Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Validating compositional fluid flow simulations using 4D seismic interpretation and vice versa in the SECARB Early Test—A critical review

We report on strengths and weaknesses of 4D seismic interpretation as a technique for monitoring carbon dioxide that was injected as part of a large scale test associated with commercial enhanced oil recovery (EOR) at Cranfield Field, Mississippi, USA. The goals of the monitoring effort are 1) to make measurements to verify that the CO 2 is contained in the reservoir according to operational designs and model predictions, and 2) that if there are deviations, to provide data which can be used to update the earth models and determine if any mitigation is needed. Our work uses a compositional numerical simulation to model CO 2 flow in the reservoir and compares the results with estimates of changes in seismic properties between a pre-injection and a survey after more than 2 million metric tons injected. The complicated physics of the problem in Cranfield field present challenges to seismic interpretations. These findings reflect partial agreement between the results of the numerical simulation and the seismic interpretations. Possible causes of discrepancies among the fluid flow model and multiple interpretations of the same seismic data sets performed with different work flows illuminates the types of uncertainties that should be considered to achieve the goals of monitoring.

4D seismic↗
DOE OSTI2015

Interpretation of the photoelectron, ultraviolet, and vacuum ultraviolet photoabsorption spectra of bromobenzene by ab initio configuration interaction and DFT computations

New photoelectron, ultraviolet (UV), and vacuum UV (VUV) spectra have been obtained for bromobenzene by synchrotron study with higher sensitivity and resolution than previous work. This, together with use of ab initio calculations with both configuration interaction and time dependent density functional theoretical methods, has led to major advances in interpretation. The VUV spectrum has led to identification of a considerable number of Rydberg states for the first time. The Franck-Condon (FC) analyses including both hot and cold bands lead to identification of the vibrational structure of both ionic and electronically excited states including two Rydberg states. The UV onset has been interpreted in some detail, and an interpretation based on the superposition of FC and Herzberg-Teller contributions has been performed. In a similar way, the 6 eV absorption band which is poorly resolved is analysed in terms of the presence of two ππ* states of {sup 1}A{sub 1} (higher oscillator strength) and {sup 1}B{sub 2} (lower oscillator strength) symmetries, respectively. The detailed analysis of the vibrational structure of the 2{sup 2}B{sub 1} ionic state is particularly challenging, and the best interpretation is based on equation-of-motion-coupled cluster with singles and doubles computations. A number of equilibrium structures of the ionic and singlet excited states show that the molecular structure is less subject to variation than corresponding studies for iodobenzene. The equilibrium structures of the 3b{sub 1}3s and 6b{sub 2}3s (valence shell numbering) Rydberg states have been obtained and compared with the corresponding ionic limit structures.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Uncovering interpretable relationships in high-dimensional scientific data through function preserving projections

Abstract In many fields of science and engineering, we frequently encounter experiments or simulations datasets that describe the behavior of complex systems and uncovering human interpretable patterns between their inputs and outputs via exploratory data analysis is essential for building intuition and facilitating discovery. Often, we resort to 2D embeddings for examining these high-dimensional relationships (e.g. dimensionality reduction). However, most existing embedding methods treat the dimensions as coordinates for samples in a high-dimensional space, which fail to capture the potential functional relationships, and the few methods that do take function into consideration either only focus on linear patterns or produce non-linear embeddings that are hard to interpret. To address these challenges, we proposed function preserving projections (FPP), which construct 2D linear embeddings optimized to reveal interpretable yet potentially non-linear patterns between the domain and the range of a high-dimensional function. The intuition here is that humans are good at understanding potentially non-linear patterns in 2D but unable to interpret non-linear mapping from high-dimensional space to 2D. Therefore, we should restrict the projection to linear but not the pattern we are seeking. Using FPP on real-world datasets, one can obtain fundamentally new insights about high-dimensional relationships in extremely large datasets that could not be processed with existing dimension reduction methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Knowledge-guided learning with curated prior genetic biomarkers for robust model interpretation

Abstract Motivation Knowledge-guided learning offers effective and robust model training strategies in data-scarce settings by incorporating established domain knowledge, thereby enhancing generalization, robustness, and interpretability. By contrast, conventional deep learning approaches rely purely on data-driven learning, which can limit robust model interpretability, particularly in high-dimensional settings with limited size samples. In computational biology, knowledge-guided learning has primarily leveraged network- and structural-based knowledge, leading to biologically interpretable representations and enhanced predictive performance compared to conventional approaches. However, curated biomarkers, one of the most accessible forms of biological knowledge, remain largely unexplored within knowledge-guided paradigms. Results In this study, we propose a model-agnostic training paradigm, Biomarker-driven Explainable Prior-guided Learning (BioExPL), that can be applied to any neural networks that incorporates curated prior knowledge. BioExPL enforces neural networks to reflect curated biomarker priors in their latent representations through a novel knowledge-alignment loss. BioExPL consistently demonstrated significantly improved predictive performance and enhanced model interpretability with minimized computational overhead in simulation studies and intensive experiments on multiple cancer datasets. BioExPL not only integrates prior curated knowledge into the model but also accurately identifies unknown associated signals additionally. BioExPL is model-agnostic and domain-independent, enabling its integration into diverse neural network architectures. Availability and implementation The open-source is publicly available at: https://github.com/datax-lab/BioExPL.

