Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “model interpretability”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Joint Modeling of Quasar Variability and Accretion Disk Reprocessing Using Latent Stochastic Differential Equations

Quasars are bright active galactic nuclei powered by the accretion of matter around supermassive black holes at the center of galaxies. Their stochastic brightness variability depends on the physical properties of the accretion disk and black hole. The upcoming Rubin Observatory Legacy Survey of Space and Time (LSST) is expected to observe tens of millions of quasars, so there is a need for efficient techniques like machine learning that can handle the large volume of data. Quasar variability is believed to be driven by an X-ray corona, which is reprocessed by the accretion disk and emitted as UV/optical variability. We are the first to introduce an auto-differentiable simulation of the accretion disk and reprocessing. We use the simulation as a direct component of our neural network to jointly model the driving variability and reprocessing, trained with supervised learning on simulated LSST-like 10 yr quasar light curves. We encode the light curves using a transformer encoder, and the driving variability is reconstructed using latent stochastic differential equations, a physically motivated generative deep learning method that can model continuous-time stochastic dynamics. By embedding the physical processes of the driving signal and reprocessing into our network, we achieve a model that is more robust and interpretable. We demonstrate that our model outperforms a Gaussian process regression baseline and can infer accretion disk parameters and time delays between wave bands, even for out-of-distribution driving signals. Our approach provides a powerful framework that can be adapted to solve other inverse problems in multivariate time series.

Fagin, Joshua [City Univ. of New York (CUNY), NY (↗
DOE OSTI2024

From minimum-viable-products to full models: a step-wise development of diagnostic forward models in support of design, analysis and modelling on the ST40 tokamak

Like most magnetic confined fusion experiments, the ST40 tokamak started off with a small subset of diagnostics and gradually increased the diagnostic set to include more complex and comprehensive systems. To make the most of each operational phase, forward models of various diagnostics are used and developed to aid design, provide consistency-checks during commissioning, test analysis methods, and build workflows to constrain high-level parameters to inform interpretation, theory and modelling. For new models and new analysis workflows, minimum-viable-products are released early, and their complexity is increased in a step-wise manner, facilitating the support of all programme phases on multiple parallel applications, while enabling learning opportunities and feedback loops. In this contribution we review the philosophy, scope and architecture of the framework under development. We discuss the details of some forward models, with examples on how they are used to aid diagnostic design, to investigate analysis methodologies through synthetic data, and how they are embedded in experimental analysis workflows. We compare previously published experimental results with new, more advanced analysis workflows employing more recent, detailed models and new diagnostic data, providing confirmation of the published material from the 2021–22 experimental campaign.

integrated data analysis↗
DOE OSTI2026

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

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

LSTM modeling↗
DOE OSTI2024

Beginner's Guide to Understanding Power System Model Results for Long-Term Resource Plans

This presentation summarizes a recently published beginner's guide for understanding power system model results for long-term resource plans. This guide is designed to improve decision-making in the electricity planning process by strengthening dialogue between system planners and relevant stakeholders. It focuses on interpreting scenario results generated by power system planning models. These results are often used to inform integrated resource plans, which are long-term plans for a utility to meet future electricity requirements. Whether you are a state utility commissioner, commission staff, part of a state energy office, an intervenor in the planning process, or another stakeholder, this guide is designed to help you better weigh in on the modeling methods or interpret the model results to improve decision-making. This guide can enhance your understanding to ask the right questions, which can enable better understanding of results and key assumptions, data, and methods.

ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2023

Deep learning integrates histopathology and proteogenomics at a pan-cancer level

We introduce a pioneering approach that integrates pathology imaging with transcriptomics and proteomics to identify predictive histology features associated with critical clinical outcomes in cancer. We utilize 2,755 H&E-stained histopathological slides from 657 patients across 6 cancer types from CPTAC. Our models effectively recapitulate distinctions readily made by human pathologists: tumor vs. normal (AUROC = 0.995) and tissue-of-origin (AUROC = 0.979). We further investigate predictive power on tasks not normally performed from H&E alone, including TP53 prediction and pathologic stage. Importantly, we describe predictive morphologies not previously utilized in a clinical setting. The incorporation of transcriptomics and proteomics identifies pathway-level signatures and cellular processes driving predictive histology features. Model generalizability and interpretability is confirmed using TCGA. We propose a classification system for these tasks, and suggest potential clinical applications for this integrated human and machine learning approach. A publicly available web-based platform implements these models.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Effects of random forest modeling decisions on biogeochemical time series predictions

Abstract Random forests (RF) are an increasingly popular machine learning approach used to model biogeochemical processes in the Earth system. While RF models are robust to many assumptions that complicate deterministic models, there are several important parameterization decisions for appropriate use and optimal model fit. We explored the role that parameter decisions, including training/testing data splitting strategies, variable selection, and hyperparameters play on RF goodness‐of‐fit by constructing models using 1296 unique parameter combinations to predict concentrations of nitrate, a key nutrient for biogeochemical cycling in aquatic ecosystems. Models were built on long‐term, publicly available water quality and meteorology time series collected by the National Estuarine Research Reserve monitoring network for two contrasting ecosystems representing freshwater and brackish estuaries. We found that accounting for temporal dependence when splitting data into training and testing subsets was key for avoiding over‐estimation of model predictive power. In addition, variable selection, the ratio of training to testing data, and to a lesser degree, variables per split and number of trees, were significant parameters for optimizing RF goodness‐of‐fit. We also explored how model parameter decisions influenced interpretation of the relative importance of predictors to the model, and model predictor‐dependent variable relationships, with results suggesting that both data structure and model parameterization influence these factors. Because much of the current RF literature is written for the computational and statistical science communities, the primary goal of this study is to provide guidelines for aquatic scientists new to machine learning to apply RF techniques appropriately to aquatic biogeochemical datasets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Veridical data science

Building and expanding on principles of statistics, machine learning, and scientific inquiry, we propose the predictability, computability, and stability (PCS) framework for veridical data science. Our framework, composed of both a workflow and documentation, aims to provide responsible, reliable, reproducible, and transparent results across the data science life cycle. The PCS workflow uses predictability as a reality check and considers the importance of computation in data collection/storage and algorithm design. It augments predictability and computability with an overarching stability principle. Stability expands on statistical uncertainty considerations to assess how human judgment calls impact data results through data and model/algorithm perturbations. As part of the PCS workflow, we develop PCS inference procedures, namely PCS perturbation intervals and PCS hypothesis testing, to investigate the stability of data results relative to problem formulation, data cleaning, modeling decisions, and interpretations. We illustrate PCS inference through neuroscience and genomics projects of our own and others. Moreover, we demonstrate its favorable performance over existing methods in terms of receiver operating characteristic (ROC) curves in high-dimensional, sparse linear model simulations, including a wide range of misspecified models. Finally, we propose PCS documentation based on R Markdown or Jupyter Notebook, with publicly available, reproducible codes and narratives to back up human choices made throughout an analysis. The PCS workflow and documentation are demonstrated in a genomics case study available on Zenodo.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Quantitative interpretation of time-lapse seismic data at Farnsworth field unit: Rock physics modeling, and calibration of simulated time-lapse velocity responses

Here, this study investigates the contribution of fluid saturation variation to the time-lapse velocity response by performing fluid substitution modeling. The methodology is exemplified by the time-lapse seismic monitoring of carbon dioxide at Farnsworth field unit (FWU). In order to evaluate the fluid distribution in a matured oil reservoir, the Southwest Regional Partnership (SWP) acquired multiple vertical seismic profile (VSP) surveys at different times during the CO 2 –water alternatinggas (WAG) injection period. In this work, we present a thorough methodology for computing the elastic response of the saturated rock for different fluid saturations using a site-specific petro-elastic model (PEM). The output from the PEM was combined with results from a fluid compositional model to compute the seismic velocities at times corresponding to each VSP survey. To produce a calibrated simulated response, the measured time-lapse seismic velocities were integrated into the numerical simulation model. The mismatches between the predicted and measured time-lapse velocities were minimized through an iterative calibration process using a trained artificial neural network proxy (ANN) coupled with a particle swarm optimizer (PSO). Our study indicates that the hybrid optimization workflow can effectively perform the history matching. With an accurate prediction of the hydrodynamic properties, the migration of CO 2 within the subsurface was modeled by predicting the spatial velocity distribution for a radius of 305 m around the injection well. The technology demonstrated and the expertise gained from this study can guide similar CO 2 -WAG projects.

