Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Explanability”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.

This report details the results of a three-fold investigation of sensitivity analysis (SA) for machine learning (ML) explainability (MLE): (1) the mathematical assessment of the fidelity of an explanation with respect to a learned ML model, (2) quantifying the trustworthiness of a prediction, and (3) the impact of MLE on the efficiency of end-users through multiple users studies. We focused on the cybersecurity domain as the data is inherently non-intuitive. As ML is being using in an increasing number of domains, including domains where being wrong can elicit high consequences, MLE has been proposed as a means of generating trust in a learned ML models by end users. However, little analysis has been performed to determine if the explanations accurately represent the target model and they themselves should be trusted beyond subjective inspection. Current state-of-the-art MLE techniques only provide a list of important features based on heuristic measures and/or make certain assumptions about the data and the model which are not representative of the real-world data and models. Further, most are designed without considering the usefulness by an end-user in a broader context. To address these issues, we present a notion of explanation fidelity based on Shapley values from cooperative game theory. We find that all of the investigated MLE explainability methods produce explanations that are incongruent with the ML model that is being explained. This is because they make critical assumptions about feature independence and linear feature interactions for computational reasons. We also find that in deployed, explanations are rarely used due to a variety of reason including that there are several other tools which are trusted more than the explanations and there is little incentive to use the explanations. In the cases when the explanations are used, we found that there is the danger that explanations persuade the end users to wrongly accept false positives and false negatives. However, ML model developers and maintainers find the explanations more useful to help ensure that the ML model does not have obvious biases. In light of these findings, we suggest a number of future directions including developing MLE methods that directly model non-linear model interactions and including design principles that take into account the usefulness of explanations to the end user. We also augment explanations with a set of trustworthiness measures that measure geometric aspects of the data to determine if the model output should be trusted.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Leveraging large language models to automate the identification of healthcare access barriers for veterans

Objective: To develop and evaluate an automated system for identifying healthcare barriers focusing on transportation issues in veterans’ clinical notes using large language models (LLMs) and to assess the impact of different prompting strategies on classification performance and explanation consistency. Methods: We developed a hybrid system combining pattern matching for templated notes with LLM analysis for free-text notes. Using 2000 manually annotated clinical notes, we compared four prompting strategies (dual-role short, dual-role long, analysis-first, analysis-only) across Mistral-7B and Llama-3.1 models. We evaluated classification performance using standard metrics and assessed explanation consistency through embedding similarity analysis. Results: The analysis-first strategy achieved superior performance, with Mistral-7B reaching an F1 score of 0.914, outperforming traditional machine learning approaches (GBM: 0.786, BERT: 0.811). LLMs demonstrated higher explanation consistency within models (mean cosine similarity 0.887–0.908) compared to cross-model similarities (0.767–0.872). Pattern matching successfully handled 6.7% of templated notes deterministically. Mistral-7B showed greater internal consistency but higher abstention rates compared to Llama-3.1. Conclusion: Requiring LLMs to analyze evidence before classification improves both accuracy and explanation consistency for identifying transportation barriers in clinical notes. This approach enables automated barrier detection at scale while providing clinically relevant explanations, supporting both population-level healthcare planning and individual patient care decisions.

Healthcare access barriers↗
DOE OSTI2025

ACES-GNN: can graph neural network learn to explain activity cliffs?

Graph Neural Networks (GNNs) have revolutionized molecular property prediction by leveraging graph-based representations, yet their opaque decision-making processes hinder broader adoption in drug discovery. This study introduces the Activity-Cliff-Explanation-Supervised GNN (ACES-GNN) framework, designed to simultaneously improve predictive accuracy and interpretability by integrating explanation supervision for activity cliffs (ACs) into GNN training. ACs, defined by structurally similar molecules with significant potency differences, pose challenges for traditional models due to their reliance on shared structural features. By aligning model attributions with chemist-friendly interpretations, the ACES-GNN framework bridges the gap between prediction and explanation. Validated across 30 pharmacological targets, ACES-GNN consistently enhances both predictive accuracy and attribution quality for ACs compared to unsupervised GNNs. Our results demonstrate a positive correlation between improved predictions and accurate explanations, offering a robust and adaptable framework to better understand and interpret ACs. This work underscores the potential of explanation-guided learning to advance interpretable artificial intelligence in molecular modeling and drug discovery.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Explaining machine-learning models for gamma-ray detection and identification

