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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

A primer on artificial intelligence in plant digital phenomics: embarking on the data to insights journey

Artificial intelligence (AI) has emerged as a fundamental component of global agricultural research that is poised to impact on many aspects of plant science. In digital phenomics, AI is capable of learning intricate structure and patterns in large datasets. We provide a perspective and primer on AI applications to phenome research. We propose a novel human-centric explainable AI (X-AI) system architecture consisting of data architecture, technology infrastructure, and AI architecture design. We clarify the difference between post hoc models and 'interpretable by design' models. We include guidance for effectively using an interpretable by design model in phenomic analysis. We also provide directions to sources of tools and resources for making data analytics increasingly accessible. In conclusion, this primer is accompanied by an interactive online tutorial.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2001

Risk analysis: divergent models and convergent interpretations

Material presented at a NASA-sponsored workshop on risk models for exposure conditions relevant to prolonged space flight are described in this paper. Analyses used mortality data from experiments conducted at Argonne National Laboratory on the long-term effects of external whole-body irradiation on B6CF1 mice by 60Co gamma rays and fission neutrons delivered as a single exposure or protracted over either 24 or 60 once-weekly exposures. The maximum dose considered was restricted to 1 Gy for neutrons and 10 Gy for gamma rays. Proportional hazard models were used to investigate the shape of the dose response at these lower doses for deaths caused by solid-tissue tumors and tumors of either connective or epithelial tissue origin. For protracted exposures, a significant mortality effect was detected at a neutron dose of 14 cGy and a gamma-ray dose of 3 Gy. For single exposures, radiation-induced mortality for neutrons also occurred within the range of 10-20 cGy, but dropped to 86 cGy for gamma rays. Plots of risk relative to control estimated for each observed dose gave a visual impression of nonlinearity for both neutrons and gamma rays. At least for solid-tissue tumors, male and female mortality was nearly identical for gamma-ray exposures, but mortality risks for females were higher than for males for neutron exposures. As expected, protracting the gamma-ray dose reduced mortality risks. Although curvature consistent with that observed visually could be detected by a model parameterized to detect curvature, a relative risk term containing only a simple term for total dose was usually sufficient to describe the dose response. Although detectable mortality for the three pathology end points considered typically occurred at the same level of dose, the highest risks were almost always associated with deaths caused by tumors of epithelial tissue origin.

Non-NASA Center↗
NASA NTRS1994

Model for the Interpretation of Hyperspectral Remote-Sensing Reflectance

Remote-sensing reflectance is easier to interpret for the open ocean than for coastal regions because the optical signals are highly coupled to the phytoplankton (e.g., chlorophyll) concentrations. For estuarine or coastal waters, variable terrigenous colored dissolved organic matter (CDOM), suspended sediments, and bottom reflectance, all factors that do not covary with the pigment concentration, confound data interpretation. In this research, remote-sensing reflectance models are suggested for coastal waters, to which contributions that are due to bottom reflectance, CDOM fluorescence, and water Raman scattering are included. Through the use of two parameters to model the combination of the backscattering coefficient and the Q factor, excellent agreement was achieved between the measured and modeled remote-sensing reflectance for waters from the West Florida Shelf to the Mississippi River plume. These waters cover a range of chlorophyll of 0.2-40 mg/cu m and gelbstoff absorption at 440 nm from 0.02-0.4/m. Data with a spectral resolution of 10 nm or better, which is consistent with that provided by the airborne visible and infrared imaging spectrometer (AVIRIS) and spacecraft spectrometers, were used in the model evaluation.

