Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Increased Interpretability for Model-Driven Deception: MARS LDRD Project

Machine learning has been proposed as a solution to several cybersecurity solutions and one of the most promising applications is for digital twins for intrusion detection and driving deceptive defense. However, machine learning techniques often result in a black-box function that is difficult for end users to interpret which for deception limits their ability to effectively define decoys. In this report, an approach to validate the equations learned are accurate is provided and demonstrated. Following, begins the process of addressing this issue for a model-driven deception technology that produces equations representing the physical process controlled by operation technology devices. This research was performed by applying subject matter expert context to machine learned models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Development of a New Chelation Model: Bioassay Data Interpretation and Dose Assessment after Plutonium Intake via Wound and Treatment with DTPA

The administration of chelation therapy to treat significant intakes of actinides, such as plutonium, affects the actinide’s normal biokinetics. In particular, it enhances the actinide’s rate of excretion, such that the standard biokinetic models cannot be applied directly to the chelation-affected bioassay data in order to estimate the intake and assess the radiation dose. Here we propose a new chelation model that can be applied to the chelation-affected bioassay data after plutonium intake via wound and treatment with DTPA. In the proposed model, chelation is assumed to occur in the blood, liver, and parts of the skeleton. Ten datasets, consisting of measurements of 14 C-DTPA, 238 Pu, and 239 Pu involving humans given radiolabeled DTPA and humans occupationally exposed to plutonium via wound and treated with chelation therapy, were used for model development. The combined dataset consisted of daily and cumulative excretion (urine and feces), wound counts, measurements of excised tissue, blood, and post-mortem tissue analyses of liver and skeleton. The combined data were simultaneously fit using the chelation model linked with a plutonium systemic model, which was linked to an ad hoc wound model. The proposed chelation model was used for dose assessment of the wound cases used in this study.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Poster Abstract: Leveraging Large Language Models to Reveal Interpretable Cooling Behaviors from Smart Thermostat Data

Frequent heatwaves and hot summers increasingly challenge occupant comfort, health, and energy grid stability. Addressing these challenges requires a detailed understanding of household cooling behaviors, such as thermostat adjustments and adaptive responses to extreme conditions. Traditional analyses often rely on aggregated numerical metrics that overlook subtle but important household-specific variations. In this study, we introduce a generalizable methodology that integrates large language models (LLMs) with vision capabilities to enable scalable and detailed analysis of residential thermostat data. Using Ecobee's Donate Your Data (DYD) dataset—which provides five-minute records of indoor temperatures, thermostat setpoints, and HVAC runtimes—we focus on two U.S. cities with contrasting summer climates : Austin (TX) and Phoenix (AZ). Because raw time-series data are not well suited for direct LLM analysis, we transform them into visual representations, such as daily indoor temperature trajectories and weekly runtime histograms, to better capture behavioral variations. Leveraging LLMs' visual interpretation, we extract descriptive behavioral features, including temperature preferences, time-of-day cooling orientation, anticipatory versus reactive heatwave responses, and behavioral consistency. These semantic features support unsupervised clustering to identify distinct occupant archetypes at scale, revealing differences—such as morning-centric anticipatory coolers versus households that shift toward warmer setpoints during heatwaves—that can inform demand response, resilience planning, and health-aware interventions. By converting raw numerical data into interpretable behavioral patterns, this methodology enables scalable and practical analysis of occupant behavior, supporting actionable insights for comfort, resilience, and energy management.

Nihar, Kopal↗
NASA NTRS1980

The effect of directional radiation models on the interpretation of earth radiation budget measurements

A parameter estimation technique is presented to estimate the radiative flux density distribution over the earth from a set of radiometer measurements at satellite altitude. The technique analyzes measurements from a wide field of view, horizon to horizon, nadir pointing sensor with a mathematical technique to derive the radiative flux density estimates at the top of the atmosphere for resolution elements smaller than the sensor field of view. A computer simulation of the data analysis technique is presented for both earth-emitted and reflected radiation. The errors resulting from the assumed directional radiation model, spatial model and random measurement error have little effect on the global mean radiation. Zonal estimates were found to be more sensitive to the spatial model than to the directional radiation model. Results from analyzing medium field of view measurements showed a much greater sensitivity to the directional radiation model even on a global scale.