As more complex predictive models are used for gamma-ray spectral analysis, methods are needed to probe and understand their predictions and behavior. Recent work has begun to bring the latest techniques from the field of Explainable Artificial Intelligence (XAI) into the applications of gamma-ray spectroscopy, including the introduction of gradient-based methods like saliency mapping and Gradient-weighted Class Activation Mapping (Grad-CAM), and black box methods like Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). In addition, new sources of synthetic radiological data are becoming available, and these new data sets present opportunities to train models using more data than ever before. In this work, we use a neural network model trained on synthetic NaI(Tl) urban search data to compare some of these explanation methods and identify modifications that need to be applied to adapt the methods to gamma-ray spectral data. We find that the black box methods LIME and SHAP are especially accurate in their results, and recommend SHAP since it requires little hyperparameter tuning. We also propose and demonstrate a technique for generating counterfactual explanations using orthogonal projections of LIME and SHAP explanations.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2020

Measure Utility, Gain Trust: Practical Advice for XAI Researchers

Research into explanation of machine learning models, i.e. explainable AI (XAI), has seen a sympathetic exponential growth alongside deep artificial neural networks throughout the past decade. For historical reasons explanation and trust have been intertwined. However this focus on trust is too narrow, and has led the research community astray from tried and true empirical methods that lead to more defensible scientific knowledge about people and explanations. To address this, we contribute a practical path forward for researchers in the XAI field. We recommend researchers focus on the utility and impact of their explanations instead of trust. We outline five broad use cases where explanations are useful and, for each, we describe pseudo-experiments that rely on objective empirical measurements and falsifiable hypotheses. We believe that this experimental rigor is necessary to contribute to scientific knowledge in the field of XAI.

Davis, Brittany F.↗
DOE OSTI2025

Explaining word embeddings with perfect fidelity: a case study in predicting research impact

The best-performing approaches for scholarly document quality prediction are based on embedding models. In addition to their performance when used in classifiers, embedding models can also provide predictions even for words that were not contained in the labelled training data for the classification model, which is important in the context of the ever-evolving research terminology. Although model-agnostic explanation methods, such as Local interpretable model-agnostic explanations, can be applied to explain machine learning classifiers trained on embedding models, these produce results with questionable correspondence to the model. We introduce a new feature importance method, Self-Model Entities Rated (SMER), for logistic regression-based classification models trained on word embeddings. We show that SMER has theoretically perfect fidelity with the explained model, as the average of logits of SMER scores for individual words (SMER explanation) exactly corresponds to the logit of the prediction of the explained model. Quantitative and qualitative evaluation is performed through five diverse experiments conducted on 50,000 research articles (papers) from the CORD-19 corpus. In conclusion, through an AOPC curve analysis, we experimentally demonstrate that SMER produces better explanations than LIME, SHAP and global tree surrogates.

Coarse-grained models↗
DOE OSTI2023

RX-ADS: Interpretable Anomaly Detection Using Adversarial ML for Electric Vehicle CAN Data

Recent year has brought considerable advancements in Electric Vehicles (EVs) and associated infrastructures/ communications. Intrusion Detection Systems (IDS) are widely deployed for anomaly detection in such critical infrastructures. This paper presents an Interpretable Anomaly Detection System (RX-ADS) for intrusion detection in CAN protocol communication in EVs. Contributions include: 1) window based feature extraction method; 2) deep Autoencoder based anomaly detection method; and 3) adversarial machine learning based explanation generation methodology. The presented approach was tested on two benchmark CAN datasets: OTIDS and Car Hacking. The anomaly detection performance of RX-ADS was compared against the state-of-the-art approaches on these datasets: HIDS and GIDS. The RX-ADS approach presented performance comparable to the HIDS approach (OTIDS dataset) and has outperformed HIDS and GIDS approaches (Car Hacking dataset). Further, the proposed approach was able to generate explanations for detected abnormal behaviors arising from various intrusions. Furthermore, these explanations were later validated by information used by domain experts to detect anomalies. Other advantages of RX-ADS include: 1) the method can be trained on unlabeled data; 2) explanations help experts in understanding anomalies and root course analysis, and also help with AI model debugging and diagnostics, ultimately improving user trust in AI systems.

42 ENGINEERING↗
DOE OSTI2026

Search for NC Delta Radiative Decay Single Photon Events In MicroBooNE

MicroBooNE, a liquid argon time projection chamber at Fermilab, is investigating the MiniBooNE anomaly, which consists of an excess of low-energy electromagnetic showers in a neutrino beam. Recent results from MicroBooNE have ruled out a 3+1 sterile neutrino explanation of the anomaly, leaving the single photon-like explanation as the most likely possibility. In this poster, we describe results of a new expanded search for the neutral current Delta radiative decay topology, a rare type of event which is by far the largest expected source of neutrino-induced single photons. Using two different reconstruction paradigms simultaneously, we study in detail events both with and without visible hadronic activity; either category of event could explain the MiniBooNE anomaly, but the two could have very different implications for underlying physics. We find that events with visible protons are excluded as an explanation of the MiniBooNE anomaly, but events without visible protons remain a possible explanation requiring further study.

