Search NASA⌕ Search

SEARCH · Search NASA

Results for “explainable artificial intelligence”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
NASA NTRS2021

ATTRACTOR: Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability

Autonomous systems (AS) are crucial to realizing the vision of new, complex transportation modes, such as advanced air mobility (AAM) and urban air mobility (UAM). A chief barrier to induction of AS into aviation is insufficient understanding of AS reliability in time-critical and safety-critical environments—an obstacle to certification. ATTRACTOR is aimed at building a basis for certification of classes of autonomous cyber-physical-human systems (CPHS) via establishing metrics and models of trustworthiness and trust in multi-agent team interactions, analyzable trajectories, explainability of computational algorithms (explainable artificial intelligence, or XAI), and persistent modeling and simulation, in the context of missions planning and operation. By “building a basis for certification,” we mean acquiring an understanding of when a system is trustworthy and developing computable means to estimate trustworthiness and trust in order to eventually inform functional requirements that contribute to certification. The outcomes are applicable not just to aviation but to all domains that rely on autonomous systems.

Autonomy↗
DOE OSTI2025

Chemical classification program synthesis using generative artificial intelligence

Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non-organic compounds with desirable material properties, or organizing large chemical libraries for drug discovery or environmental monitoring. However, manual classification is labor-intensive and difficult to scale to large chemical databases. Existing automated approaches either rely on manually constructed classification rules, or are deep learning methods that lack explainability. This work presents an approach that uses generative artificial intelligence to automatically write chemical classifier programs for classes in the Chemical Entities of Biological Interest (ChEBI) database. These programs can be used for efficient deterministic run-time classification of SMILES structures, with natural language explanations. The programs themselves constitute an explainable computable ontological model of chemical class nomenclature, which we call the ChEBI Chemical Class Program Ontology (C3PO). We validated our approach against the ChEBI database, and compared our results against deep learning models and a naive SMARTS pattern based classifier. C3PO outperforms the naive classifier, but does not reach the performance of state of the art deep learning methods. However, C3PO has a number of strengths that complement deep learning methods, including explainability and reduced data dependence. C3PO can be used alongside deep learning classifiers to provide an explanation of the classification, where both methods agree. The programs can be used as part of the ontology development process, and iteratively refined by expert human curators.

Artificial Intelligence↗
DOE OSTI2025

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution

Despite its significant benefits in enhancing the transparency and trustworthiness of artificial intelligence (AI) systems, explainable AI (XAI) can unintentionally provide adversaries with insights into blackbox models, increasing their vulnerability to various attacks. In this paper, we develop a novel explanation-driven adversarial attack against blackbox classifiers based on feature substitution, called XSub. The key idea of XSub is to strategically replace important features (identified via XAI) in the original sample with corresponding important features of a different label, thereby increasing the likelihood of the model misclassifying the perturbed sample. XSub only requires a minimal number of queries and can be easily extended to launch backdoor attacks in case the attacker has access to the model's training data. Our evaluation shows that XSub is not only effective and stealthy but also low-cost, showcasing its feasibility across a wide range of AI applications.

adversarial attack↗
NASA NTRS2018

Serious Gaming for Building a Basis of Certification via Trust and Trustworthiness of Autonomous Systems