58 GEOSCIENCES↗
DOE OSTI2021

Fourier Neural Networks as Function Approximators and Differential Equation Solvers

We present a Fourier neural network (FNN) that can be mapped directly to the Fourier decomposition. The choice of activation and loss function yields results that replicate a Fourier series expansion closely while preserving a straightforward architecture with a single hidden layer. The simplicity of this network architecture facilitates the integration with any other higher-complexity networks, at a data pre- or postprocessing stage. We validate this FNN on naturally periodic smooth functions and on piecewise continuous periodic functions. We showcase the use of this FNN for modeling or solving partial differential equations with periodic boundary conditions. The main advantages of the current approach are the validity of the solution outside the training region, interpretability of the trained model, and simplicity of use.

Fourier decomposition↗
DOE OSTI2025

Development of a data-driven neural network model for electron thermal transport in NSTX

A data-driven electron thermal transport neural network (ETT-NN) model, trained on TRANSP interpretative analysis results of National Spherical Torus Experiment (NSTX), was developed to enable faster and more accurate ETT computation for spherical tokamaks (STs). The model incorporates both convolutional NNs and recurrent NNs, allowing it to simultaneously account for the spatial and temporal non-localities and multi-scale features of turbulent transport, which have been considered only in a limited manner in conventional models. The model was validated through interpretative analysis and predictive simulations using Tokamak Reactor Integrated Automated Suite for Simulation and Computation, demonstrating relatively high accuracy. Additionally, parameter scans were performed on test discharges known to exhibit specific turbulent modes, such as microtearing mode, trapped electron mode, kinetic ballooning mode, and electron temperature gradient mode. The scanning results revealed that the ETT-NN model exhibits the same trends as those observed in conventional gyrokinetic simulations or theories, while also capturing the global nature of turbulent transport, indicating that the data-driven model accurately reflects the underlying physical characteristics. Furthermore, due to the dimensionless nature of the model, we can feasibly expand its applicability by incorporating data from other devices and uncovering the characteristics of ETT in STs in the future.

NSTX↗
DOE OSTI2022

A reduced model for the ITER divertor based on SOLPS solutions for ITER Q = 10 baseline conditions: A. identifying options for the control parameters*

Edge codes such as SOLPS coupled to neutral codes such as EIRENE have become so comprehensive and sophisticated that they now constitute, in effect, 'code-experiments' that, as for actual experiments, can benefit from interpretation using simple models and conceptual frameworks, i.e. reduced models. The first task is the identification of options for the reduced model control parameters that are best suited for control of the action of the divertor, i.e. for control of target power loading and sputter-erosion, primarily. A strong correlation between the electron temperature at the divertor target, T e,t , and the neutral deuterium D 2 density at the target, n D2,t , flux-tube resolved, has recently been reported for a number of code studies including SOLPS-4.3 modeling of a set of ~50 ITER baseline cases: Q DT = 10, q 95 = 3, P SOL = 100 MW, metallic walls, and Ne seeding. This part A of the present study reports new results for largely the same ITER cases, confirming the strong correlations reported earlier between local values of T e,t , and (i) n D2,t , and (ii) normalized volumetric losses of power and pressure in the divertor. Strong correlations have now also been found, and are reported here for the first time, between T e,t and all of the divertor target quantities of practical interest. A physical explanation for this surprising result has not been fully identified; nevertheless it has encouraging implications for reduced modeling of the ITER divertor. For such ITER conditions, (i) the global Ne injection rate, Inj Ne [Ne/s], and (ii) the electron temperature at the location on the target where the peak power deposition occurs, T e,t @q ⊥,pk (eV), are found to be promising reduced model control parameters. In the companion report, part B, a reduced model for the ITER divertor is developed and described in detail, based on reversed-direction 2 point modelling, Rev2PM. The input to the reduced model is a value of the variable pair (T et @q ⟂,pk ,Inj Ne ) and the output are values of the various target as well as divertor-entrance quantities of practical interest, e.g. q ⊥,pk , n e,Xpt (the electron density at the poloidal location of the X-point), etc. In part B the reduced model is quantitatively characterized using one half of the code cases; it is then used to successfully predict (replicate) the code values of e.g. n e,Xpt for the other half of the cases.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