Lee, Zhongping↗
DOE OSTI2025

Explaining drivers of housing prices with nonlinear hedonic regressions

Housing markets play a critical role in shaping the spatial and demographic evolution of urban areas. Simulating housing price dynamics can enhance projections of future urban development outcomes. However, traditional hedonic regressions for housing prices, which neglect nonlinear interactions among explanatory variables, often exhibit limited predictive performance. While machine learning (ML) methods can provide a more flexible representation of the relationships between predictors, they are often regarded as “black boxes” due to their complexity and lack of transparency. Interpretable ML techniques provide a promising route by combining the flexibility of ML methods with approaches to analyze the relationships between inputs and outputs. In this study, we employ interpretable ML to analyze the patterns driving the housing market in Baltimore, Maryland, USA. We train an Artificial Neural Network (ANN) to predict Baltimore housing prices based on structural characteristics (e.g., home size, number of stories) and locational attributes (e.g., distance to the city center). We then conduct sensitivity and Partial Dependence Plot (PDP) analyses to interpret the fitted ANN model. We find that the ML model achieves higher predictive accuracy and explains 16 % more of housing price variance than a traditional linear regression model. The interpretable ML model also reveals more nuanced and realistic nonlinear relationships between housing sales price and predictors as well as interactive effects underlying Baltimore home price dynamics. For instance, while the linear model indicates a steady housing price increase over time, our interpretable ML model detects a post-2008 decline, with smaller properties experiencing the sharpest drop.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1990

Exponential ground impedance models and their interpretation

The authors compare the results of Donato's exponentially varying ground model, Attenborough's exponentially varying ground model and the rigid backed thin layer model. They show that these models produce similar results for slow variations. For rapid variations the results are quite different, but the basic theory used is only correct for the thin layer model. These results suggest that the exponentially varying models are not necessary for fitting ground impedance data.

Raspet, Richard↗
DOE OSTI2023

Learning to Branch with Interpretable Machine Learning Models

Machine learning is being increasingly used in improving decisions made within branch-and-bound algorithms for solving mixed-integer programs (MIPs). Branching is a key component in branch-and-bound algorithms, this work presents IDAES-core project update on building simple and interpretable machine learning models for branching and improving decision-making tools applied for the optimization of advanced energy systems.

Bayramoglu, Selin↗
NASA NTRS1977

The embedded feature model for the interpretation of chromospheric contrast profiles

Contrast profiles obtained from chromospheric filtergrams and spectra of bright and dark mottles have to date been interpreted almost exclusively in terms of Becker's cloud model. Here we demonstrate the failure of this model to account in a physically consistent way for the observed contrasts. As an alternative, we introduce an embedded-feature model, restricting our discussion in this paper to stationary features. Our model is then characterized by three independent parameters: the density of absorbing atoms, the geometrical depth, and the profile of the absorption coefficient. An analytic approximation to the contrast resulting from such a model reproduces well the observed behavior of all types of contrast profiles.

Steinitz, R.↗
DOE OSTI2024

Interpretable Machine Learning Models for Practical Antimonate Electrocatalyst Performance

Computationally predicting the performance of catalysts under reaction conditions is a challenging task due to the complexity of catalytic surfaces and their evolution in situ, different reaction paths, and the presence of solid-liquid interfaces in the case of electrochemistry. We demonstrate here how relatively simple machine learning models can be found that enable prediction of experimentally observed onset potentials. Inputs to our model are comprised of data from the oxygen reduction reaction on non-precious transition-metal antimony oxide nanoparticulate catalysts with a combination of experimental conditions and computationally affordable bulk atomic and electronic structural descriptors from density functional theory simulations. From human-interpretable genetic programming models, we identify key experimental descriptors and key supplemental bulk electronic and atomic structural descriptors that govern trends in onset potentials for these oxides and deduce how these descriptors should be tuned to increase onset potentials. Here, we finally validate these machine learning predictions by experimentally confirming that scandium as a dopant in nickel antimony oxide leads to a desired onset potential increase. Macroscopic experimental factors are found to be crucially important descriptors to be considered for models of catalytic performance, highlighting the important role machine learning can play here even in the presence of small datasets.

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

Interpretable machine learning models classify minerals via spectroscopy

Developing methods to identify mineral species confidently and rapidly from Raman spectral analysis is critical to numerous fields. Traditionally, analysis relies on pattern matching the Raman spectrum of an unknown dataset with a supporting library of well-characterized spectral data, which may prove difficult for environmental samples that are poorly crystalline or phase mixtures. Here, we developed interpretable machine learning models that can classify uranium minerals by secondary oxyanion chemistry and other physicochemical properties based solely on Raman spectra. This new ML method produces a mineral profile of physical and chemical properties for an unknown sample and can rapidly classify or identify unknown minerals from Raman data, without the need for an exact pattern match in a spectral library. Training models are validated by 1. Strong correlation of high confidence model regions with published spectroscopic assignments and 2. Correct classification of a mineral not present in training data. Training data are from the Compendium of Uranium Raman and Infrared Experimental Spectra and available crystallographic information files within the open-source Smart Spectral Matching scientific framework. Physically meaningful classifier models can rapidly identify key structural and chemical information about unknown uranium minerals and the overall methodology is broadly applicable for mineral phases.