Baek, Beomsu [Department of Computer Science, Univ↗
DOE OSTI2023

Interpretable boosted-decision-tree analysis for the Majorana Demonstrator

The Majorana Demonstrator is a leading experiment searching for neutrinoless double-beta decay with high purity germanium detectors (HPGe). Machine learning provides a new way to maximize the amount of information provided by these detectors, but the data-driven nature makes it less interpretable compared to traditional analysis. An interpretability study reveals the machine's decision-making logic, allowing us to learn from the machine to feedback to the traditional analysis. In this work, we have presented the first machine learning analysis of the data from the Majorana Demonstrator; this is also the first interpretable machine learning analysis of any germanium detector experiment. Two gradient boosted decision tree models are trained to learn from the data, and a game-theory-based model interpretability study is conducted to understand the origin of the classification power. By learning from data, this analysis recognizes the correlations among reconstruction parameters to further enhance the background rejection performance. By learning from the machine, this analysis reveals the importance of new background categories to reciprocally benefit the standard Majorana analysis. This model is highly compatible with next-generation germanium detector experiments like LEGEND since it can be simultaneously trained on a large number of detectors.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Symbolic diagnostics to interpret and analyze neural network models

Embedded machine-learned models (EMLMs) have the promise to improve the predictive accuracy of engineering simulators in environments of national interest. EMLMs often comprise complex input-output maps (e.g., neural networks), which make them unamenable to rigorous analysis and generally difficult to interpret. In the face of decades of theory, this lack of interpretability is a significant barrier to building confidence in these models. This work outlines an approach to interpret EMLMs using sparse polynomial regression for comparison with theoretical understanding. To do so, we build on the concept of Locally Interpretable Model-agnostic Explanations (LIME) using physics-informed clustering, prototype selection, and library construction. While general, we demonstrate our method on tensor-basis neural networks used in Reynolds-Averaged Navier-Stokes simulations of hypersonic fluid flows. Results are presented for a simulated toy model and for direct numerical simulations (DNS) of turbulent flows over a flat plate.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1976

Applied photo interpretation for airbrush cartography

New techniques of cartographic portrayal have been developed for the compilation of maps of lunar and planetary surfaces. Conventional photo interpretation methods utilizing size, shape, shadow, tone, pattern, and texture are applied to computer processed satellite television images. The variety of the image data allows the illustrator to interpret image details by inter-comparison and intra-comparison of photographs. Comparative judgements are affected by illumination, resolution, variations in surface coloration, and transmission or processing artifacts. The validity of the interpretation process is tested by making a representational drawing by an airbrush portrayal technique. Production controls insure the consistency of a map series. Photo interpretive cartographic portrayal skills are used to prepare two kinds of map series and are adaptable to map products of different kinds and purposes.

Inge, J. L.↗
NASA NTRS1976

Interpretation key for SAR /L-band/ imagery of sea ice

An interpretation key, similar to those previously developed for use with aerial photography and other remotely sensed data, was developed for L-band (25 cm) radar imagery collected over the Arctic Ocean. Data from April, August, and October were considered. The procedure for developing a valid interpretation key for operation use involves substituting time for space. Open water situations (polynyas, leads, flaws), examples of unconsolidated ice (frazil, slush, brash), thin ice (nilas), and annual ice (first year, multi-year ice) situations are examined. It is suggested that the interpretation key will enhance the use of side looking airborne radar data in the qualitative photo interpretation mode.

Bryan, M. L.↗
NASA NTRS1981

Ground photography for improvved image interpretation training

Systematic sets of ground based color and color infrared photography were presented to students in remote sensing classes to enhance their ability to interpret satellite images. Features readily apparent on computer enhanced LANDSAT images were presented simultaneously with ground based photography in the format of slide triplicates. It was hypothesized that this instructional approach would improve the students' abilities to recognize, understand and interpret ground phenomena present on remotely sensed imagery. Tests conducted in undergraduate remote sensing classes substantially upheld this hypothesis. Student image interpretive abilities were tested before and after being exposed to the ground level photography. In general, image interpretive skills of the class improved by 25%. Also, the performance of students having different academic majors varied greatly for differing types of image subjects.