Evidence that the Hot Jupiter WASP-77 A b Formed Beyond Its Parent Protoplanetary Disk’s H2O Ice Line

Idealized protoplanetary disk and giant planet formation models have been interpreted to suggest that a giant planet's atmospheric abundances can be used to infer its formation location in its parent protoplanetary disk. It has recently been reported that the hot Jupiter WASP-77 A b has subsolar atmospheric carbon and oxygen abundances with a solar C/O abundance ratio. Assuming solar carbon and oxygen abundances for its host star WASP-77 A, WASP-77 A b's atmospheric carbon and oxygen abundances possibly indicate that it accreted its envelope interior to its parent protoplanetary disk's H 2 O ice line from carbon-depleted gas with little subsequent planetesimal accretion or core erosion. We show that the photospheric abundances of carbon and oxygen in WASP-77 A are supersolar with a subsolar C/O abundance ratio, implying that WASP-77 A b's atmosphere has significantly substellar carbon and oxygen abundances with a superstellar C/O ratio. Our result possibly indicates that WASP-77 A b's envelope was accreted by the planet beyond its parent protoplanetary disk's H 2 O ice line. While numerous theoretical complications to these idealized models have now been identified, the possibility of nonsolar protoplanetary disk abundance ratios confound even the most sophisticated protoplanetary disk and giant planet formation models. We therefore argue that giant planet atmospheric abundance ratios can only be meaningfully interpreted relative to the possibly nonsolar mean compositions of their parent protoplanetary disks as recorded in the photospheric abundances of their dwarf host stars.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

A Physically-Based Model for Thermo-Oxidative and Hydrolytic Aging of Elastomers

A computationally efficient model is proposed to capture the loss of mechanical performance due to chemical aging that are formed as the competition of chain scission and cross-link formation/dissolution, such as thermo-oxidative aging or hydrolytic aging. The model should be considered an extension of our recent models [1, 2, 3] which further simplifies the matrix behavior based on the assumption of independence of environmental and mechanical damage. The model uses this assumption to reduce the necessary material parameters needed to model constitutive and inelastic behavior of elastomers during aging. To this end, the model can provide accurate predictions of the material performance with the significantly fewer number of fitting parameters. The model is relevant for all decay mechanisms formed by the occurrence of two simultaneous micro-mechanisms; (i) formation/reduction of the cross-links, and (ii) chain scission, both of which are present in thermo-oxidation and hydrolytic aging. Assuming the alteration of the chain density along the aging trajectory is identical to the peroxide cross-link density for thermo-oxidation, and the change of the average molecular weight for hydrolysis, the strain energy of polymer matrix can be rewritten as a function of deformation, deformation history, storage time and aging temperature. Next, the modified network alteration model is formulated for implementation into Finite Element (FE) simulations. The model is built on the presumption of homogeneous and consistent oxygen/water absorption and thus is mainly relevant for relatively thin samples exposed to environmental loads for a long time. The proposed model includes only six physically inspired material parameters. Therefore, while it is computationally efficient, it shows good agreement with own experimental data, which performed on various range of accelerated aging temperatures and times. With respect to its computational efficiency, simplicity, accuracy, and interpret-ability, the model is the right choice for advanced implementations in FE programs.

