindering interpretability and clinical adoption. Here we propose a human-in-the-loop explanation framework, MorphoXAI, which provides both local and global interpretability for deep learning models by incorporating human-expert interpretations. At the global level, it reveals the histomorphological patterns on which the model consistently relies to distinguish between classes of WSIs, as well as the patterns associated with confusion between classes. At the local level, it indicates which of these patterns are used in the prediction of an individual WSI and which regions within the slide correspond to such patterns. We validated our method across multiple deep learning–based WSI analysis tasks spanning different tissue types. The results show that our framework generates explanations that accurately reflect the histomorphology underlying the model’s predictions at both global and local levels. For interpretability and clinical utility in diagnostic contexts, human evaluation results showed that our explanations were easy to interpret, rich in diagnostic features, and directly helpful for diagnostic decision-making, thereby enhancing pathologist-AI collaboration. Our work highlights that unifying global and local explanations and grounding them in expert-interpreted morphology enhances the interpretability and verifiability of deep learning models, thereby facilitating the transparent deployment of such models in clinical practice.

Lou, Peiliang↗
DOE OSTI2025

Search for dark matter produced in association with one or two top quarks in proton-proton collisions at $\sqrt{\text{s}}$ = 13 TeV

A search is performed for dark matter (DM) produced in association with a single top quark or a pair of top quarks using the data collected with the CMS detector at the LHC from proton-proton collisions at a center-of-mass energy of 13 TeV, corresponding to 138 fb −1 of integrated luminosity. An excess of events with a large imbalance of transverse momentum is searched for across 0, 1 and 2 lepton final states. Novel multivariate techniques are used to take advantage of the differences in kinematic properties between the two DM production mechanisms. No significant deviations with respect to the standard model predictions are observed. The results are interpreted considering a simplified model in which the mediator is either a scalar or pseudoscalar particle and couples to top quarks and to DM fermions. Axion-like particles that are coupled to top quarks and DM fermions are also considered. Expected exclusion limits of 410 and 380 GeV for scalar and pseudoscalar mediator masses, respectively, are set at the 95% confidence level. A DM particle mass of 1 GeV is assumed, with mediator couplings to fermions and DM particles set to unity. A small signal-like excess is observed in data, with the largest local significance observed to be 1.9 standard deviations for the 150 GeV pseudoscalar mediator hypothesis. Because of this excess, mediator masses are only excluded below 310 (320) GeV for the scalar (pseudoscalar) mediator. The results are also translated into model-independent 95% confidence level upper limits on the visible cross section of DM production in association with top quarks, ranging from 1 pb to 0.02 pb.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