Autonomous systems governed by a variety of adaptive and nondeterministic algorithms are being planned for inclusion into safety-critical environments, such as unmanned aircraft and space systems in both civilian and military applications. However, until autonomous systems are proven and perceived to be capable and resilient in the face of unanticipated conditions, humans will be reluctant or unable to delegate authority, remaining in control aided by machine-based information and decision support. Proving capability, or trustworthiness, is a necessary component of certification. Perceived capability is a component of trust. Trustworthiness is an attribute of a cyber-physical system that requires context-driven metrics to prove and certify. Trust is an attribute of the agents participating in the system and is gained over time and multiple interactions through trustworthy behavior and transparency. Historically, artificial intelligence and machine learning systems provide answers without explanation - without a rationale or insight into the machine “thinking”. In order to function as trusted teammates, machines must be able to explain their decisions and actions. This transparency is a product of both content and communication. NASA’s Autonomy Teaming & TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project seeks to build a basis for certification of autonomous systems via establishing metrics for trustworthiness and trust in multi-agent team interactions, using AI (Artificial Intelligence) explainability and persistent modeling and simulation, in the context of mission planning and execution, with analyzable trajectories. Inspired by Massively Multiplayer Online Role Playing Games (MMORPG) and Serious Gaming, the proposed ATTRACTOR modeling and simulation environment is similar to online gaming environments in which player (aka agent) participants interact with each other, affect their environment, and expect the simulation to persist and change regardless of any individual agent’s active participation. This persistent simulation environment will accommodate individual agents, groups of self-organizing agents, and large-scale infrastructure behavior. The effects of the emerging adaptation and coevolution can be observed and measured to building a basis of measurable trustworthiness and trust, toward certification of safety-critical autonomous systems.

Allen, B. Danette↗
DOE OSTI2025

Using a Large Language Model for Accurate Technical Language Generation in the Predictive Maintenance of Circulating Water Systems in Nuclear Power Plants

Machine learning (ML) methods for predictive maintenance (PdM) are emerging as effective proactive strategies for diagnosing equipment degradation and enabling effective decision-making. However, explainability and trustworthiness of artificial intelligence are two salient challenges that need to be addressed for wider deployment of these technologies in nuclear power plants (NPPs). Large language models (LLMs) offer a unique approach to tackle these challenges by explaining PdM, work orders, diagnosis results, and ML algorithms to users, who may not be familiar with ML and PdM in general. Moreover, by dynamically retrieving relevant information from technical documents and evaluating factuality of LLM generation, the accuracy and relevance of LLM generations can be improved. This work demonstrates using LLMs to explain the causes and consequences of circulating water system failures based on multiyear NPP work orders. This work tests the capability of multimodal LLM approaches in explaining the differences in the circulating water system from both the Salem and Hope Creek NPPs using both text and image resources. This work also demonstrates the use of multimodal LLMs in describing the diagnosis tab of a predictive maintenance software named VIsualization for PrEdictive maintenance Recommendation (VIPER) to users.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRSDate not supplied

Plan-Property Dependencies are Useful: A User Study

The trade-offs between different desirable plan properties –e. g. PDDL temporal plan preferences – are often difficult to understand. Recent work proposes to address this by iterative planning with explanations elucidating the dependencies between such plan properties. Users can ask questions of the form “Why does the plan you suggest not satisfy property p?”, which are answered by “Because then we would have to forego q” where ¬q is entailed by p in plan space. It has been shown that such plan-property dependencies can be computed reasonably efficiently. But is this form of explanation actually useful for users? We contribute a user study evaluating that question. We design use cases from three domains and run a large user study (N= 40 for each domain, ca. 40 minutes work time per user and domain) on the internet platform Prolific. Comparing users with vs. without access to the explanations, we find that the explanations tend to enable users to identify better trade-offs between the plan properties, indicating an improved understanding of the task.

Explainable Planning↗
DOE OSTI2026

NuGraph2 with explainability: post-hoc explanations for geometric neural network predictions

With the growing popularity of artificial intelligence (AI) used for scientific applications, the ability of attribute a result to a reasoning process from the network is in high demand for robust scientific generalizations to hold. In this work we aim to motivate the need for and demonstrate the use of post-hoc explainability methods when applied to AI methods used in scientific applications. To this end, we introduce explainability add-ons to the existing graph neural network (GNN) for neutrino tagging, NuGraph2. The explanations take the form of a suite of techniques examining the output of the network (node classifications) and the edge connections between them, and probing of the latent space using novel general-purpose tools applied to this network. We show how none of these methods are singularly sufficient to show network ‘understanding’, but together can give insights into the processes used in classification. While these methods are tested on the NuGraph2 application, they can be applied to a broad range of networks, not limited to GNNs. The code for this work is publicly available on GitHub at https://github.com/voetberg/XNuGraph.