Hagaman, Lee [Nevis Labs, Columbia U.] (ORCID:0000↗
NASA NTRS1987

Communications and tracking expert systems study

The original objectives of the study consisted of five broad areas of investigation: criteria and issues for explanation of communication and tracking system anomaly detection, isolation, and recovery; data storage simplification issues for fault detection expert systems; data selection procedures for decision tree pruning and optimization to enhance the abstraction of pertinent information for clear explanation; criteria for establishing levels of explanation suited to needs; and analysis of expert system interaction and modularization. Progress was made in all areas, but to a lesser extent in the criteria for establishing levels of explanation suited to needs. Among the types of expert systems studied were those related to anomaly or fault detection, isolation, and recovery.

Leibfried, T. F.↗
NASA NTRS1994

The transition from diapirism to dike intrusion: Implications for planetary volcanism

Magma transport processes influence the rate of magma transport and how far the magma travels before it freezes, the degree to which the magma communicates chemically with the host rock, the morphology of volcanic landforms on planetary surfaces, the interplay between magmatism and regional tectonics, and even the direction the magma moves. The primary question motivating this research is: How does magma rheology influence the mechanisms by which it is transported through planetary lithospheres? It is widely recognized that on Earth basaltic intrusions typically take the form of narrow dikes, while granites are typically found in more equidimensional plutons. Several explanations for this observation were offered over the last 50 years. While basalts and rhyolites vary somewhat in temperature and density, the major difference is the 2 to 8 orders of magnitude contrast in viscosity. The significant ductile strains associated with many granitic plutons has led to the statement that the occurrence of granites in diapirs rather than dikes results from the fact that there is insufficient viscosity contrast between the magma and wall rock for the granite to intrude narrow cracks. A second explanation states that granites are so viscous that they cannot propagate far before freezing. Despite the length of time these explanations have been around, there has been relatively little effort to investigate them quantitatively. My goal has been to evaluate these explanations through a series of well-posed numerical models. These models can be tested by the decades of field data collected by structural geologists that have yet to be integrated into any coherent theory, and the results should have important implications for volcanism on the terrestrial planets.

Rubin, Allan M.↗
NASA NTRS2005

Formal Safety Certification of Aerospace Software

In principle, formal methods offer many advantages for aerospace software development: they can help to achieve ultra-high reliability, and they can be used to provide evidence of the reliability claims which can then be subjected to external scrutiny. However, despite years of research and many advances in the underlying formalisms of specification, semantics, and logic, formal methods are not much used in practice. In our opinion this is related to three major shortcomings. First, the application of formal methods is still expensive because they are labor- and knowledge-intensive. Second, they are difficult to scale up to complex systems because they are based on deep mathematical insights about the behavior of the systems (t.e., they rely on the "heroic proof"). Third, the proofs can be difficult to interpret, and typically stand in isolation from the original code. In this paper, we describe a tool for formally demonstrating safety-relevant aspects of aerospace software, which largely circumvents these problems. We focus on safely properties because it has been observed that safety violations such as out-of-bounds memory accesses or use of uninitialized variables constitute the majority of the errors found in the aerospace domain. In our approach, safety means that the program will not violate a set of rules that can range for the simple memory access rules to high-level flight rules. These different safety properties are formalized as different safety policies in Hoare logic, which are then used by a verification condition generator along with the code and logical annotations in order to derive formal safety conditions; these are then proven using an automated theorem prover. Our certification system is currently integrated into a model-based code generation toolset that generates the annotations together with the code. However, this automated formal certification technology is not exclusively constrained to our code generator and could, in principle, also be integrated with other code generators such as RealTime Workshop or even applied to legacy code. Our approach circumvents the historical problems with formal methods by increasing the degree of automation on all levels. The restriction to safety policies (as opposed to arbitrary functional behavior) results in simpler proof problems that can generally be solved by fully automatic theorem proves. An automated linking mechanism between the safety conditions and the code provides some of the traceability mandated by process standards such as DO-178B. An automated explanation mechanism uses semantic markup added by the verification condition generator to produce natural-language explanations of the safety conditions and thus supports their interpretation in relation to the code. It shows an automatically generated certification browser that lets users inspect the (generated) code along with the safety conditions (including textual explanations), and uses hyperlinks to automate tracing between the two levels. Here, the explanations reflect the logical structure of the safety obligation but the mechanism can in principle be customized using different sets of domain concepts. The interface also provides some limited control over the certification process itself. Our long-term goal is a seamless integration of certification, code generation, and manual coding that results in a "certified pipeline" in which specifications are automatically transformed into executable code, together with the supporting artifacts necessary for achieving and demonstrating the high level of assurance needed in the aerospace domain.

Denney, Ewen↗