Machine learning↗
NASA NTRS1994

The calculation of theoretical chromospheric models and the interpretation of the solar spectrum

Since the early 1970s we have been developing the extensive computer programs needed to construct models of the solar atmosphere and to calculate detailed spectra for use in the interpretation of solar observations. This research involves two major related efforts: work by Avrett and Loeser on the Pandora computer program for non-LTE modeling of the solar atmosphere including a wide range of physical processes, and work by Kurucz on the detailed synthesis of the solar spectrum based on opacity data for over 58 million atomic and molecular lines. Our goals are to determine models of the various features observed on the sun (sunspots, different components of quiet and active regions, and flares) by means of physically realistic models, and to calculate detailed spectra at all wavelengths that match observations of those features. These two goals are interrelated: discrepancies between calculated and observed spectra are used to determine improvements in the structure of the models, and in the detailed physical processes used in both the model calculations and the spectrum calculations. The atmospheric models obtained in this way provide not only the depth variation of various atmospheric parameters, but also a description of the internal physical processes that are responsible for nonradiative heating, and for solar activity in general.

Avrett, Eugene H.↗
NASA NTRS1998

The Calculation of Theoretical Chromospheric Models and the Interpretation of the Solar Spectrum

Since the early 1970s we have been developing the extensive computer programs needed to construct models of the solar atmosphere and to calculate detailed spectra for use in the interpretation of solar observations. This research involves two major related efforts: work by Avrett and Loeser on the Pandora computer program for non-LTE modeling of the solar atmosphere including a wide range of physical processes, and work by Rurucz on the detailed synthesis of the solar spectrum based on opacity data or over 58 million atomic and molecular lines. our goals are: to determine models of the various features observed on the Sun (sunspots, different components of quiet and active regions, and flares) by means of physically realistic models, and to calculate detailed spectra at all wavelengths that match observations of those features. These two goals are interrelated: discrepancies between calculated and observed spectra are used to determine improvements in the structure of the models, and in the detailed physical processes used in both the model calculations and the spectrum calculations. The atmospheric models obtained in this way provide not only the depth variation of various atmospheric parameters, but also a description of the internal physical processes that are responsible for non-radiative heating, and for solar activity in general.

Avrett, Eugene H.↗
NASA NTRS1986

The calculation of theoretical chromospheric models and the interpretation of solar spectra from rockets and spacecraft

Calculated results based on two chromospheric flare models F1 and F2 of Machado, et al., (1980) are presented. Two additional models are included: F1*, which has enhanced temperatures relative to the weak-flare model F1 in the upper photosphere and low chromosphere, and F3 which has enhanced temperatures relative to the strong flare model F2 in the upper chromosphere. Each model is specified by means of a given variation of the temperature as a function of column mass. The corresponding variation of particle density and the geometrical height scale are determined by assuming hydrostatic equilibrium. The coupled equations of statistical equilibrium is solved as is radiative transfer for H, H-, He I-II, C I-IV, Si I-II, Mg I-II, Fe, Al, O I-II, Na, and Ca II. The overall absorption and emission of radiation by lines throughout the spectrum is determined by means of a reduced set of opacities sampled from a compilation of over 10 to the 7th power individual lines. That the white flight flare continuum may arise by extreme chromospheric overheating as well as by an enhancement of the minimum temperature region is also shown. The radiative cooling rate calculations for our brightest flare model suggest that chromospheric overheating provides enhanced radiation that could cause significant heating deep in the flare atmosphere.