Voetberg, Margaret [Fermilab] (ORCID:0009000527154↗
DOE OSTI2025

Role of Uncertainty Quantification in the Explainability of Large Language Models for the Nuclear Industry

The meteoric rise of generative artificial intelligence (AI) large language models (LLMs) has created an opportunity to utilize them to increase efficiencies in a multitude of industries. While LLMs carry great potential to revolutionize the manner in which work is performed, numerous known deficiencies limit their utility, including the black box nature of the models, the stochastic nature of the response (i.e., presenting the same prompt multiple times results in different responses), and the potential for hallucination. Widespread adoption of LLMs in safety-critical industries such as nuclear will require some form of explainability to assure end users that the LLM’s response to a given query is valid. Model uncertainty is inherently linked to the concepts of trust and explainability, and can be used to identify situations in which the model is insufficiently certain about its answer. Although uncertainty is not enough in and of itself to determine the suitability of an answer—a model can be very certain of an inaccurate answer—it still provides valuable supporting information. Practical methodologies for gauging or quantifying the uncertainty in LLM outputs are presented herein, along with examples based on nuclear-specific prompts.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS2021

NASA Framework for the Ethical Use of Artificial Intelligence (AI)

The NASA Framework for the Ethical Use of Artificial Intelligence (AI) provides six key principles to guide NASA's use of AI. The principles are NASA's AI must be 1. Fair, 2., Explainable and transparent, 3. Accountable, 4. Secure and safe, 5. Human-centric and societally beneficial, and 6. Scientifically and technically robust. The framework describes each ethical AI principle, and then applies that principle to NASA work. The framework also includes a list of questions practitioners should use to guide their AI work. Finally, the framework focuses on concrete, practical considerations for the next five - ten years, while also beginning to lay the foundation for longer-term disruptive change as human-level (or beyond) AI is created.

Artificial Intelligence↗
DOE OSTI2026

Explainable tokamak-agnostic forecasting of fusion plasma instability via megahertz turbulent fluctuations

Scientific applications of artificial intelligence (AI) often remain limited by device-specific training and unexplained “black-box” approaches, creating fundamental barriers to cross-system generalization. This challenge is critical for nuclear fusion, where future reactors will have limited operational data for AI training. Here, we demonstrate that our neural network, trained solely on megahertz-scale turbulence measurements from one machine (DIII-D), forecasts Type-I edge localized mode (ELM) onsets in a different tokamak (KSTAR) through zero-shot weight transfer following physics-consistent preprocessing without device-specific retraining. Through an explainable AI framework combining gradient-weighted class activation mapping with physics validation, we reveal that our network can internalize physics relationships governing the ELM instabilities rather than memorizing device-specific patterns. The network perceives spatiotemporal features that correlate consistently with independently calculated instability growth rates, magnetohydrodynamic stability limits, and pedestal structure dynamics. Statistical analyses of dimensionally-reduced saliency features reveal the identical triangular features between the saliency representations, instability growth rates, and prediction probability across tokamaks, providing evidence that our forecasting system can show tokamak-agnostic generalization. This work contributes to a foundation for explainable scientific AI systems, where cross-system developments are essential for transcending traditional domain-specific constraints.

AI↗
DOE OSTI2026

Regulation compliant AI for fusion: explainable image-based feedback control of divertor detachment in DIII-D tokamak

While artificial intelligence (AI) has been promising for fusion control, its inherent black-box nature will make compliant implementation in regulatory environments a challenge. This study implements and validates a real-time AI-enabled linear and interpretable control system for successful divertor detachment control with the DIII-D lower divertor camera. Using D 2 gas, we demonstrate successful feedback divertor detachment control with a mean absolute difference of 2% from the target for both detachment and reattachment. This automatic training and linear processing framework can be extended to any image-based diagnostic for future fusion reactors.

computer vision↗
NASA NTRS2022

Using an Explainable Machine Learning Approach to Characterize Earth System Model Errors: Application of SHAP Analysis to Modeling Lightning Flash Occurrence