Green, R. N.↗
DOE OSTI2020

DDxNet: a deep learning model for automatic interpretation of electronic health records, electrocardiograms and electroencephalograms

Effective patient care mandates rapid, yet accurate, diagnosis. With the abundance of non-invasive diagnostic measurements and electronic health records (EHR), manual interpretation for differential diagnosis has become time-consuming and challenging. This has led to wide-spread adoption of AI-powered tools, in pursuit of improving accuracy and efficiency of this process. While the unique challenges presented by each modality and clinical task demand customized tools, the cumbersome process of making problem-specific choices has triggered the critical need for a generic solution to enable rapid development of models in practice. In this spirit, we develop DDxNet, a deep architecture for time-varying clinical data, which we demonstrate to be well-suited for diagnostic tasks involving different modalities (ECG/EEG/EHR), required level of characterization (abnormality detection/phenotyping) and data fidelity (single-lead ECG/22-channel EEG). Using multiple benchmark problems, we show that DDxNet produces high-fidelity predictive models, and sometimes even provides significant performance gains over problem-specific solutions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Machine Learning Framework for Characterizing Processing–Structure Relationship in Block Copolymer Thin Films

The morphology of block copolymers (BCPs) critically influences material properties and applications. This work introduces a machine learning (ML)-enabled, high-throughput framework for analyzing grazing incidence small-angle X-ray scattering (GISAXS) data and atomic force microscopy (AFM) images to characterize BCP thin film morphology. A convolutional neural network was trained to classify AFM images by surface features, achieving 97% testing accuracy. Classified images were then analyzed to extract 2D grain size measurements from the samples in a high-throughput manner. ML models were trained to predict domain orientation based on processing parameters such as solvent ratio, additive type, and additive ratio. GISAXS-based properties were predicted with strong performances (R 2 > 0.75), while AFM-based property predictions were less accurate (R 2 < 0.60), likely due to the localized nature of AFM measurements compared to the bulk information captured by GISAXS. Beyond model performance, interpretability was addressed using SHapley Additive exPlanations (SHAP). SHAP analysis revealed that the additive ratio had the largest impact on morphological predictions, where additive provides the BCP chains with increased volume to rearrange into thermodynamically favorable morphologies. This interpretability helps validate model predictions and offers insight into parameter importance. Altogether, the presented framework combining high-throughput characterization and interpretable ML offers an approach to exploring and optimizing BCP thin film morphology across a broad processing landscape.

36 MATERIALS SCIENCE↗
NASA NTRS2021

A data–model approach to interpreting speleothem oxygen isotope records from monsoon regions