Lougeay, R.↗
NASA NTRS1987

A review of computer aided interpretation technology for the evaluation of radiographs of aluminum welds

Industrial radiography is a well established, reliable means of providing nondestructive structural integrity information. The majority of industrial radiographs are interpreted by trained human eyes using transmitted light and various visual aids. Hundreds of miles of radiographic information are evaluated, documented and archived annually. In many instances, there are serious considerations in terms of interpreter fatigue, subjectivity and limited archival space. Quite often it is difficult to quickly retrieve radiographic information for further analysis or investigation. Methods of improving the quality and efficiency of the radiographic process are being explored, developed and incorporated whenever feasible. High resolution cameras, digital image processing, and mass digital data storage offer interesting possibilities for improving the industrial radiographic process. A review is presented of computer aided radiographic interpretation technology in terms of how it could be used to enhance the radiographic interpretation process in evaluating radiographs of aluminum welds.

Lloyd, J. F., Sr.↗
NASA NTRS1989

Image understanding and interpretation in microwave diversity imaging

The authors investigate microwave imaging of metallic objects using a diversity method and interpret and predict the reconstructed image from an approach based on analysis of the scattering mechanism and a back-projection algorithm used in image retrieval. The connection between the various scattering mechanisms and the reconstructed images is discussed, what the images represent is interpreted, and a prediction is made as to what the image will look like over given spectral and angular windows. A brief description is given of the microwave diversity imaging system and the formulation of the microwave diversity imaging based on the physical optics approximation. The scattering mechanism of a complex shaped metallic object is then briefly reviewed and an alternate approach to interpreting the reconstructed image based on the understanding of the scattering mechanism and the reconstruction algorithm is given. Several numerical and experimental examples are included to support this interpretation approach.

Li, Hsueh-Jyh↗
NASA NTRS1994

Synoptic interpretation of measurements from HALOE

The degree to which the Southern Hemisphere polar vortex is isolated against horizontal (isentropic) mixing is investigated using data from the Halogen Occultation Experiment (HALOE), U.K. Meteorological Office (UKMO) potential vorticity (PV), and contour advection diagnostics. Measurements of methane and water vapor taken by HALOE during a disturbed period in the Southern Hemisphere springtime (21 September - 15 October 1992) are interpreted in light of the prevailing synoptic meteorology. Daily fields of winds and PV are shown to be essential in the interpretation of the data. A climatological high pressure region is responsible for a distorted vortex, and a substantial 'vortex stripping' event is present, associated with the early stages of vortex breakdown. This leads to significant temporal, zonal, and altitudinal variations in the distribution of tracers. The authors point out the difficulties this presents for the interpretation of solar occultation data, especially with regard to the use of zonal average time series. Longitude-height methane distributions from two days during the period are examined. Both days show substantial variations in abundance around a latitude circle. In particular, the authors investigate HALOE measurements at 77 deg S on 15 October 1992, which indicate an abundance of methane in the height region 600-2000 K (approximately 30-1 mb) that is more typical of midlatitude air. Similar distributions, observed in the 1991 HALOE data, have previously been interpreted as evidence for the penetration of midlatitude air into the vortex. Gradients of potential vorticity and contour advection diagnositcs are employed to examine whether the UKMO winds are consistent with this hypothesis in 1992. Although midlatitude air is able to penetrate poleward of the main jet core by advection processes alone, an essentially intact inner core of vortex air remains, which does not mix to any great extent with air from lower latitudes. The authors show that the high-latitude HALOE abundances that are typical of midlatitude air were observed in a region of extensive filamentation and mixing, rather than within the inner, more isolated, core.

Bithell, M.↗
NASA NTRS1991

On the Power of Abstract Interpretation

Increasingly sophisticated applications of static analysis place increased burden on the reliability of the analysis techniques. Often, the failure of the analysis technique to detect some information my mean that the time or space complexity of the generated code would be altered. Thus, it is important to precisely characterize the power of static analysis techniques. We follow the approach of Selur et. al. who studied the power of strictness analysis techniques. Their result can be summarized by saying 'strictness analysis is perfect up to variations in constants.' In other words, strictness analysis is as good as it could be, short of actually distinguishing between concrete values. We use this approach to characterize a broad class of analysis techniques based on abstract interpretation including, but not limited to, strictness analysis. For the first-order case, we consider abstract interpretations where the abstract domain for data values is totally ordered. This condition is satisfied by Mycroft's strictness analysis that of Sekar et. al. and Wadler's analysis of list-strictness. For such abstract interpretations, we show that the analysis is complete in the sense that, short of actually distinguishing between concrete values with the same abstraction, it gives the best possible information. We further generalize these results to typed lambda calculus with pairs and higher-order functions. Note that products and function spaces over totally ordered domains are not totally ordered. In fact, the notion of completeness used in the first-order case fails if product domains or function spaces are added. We formulate a weaker notion of completeness based on observability of values. Two values (including pairs and functions) are considered indistinguishable if their observable components are indistinguishable. We show that abstract interpretation of typed lambda calculus programs is complete up to this notion of indistinguishability. We use denotationally-oriented arguments instead of the detailed operational arguments used by Selur et. al.. Hence, our proofs are much simpler. They should be useful for further future improvements.