Computational models of the Earth System are critical tools for modern scientific inquiry. Effortstoward evaluating and improving errors in representations of physical and chemical processes inthese large computational systems are commonly stymied by highly nonlinear and complexerror behavior. Recent work has shown that these errors can be effectively predicted usingmodern Artificial Intelligence (A.I.) techniques. In this work, we go beyond these previousstudies to apply an interpretable A.I. technique to not only predict model errors but also movetoward understanding the underlying reasons for successful error prediction. We use XGBoostclassification trees and SHapley Additive exPlanations (SHAP) analysis to explore the errors inthe prediction of lightning occurrence in the NASA GEOS model, a widely used Earth SystemModel. This explainable error prediction system can effectively predict the model error andindicates that the errors are strongly related to convective processes and the characteristics ofthe land surface.

Artificial intelligence↗
NASA NTRS1980

Decision making and problem solving with computer assistance

In modern guidance and control systems, the human as manager, supervisor, decision maker, problem solver and trouble shooter, often has to cope with a marginal mental workload. To improve this situation, computers should be used to reduce the operator from mental stress. This should not solely be done by increased automation, but by a reasonable sharing of tasks in a human-computer team, where the computer supports the human intelligence. Recent developments in this area are summarized. It is shown that interactive support of operator by intelligent computer is feasible during information evaluation, decision making and problem solving. The applied artificial intelligence algorithms comprehend pattern recognition and classification, adaptation and machine learning as well as dynamic and heuristic programming. Elementary examples are presented to explain basic principles.

Kraiss, F.↗
DOE OSTI2025

SetBERT: the deep learning platform for contextualized embeddings and explainable predictions from high-throughput sequencing

MOTIVATION: High-throughput sequencing (HTS) is a modern sequencing technology used to profile microbiomes by sequencing thousands of short genomic fragments from the microorganisms within a given sample. This technology presents a unique opportunity for artificial intelligence to comprehend the underlying functional relationships of microbial communities. However, due to the unstructured nature of HTS data, nearly all computational models are limited to processing DNA sequences individually. This limitation causes them to miss out on key interactions between microorganisms, significantly hindering our understanding of how these interactions influence the microbial communities as a whole. Furthermore, most computational methods rely on post-processing of samples which could inadvertently introduce unintentional protocol-specific bias. RESULTS: Addressing these concerns, we present SetBERT, a robust pre-training methodology for creating generalized deep learning models for processing HTS data to produce contextualized embeddings and be fine-tuned for downstream tasks with explainable predictions. By leveraging sequence interactions, we show that SetBERT significantly outperforms other models in taxonomic classification with genus-level classification accuracy of 95%. Furthermore, we demonstrate that SetBERT is able to accurately explain its predictions autonomously by confirming the biological-relevance of taxa identified by the model. AVAILABILITY AND IMPLEMENTATION: All source code is available at https://github.com/DLii-Research/setbert. SetBERT may be used through the q2-deepdna QIIME 2 plugin whose source code is available at https://github.com/DLii-Research/q2-deepdna.

Ludwig, David W↗
DOE OSTI2025

A comparison of probabilistic generative frameworks for molecular simulations

Generative artificial intelligence is now a widely used tool in molecular science. Despite the popularity of probabilistic generative models, numerical experiments benchmarking their performance on molecular data are lacking. Here, in this work, we introduce and explain several classes of generative models, broadly sorted into two categories: flow-based models and diffusion models. We select three representative models: neural spline flows, conditional flow matching, and denoising diffusion probabilistic models, and examine their accuracy, computational cost, and generation speed across datasets with tunable dimensionality, complexity, and modal asymmetry. Our findings are varied, with no one framework being the best for all purposes. In a nutshell, (i) neural spline flows do best at capturing mode asymmetry present in low-dimensional data, (ii) conditional flow matching outperforms other models for high-dimensional data with low complexity, and (iii) denoising diffusion probabilistic models appear the best for low-dimensional data with high complexity. Our datasets include a Gaussian mixture model and the dihedral torsion angle distribution of the Aib9 peptide, generated via a molecular dynamics simulation. We hope our taxonomy of probabilistic generative frameworks and numerical results may guide model selection for a wide range of molecular tasks.

Artificial intelligence↗