Reconstruction of past changes in monsoon climate from speleothem oxygen isotope (δ 18 O) records is complex because δ 18 O signals can be influenced by multiple factors including changes in precipitation, precipitation recycling over land, temperature at the moisture source, and changes in the moisture source region and transport pathway. Here, we analyse >150 speleothem records of the Speleothem Isotopes Synthesis and AnaLysis (SISAL) database to produce composite regional trends in δ 18 O in monsoon regions; compositing minimises the influence of site-specific karst and cave processes that can influence individual site records. We compare speleothem δ 18 O observations with isotope-enabled climate model simulations to investigate the specific climatic factors causing these regional trends. We focus on differences in δ 18 O signals between the mid-Holocene, the peak of the Last Interglacial (Marine Isotope Stage 5e) and the Last Glacial Maximum as well as on δ 18 O evolution through the Holocene. Differences in speleothem δ 18 O between the mid-Holocene and the Last Interglacial in the East Asian and Indian monsoons are small, despite the larger summer insolation values during the Last Interglacial. Last Glacial Maximum δ 18 O values are significantly less negative than interglacial values. Comparison with simulated glacial–interglacial δ 18 O shows that changes are principally driven by global shifts in temperature and regional precipitation. Holocene speleothem δ 18 O records show distinct and coherent regional trends. Trends are similar to summer insolation in India, China and southwestern South America, but they are different in the Indonesian–Australian region. Redundancy analysis shows that 37 % of Holocene variability can be accounted for by latitude and longitude, supporting the differentiation of records into individual monsoon regions. Regression analysis of simulated precipitation δ 18 O and climate variables show significant relationships between global Holocene monsoon δ 18 O trends and changes in precipitation, atmospheric circulation and (to a lesser extent) source area temperature, whereas precipitation recycling is non-significant. However, there are differences in regional-scale mechanisms: there are clear relationships between changes in precipitation and δ 18 O for India, southwestern South America and the Indonesian–Australian regions but not for the East Asian monsoon. Changes in atmospheric circulation contribute to δ 18 O trends in the East Asian, Indian and Indonesian–Australian monsoons, and a weak source area temperature effect is observed over southern and central America and Asia. Precipitation recycling is influential in southwestern South America and southern Africa. Overall, our analyses show that it is possible to differentiate the impacts of specific climatic mechanisms influencing precipitation δ 18 O and use this analysis to interpret changes in speleothem δ 18 O.

speleothem oxygen isotope records↗
NASA NTRSDate not supplied

Application of a Bayesian Framework for Plasticity Model Selection

Interpretable Machine Learning (IML) has performed well when tasked with deriving constitutive material models. However, IML has been shown to prefer models that overfit noise in data, which tends to lead to bloat and a decrease in interpretability. Due to these issues, the ability of IML to reliably derive models that fit the data and are both interpretable and generalizable is limited. A method developed recently has shown promise to improve upon traditional IML by using a Bayesian fitness definition for the evolution of free-form models with non-deterministic parameters. This framework was developed for genetic-programming-based symbolic regression(GPSR) and involves model parameter estimation using Sequential Monte Carlo sampling (SMC).The method has demonstrated a reduction in bloat when dealing with noisy data in comparison to conventional GPSR. The results of this framework applied to stress-strain data for copper show models that more effectively predict the experimental data better than was previously shown with GPSR.

plasticity↗
DOE OSTI2025

Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets

This study addresses the challenge of statistically extracting generative factors from complex, high-dimensional datasets in unsupervised or semi-supervised settings. We investigate encoder-decoder-based generative models for nonlinear dimensionality reduction, focusing on disentangling low-dimensional latent variables corresponding to independent physical factors. Introducing Aux-VAE, a novel architecture within the classical Variational Autoencoder framework, we achieve disentanglement with minimal modifications to the standard VAE loss function by leveraging prior statistical knowledge through auxiliary variables. These variables guide the shaping of the latent space by aligning latent factors with learned auxiliary variables. We validate the efficacy of Aux-VAE through comparative assessments on multiple datasets, including astronomical simulations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Response to ‘Stochastic and deterministic interpretation of pool models’

Here, we concur with Azizi-Rad et al. (2021) that it is vital to critically evaluate and compare different soil carbon models, and we welcome the opportunity to further describe the unique contribution of the PROMISE model (Waring et al., 2020) to this literature. The PROMISE framework does share many features with established biogeochemical models, as our original manuscript highlighted in Table 1, and our work builds upon model innovations developed by many different groups, including that of Azizi-Rad and colleagues. Yet, the PROMISE framework is distinctive due to where it places mechanistic emphasis, and how these mechanisms are formalized in the mathematical model structure.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Learning to Branch with Interpretable Machine Learning Models

This presentation describes an algorithm for applying machine learning to branching to speed up the solution of integer optimization problems. These problems are challenging and solved multiple times a day by power systems operators. We show that our approach speeds up a widely used open-source optimization solver.