42 ENGINEERING↗
DOE OSTI2021

A Modified Network Alteration Model to Predict Quasi-Static Behavior of the Cross-Linked Polymers During Hydrolytic Aging

Abstract The network alteration theory is utilized to capture the effects of hydrolytic aging on the mechanical integrity of the polymer matrix. Hydrolytic degradation generally considered as a result of two simultaneous chemical phenomena; (i) reduction of the cross-links, and (ii) active chain loss. Assuming the alteration of the chain density is identical to the change of the number average molecular weight along the aging trajectory, the strain energy of polymer matrix can be rewritten as a function of deformation, deformation history, storage time, and aging temperature. The proposed model includes only five physically inspired material parameters. Thus, while it is computationally efficient, it shows good agreement with own experimental data, which performed on various range of accelerated aging temperatures and times. With respect to its computational efficiency, simplicity, accuracy, and interpret-ability, the model is a good choice for advanced implementations in FE programs.

Bahrololoumi, Amir↗
DOE OSTI2021

Spontaneous CP violation and horizontal symmetry in the MSSM: toward lepton flavor naturalness

We study the contributions of supersymmetric models with a U(1) horizontal symmetry and only spontaneous CP breaking to various lepton flavor observables, such as μ → eγ and the electron electric dipole moment. We show that both a horizontal symmetry and a lack of explicit CP violation can alleviate the existing bounds from such observables. The undetermined \( \mathcal{O} \) (1) coefficients in such mass matrix models muddle the interpretation of the bounds from various flavor observables. To overcome this, we define a new fine-tuning measure for different observables in such setups. This allows us to study how naturally the observed IR flavor observables can emerge from a given mass matrix model. We use our flavor-naturalness measure in study of our supersymmetric models and quantify the degree of fine tuning required by the bounds from various lepton flavor observables at each mass scale of sleptons, neutralinos, and charginos.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Mechanism of Rad26-assisted rescue of stalled RNA polymerase II in transcription-coupled repair

Transcription-coupled repair is essential for the removal of DNA lesions from the transcribed genome. The pathway is initiated by CSB protein binding to stalled RNA polymerase II. Mutations impairing CSB function cause severe genetic disease. Yet, the ATP-dependent mechanism by which CSB powers RNA polymerase to bypass certain lesions while triggering excision of others is incompletely understood. Here we build structural models of RNA polymerase II bound to the yeast CSB ortholog Rad26 in nucleotide-free and bound states. This enables simulations and graph-theoretical analyses to define partitioning of this complex into dynamic communities and delineate how its structural elements function together to remodel DNA. We identify an allosteric pathway coupling motions of the Rad26 ATPase modules to changes in RNA polymerase and DNA to unveil a structural mechanism for CSB-assisted progression past less bulky lesions. Our models allow functional interpretation of the effects of Cockayne syndrome disease mutations.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Reprocessing Models for the Optical Light Curves of Hypervariable Quasars from the Sloan Digital Sky Survey Reverberation Mapping Project

We explore reprocessing models for a sample of 17 hypervariable quasars, taken from the Sloan Digital Sky Survey Reverberation Mapping project, which all show coordinated optical luminosity hypervariability with amplitudes of factors ≳2 between 2014 and 2020. We develop and apply reprocessing models for quasar light curves in simple geometries that are likely to be representative of quasar inner environments. In addition to the commonly investigated thin-disk model, we include the thick-disk and hemisphere geometries. The thick-disk geometry could, for instance, represent a magnetically elevated disk, whereas the hemisphere model can be interpreted as a first-order approximation for any optically thick out-of-plane material caused by outflows/winds, warped/tilted disks, and so on. Of the 17 quasars in our sample, 11 are best-fitted by a hemisphere geometry, five are classified as thick disks, and both models fail for just one object. We highlight the successes and shortcomings of our thermal reprocessing models in case studies of four quasars that are representative of the sample. While reprocessing is unlikely to explain all of the variability that we observe in quasars, we present our classification scheme as a starting point for revealing the likely geometries of reprocessing for quasars in our sample and hypervariable quasars in general.

79 ASTRONOMY AND ASTROPHYSICS↗