Reddy, Uday S.↗
NASA NTRS2004

Understanding AOP through the Study of Interpreters

I return to the question of what distinguishes AOP languages by considering how the interpreters of AOP languages differ from conventional interpreters. Key elements for static transformation are seen to be redefinition of the set and lookup operators in the interpretation of the language. This analysis also yields a definition of crosscutting in terms of interlacing of interpreter actions.

Filman, Robert E.↗
NASA NTRSDate not supplied

Interpretable Convolutional Learning Classifier System (C-LCS) for Higher Dimensional Datasets

The purpose of this paper is to devise an interpretable hybrid classification model for Convolutional Neural Networks (CNN) and a Learning Classifier System (LCS). The presented hybrid system integrates the fundamental attributes from both types of these classifiers. In the proposed hybrid model CNN works as an automatic feature extractor, and LCS works to provide interpretable rule-based classification results. Although LCS has limitations working on higher dimensional datasets, we resolve this limitation by using CNN as a feature extractor. The other concept of the non-interpretability of CNN is addressed by using the LCS rule. Furthermore, our experiment with higher dimensional datasets like CIFAR-10 and Fashion-MNIST shows that extended LCS provides comparable performance to the standard neural network model while also providing interpretable results. We named this extended LCS method Convolutional Learning Classifier Cystem (C-LCS).

Jelani Owens↗
DOE OSTI2022

An interpretable machine learning model for advancing terrestrial ecosystem predictions

We apply an interpretable Long Short-Term Memory (iLSTM) network for land-atmosphere carbon flux predictions based on time series observations of seven environmental variables. iLSTM enables interpretability of variable importance and variable-wise temporal importance to the prediction of targets by exploring internal network structures. The application results indicate that iLSTM not only improves prediction performance by capturing different dynamics of individual variables, but also reasonably interprets the different contribution of each variable to the target and its different temporal relevance to the target. This variable and temporal importance interpretation of iLSTM advances terrestrial ecosystem model development as well as our predictive understanding of the system.

Lu, Dan↗
DOE OSTI2025

AI for Interpreting Nuclear Power Plant Documents for Power Uprates

To reduce the cost and time needed for regulatory compliance, nuclear power plants (NPPs) can utilize artificial intelligence (AI) to assist in interpreting complex and voluminous documents that typically span thousands of pages. Usually, the process of interpreting a plant’s technical specifications (TSs) and associated documents is labor intensive. This study aims to understand what processes state-of-the-art large language models (LLMs) can automate and to identify the pitfalls associated with using LLMs to reduce human labor costs and time. This research uses a recent AI technology called retrieval augmented generation (RAG), which retrieves pages of information from TSs and associated documents to assist with NPP power uprates (cleared to produce more power). LLMs are integral to RAG because they create human-like responses based on the retrieved information, aiding in the interpretation and application processes. A baseline case demonstrates how LLMs can operate successfully for a power uprate application. Then five use cases show five types of potential failures: (1) RAG retrieving the incorrect information, (2) RAG misinterpreting the retrieved information, (3) RAG relying on knowledge not contained in the retrieved information, (4) RAG hallucinating, and (5) RAG refusing to answer. The results of the five use cases suggest that automating the human interpretation of TSs and associated documents with AI should be approached with caution. A subject-matter expert reviewed the AI outputs from the five use cases and concluded that an LLM can produce technical information that is needed to produce power uprate applications in certain instances.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗
DOE OSTI2017

Interpretation of production tests in geothermal wells with T2Well-EWASG

In the geothermal sector, being able to simulate production tests by combining surface and downhole measurements can be extremely useful, improving data interpretation and reducing the impact of unavailable field data. This is possible with T2Well, a coupled wellbore-reservoir simulator. In this study, we plugged the EWASG equation of state for high enthalpy geothermal reservoirs into T2Well and extended the function to analytically compute the heat exchange between wellbore and formation at the short times. Changes to the analytical heat exchange function were verified by comparison with wellbore-formation heat exchange numerically simulated. T2Well-EWASG was validated by reproducing the flowing pressure and temperature logs taken from literature, and by using the software for the interpretation of a short production test. Lastly, simulation results indicate that T2Well-EWASG can be effectively used to improve the interpretation of production tests performed in geothermal wells.

58 GEOSCIENCES↗