Bayramoglu, Selin↗
DOE OSTI2021

Mapping Stellar Surfaces. II. An Interpretable Gaussian Process Model for Light Curves

The use of Gaussian processes (GPs) as models for astronomical time series data sets has recently become almost ubiquitous, given their ease of use and flexibility. In particular, GPs excel at marginalization over the stellar signal when the variability due to starspots is treated as a nuisance, as in exoplanet transit modeling. However, these effective models are less useful in cases where the starspot signal is of primary interest, since it is not obvious how the parameters of the GP relate to physical parameters like the spot size, contrast, and latitudinal distribution. Instead, it is common practice to explicitly model the effect of individual starspots on the light curve and attempt to infer their properties via optimization or posterior inference. Unfortunately, this process is ill-posed and often computationally intractable when applied to stars with more than a few spots and/or to ensembles of many stars. Here we derive a closed-form expression for a GP that describes the light curve of a rotating, evolving stellar surface conditioned on a given distribution of starspot sizes, contrasts, and latitudes. We demonstrate that this model is correctly calibrated, allowing one to robustly infer physical parameters of interest from one or more light curves, including the typical spot radii and latitudes. Our GP has far-ranging implications for understanding the variability and magnetic activity of stars from light curves and radial velocity measurements, as well as for modeling correlated noise in exoplanet searches. Our implementation is efficient, user-friendly, and open-source, available in the package starry-process.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS1974

The contamination of lunar highland rocks by KREEP - Interpretation by mixing models

A mixing model method was used to determine the component abundance in the Apollo 16 and 17 soils. This method uses the chemical composition of the soils for up to 30 elements and a weighted least-squares mixing model technique. Elements included in the calculations are: Si, Ti, Al, Ca, Fe, Mg, P, Cr, Mn, Na, K, Rb, Ba, U, Th, La, Ce, Sm, Eu, Sr, Yb, Y, Sc, V, Zr, Nb, Co, Ni, Li, Au, and Ir. The method was used to examine the possibility that some of the highland rocks such as VHA and low-K Fra Mauro basalt are mixtures. The results of the mixing model calculations show that it is possible that these rocks are mixtures of KREEP, troctolite, 'anorthosites', and a meteoritic component. The Rb-Sr systematics are consistent with such a model for the genesis of the highland rocks. KREEP has high relative concentrations of Rb, U, and radiogenic Sr and Pb and its model age of about 4.4 AE dominates the model age of all the 'contaminated' highland rocks.

Schonfeld, E.↗
NASA NTRS1979

Photopolarimetry of scattering surfaces and their interpretation by computer model

Wolff's computer model of a rough planetary surface was simplified and revised. Close adherence to the actual geometry of a pitted surface and the inclusion of a function for diffuse light resulted in a quantitative model comparable to observations by planetary satellites and asteroids. A function is also derived to describe diffuse light emitted from a particulate surface. The function is in terms of the indices of refraction of the surface material, particle size, and viewing angles. Computer-generated plots describe the observable and theoretical light components for the Moon, Mercury, Mars and a spectrum of asteroids. Other plots describe the effects of changing surface material properties. Mathematical results are generated to relate the parameters of the negative polarization branch to the properties of surface pitting. An explanation is offered for the polarization of the rings of Saturn, and the average diameter of ring objects is found to be 30 to 40 centimeters.

Wolff, M.↗
NASA NTRS1980

Earth radiation budget measurements from satellites and their interpretation for climate modeling and studies

The annual and seasonal averaged Earth atmosphere radiation budgets derived from the most complete set of satellite observations available are presented. The budgets were derived from a composite of 48 monthly mean radiation budget maps. Annually and seasonally averaged radiation budgets are presented as global averages and zonal averages. The geographic distribution of the various radiation budget quantities is described. The annual cycle of the radiation budget was analyzed and the annual variability of net flux was shown to be largely dominated by the regular semi and annual cycles forced by external Earth-Sun geometry variations. Radiative transfer calculations were compared to the observed budget quantities and surface budgets were additionally computed with particular emphasis on discrepancies that exist between the present computations and previous surface budget estimates.

Vonderhaar, T. H.↗