Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “XAI”

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.

43 records · Page 3
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

An MLCommons Scientific Benchmarks Ontology

Scientific machine learning research spans diverse domains and data modalities, yet existing benchmark efforts remain siloed and lack standardization. This makes novel and transformative applications of machine learning to critical scientific use-cases more fragmented and less clear in pathways to impact. This paper introduces an ontology for scientific benchmarking developed through a unified, community-driven effort that extends the MLCommons ecosystem to cover physics, chemistry, materials science, biology, climate science, and more. Building on prior initiatives such as XAI-BENCH, FastML Science Benchmarks, PDEBench, and the SciMLBench framework, our effort consolidates a large set of disparate benchmarks and frameworks into a single taxonomy of scientific, application, and system-level benchmarks. New benchmarks can be added through an open submission workflow coordinated by the MLCommons Science Working Group and evaluated against a six-category rating rubric that promotes and identifies high-quality benchmarks, enabling stakeholders to select benchmarks that meet their specific needs. The architecture is extensible, supporting future scientific and AI/ML motifs, and we discuss methods for identifying emerging computing patterns for unique scientific workloads. The MLCommons Science Benchmarks Ontology provides a standardized, scalable foundation for reproducible, cross-domain benchmarking in scientific machine learning. A companion webpage for this work has also been developed as the effort evolves: https://mlcommons-science.github.io/benchmark/

Hawks, Ben [Fermilab] (ORCID:0000000157000288)↗
DOE OSTI2025

33 Unresolved Questions in Nanoscience and Nanotechnology

Significant advances in science and engineering often emerge at the intersections of disciplines. Nanoscience and nanotechnology are inherently interdisciplinary, uniting researchers from chemistry, physics, biology, medicine, materials science, and engineering. This convergence has fostered novel ways of thinking and enabled the development of materials, tools, and technologies that have transformed both basic and applied research, as well as how we address critical societal challenges. In this Nano Focus, we pose and explore 33 questions whose answers could profoundly impact fields such as energy, electronics, the environment, optics, and medicine. These questions highlight the need for deeper foundational understanding, improved tools and techniques, and innovative applications─each with significant societal relevance. Together, they represent a global call-to-action for the scientific community.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
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 OSTI2022

304L Can Crush Validation Studies

Accurate prediction of ductile behavior of structural alloys up to and including failure is essential in component or system failure assessment, which is necessary for nuclear weapons alteration and life extensions programs of Sandia National Laboratories. Modeling such behavior requires computational capabilities to robustly capture strong nonlinearities (geometric and material), rate- dependent and temperature-dependent properties, and ductile failure mechanisms. This study's objective is to validate numerical simulations of a high-deformation crush of a stainless steel can. The process consists of identifying a suitable can geometry and loading conditions, conducting the laboratory testing, developing a high-quality Sierra/SM simulation, and then drawing comparisons between model and measurement to assess the fitness of the simulation in regards to material model (plasticity), finite element model construction, and failure model. Following previous material model calibration, a J 2 plasticity model with a microstructural BCJ failure model is employed to model the test specimen made of 304L stainless steel. Simulated results are verified and validated through mesh and mass-scaling convergence studies, parameter sensitivity studies, and a comparison to experimental data. The converged mesh and degree of mass-scaling are the mesh discretization with 140,372 elements, and a mass scaling with a target time increment of 1.0e-6 seconds and time step scale factor of 0.5, respectively. Results from the coupled thermal-mechanical explicit dynamic analysis are comparable to the experimental data. Simulated global force vs displacement (F/D) response predicts key points such as yield, ultimate, and kinks of the experimental F/D response. Furthermore, the final deformed shape of the can and field data predicted from the analysis are similar to that of the deformed can, as measured by 3D optical CMM scans and DIC data from the experiment.

36 MATERIALS SCIENCE↗