Avrett, E. H.↗
NASA NTRS1993

The calculation of theoretical chromospheric models and the interpretation of solar spectra from rockets and spacecraft

Since the early 1970s we have been developing the extensive computer programs needed to construct models of the solar atmosphere and to calculate detailed spectra for use in the interpretation of solar observations. This research involves two major related efforts: work by Avrett and Loeser on the Pandora computer program for non-LTE modeling of the solar atmosphere including a wide range of physical processes, and work by Kurucz on the detailed synthesis of the solar spectrum based on opacity data for over 58 million atomic and molecular lines. Our goals are to determine models of the various features observed on the Sun (sunspots, different components of quiet and active regions, and flares) by means of physically realistic models, and to calculate detailed spectra at all wavelengths that match observations of those features. These two goals are interrelated: discrepancies between calculated and observed spectra are used to determine improvements in the structure of the models, and in the detailed physical processes used in both the model calculations and the spectrum calculations. The atmospheric models obtained in this way provide not only the depth variation of various atmospheric parameters, but also a description of the internal physical processes that are responsible for non-radiative heating, and for solar activity in general.

Avrett, Eugene H.↗
DOE OSTI2021

Methodology for interpretable reinforcement learning model for HVAC energy control

Deep reinforcement learning (DRL) approaches have been used in various application areas to improve efficiency, optimization, or automation. However, very little is known about how the DRL algorithms make decisions and what features affect their performance. Using a case study of a DRL based Heating, Ventilation and Air Conditioning (HVAC) optimization methodology, we demonstrate how we can address these challenges by applying interpretability tools and systematically exploring the model inputs for better understanding the DRL behaviour and decision making process. We developed a methodology for interpretable reinforcement learning and evaluated our approach in real-world house located in Knoxville, TN. Our findings explain the reasoning behind DRL-based optimization decisions under different circumstances which has been discussed and confirmed by the experts in the field.

Kotevska, Olivera↗
DOE OSTI2025

TRANSP integrated modeling code for interpretive and predictive analysis of tokamak plasmas

This paper provides a comprehensive review of the TRANSP code, a sophisticated tool for interpretive and predictive analysis of tokamak plasmas, detailing its major capabilities and features. It describes the equations for particle, power, and momentum balance analysis, as well as the poloidal field diffusion equations. The paper outlines the spatial and time grids used in TRANSP and details the equilibrium assumptions and solvers. Various models for heating and current drive and radiation, including updates to the NUBEAM model, are discussed. The handling of large-scale events such as sawtooth crashes and pellet injections is examined, along with the predictive capabilities for advancing plasma profiles. The integration of TRANSP with the ITER Integrated Modeling and Analysis Suite (IMAS) is highlighted, demonstrating enhanced data access and analysis capabilities. Additionally, the paper discusses best practices and continuous integration techniques to enhance TRANSP's robustness. The suite of TRANSP tools, designed for efficient data analysis and simulation, further supports the optimization of tokamak operations and coupling with other tokamak codes. Continuous development and support ensure that TRANSP remains a major code for the analysis of experimental data for controlled thermonuclear fusion, maintaining its critical role in supporting the optimization of tokamak operations and advancing fusion research.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS2012

A Discussion on Uncertainty Representation and Interpretation in Model-Based Prognostics Algorithms based on Kalman Filter Estimation Applied to Prognostics of Electronics Components

This article discusses several aspects of uncertainty representation and management for model-based prognostics methodologies based on our experience with Kalman Filters when applied to prognostics for electronics components. In particular, it explores the implications of modeling remaining useful life prediction as a stochastic process and how it relates to uncertainty representation, management, and the role of prognostics in decision-making. A distinction between the interpretations of estimated remaining useful life probability density function and the true remaining useful life probability density function is explained and a cautionary argument is provided against mixing interpretations for the two while considering prognostics in making critical decisions.

Celaya, Jose R.↗
NASA NTRS2012

Uncertainty Representation and Interpretation in Model-Based Prognostics Algorithms Based on Kalman Filter Estimation

This article discusses several aspects of uncertainty representation and management for model-based prognostics methodologies based on our experience with Kalman Filters when applied to prognostics for electronics components. In particular, it explores the implications of modeling remaining useful life prediction as a stochastic process, and how it relates to uncertainty representation, management and the role of prognostics in decision-making. A distinction between the interpretations of estimated remaining useful life probability density function is explained and a cautionary argument is provided against mixing interpretations for two while considering prognostics in making critical decisions.

Galvan, Jose Ramon↗