Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Model interpretation and visualization”

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 19 records
All sourcesNASA NTRSDOE OSTI
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 OSTI2026

AIF for Vis (Active Inference for simulating human interpretation of data visualization) [SWR-26-084]

AIF for Vis contains the Active Inference models and analysis scripts used to study a simple visualization-interpretation task: estimating the average value of two bars in a bar chart. The work is a proof of concept for translating hypothesized cognitive strategies into executable, inspectable process models. We implement two idealized strategies inspired by dual-process accounts of visualization-aided decision making: *Fast model: a compressed, heuristic strategy that estimates the visual midpoint of the two bars and maintains a single belief over their average. *Slow model: a sequential, analytic strategy that estimates the two bar heights separately and maintains them in working memory before computing an average. Both models use a common Active-Inference-inspired framework for sequential perception, belief updating, action selection, and reporting. Their different internal representations produce distinct predicted vulnerabilities: *the Fast model is more susceptible to tick-salience bias; *the Slow model is more susceptible to working-memory decay. The repository includes the model implementations, scripts used for the experiments reported in the paper, precomputed trial-level results, and plotting scripts.

Goldwyn, Harrison [National Laboratory of the Rock↗
DOE OSTI2025

Machine Learned Empirical Numerical Integrator from Simulated Data

Recently, a number of state-of-the-art surrogate machine learning (ML) models have been designed for global weather and climate prediction, which have been trained using reanalysis data products. Reanalysis data products are constructed using numerical model simulations that combine numerical integration of partial differential equations and parameterization schemes. These products are typically only archived and made available using coarsened spatial and temporal resolutions. This study explores the impact of the numerical generation methods used to produce the training datasets and the temporal resolution of those datasets on machine learning surrogate models. Using the nonlinear vector autoregression (NVAR) machine as an explainable ML technique, simple dynamical systems are emulated with ML models trained on data produced by three classical numerical integration schemes. NVAR is validated as a skillful ML method, capable of producing accurate predictions and, more importantly, reconstructing both the underlying dynamics and the numerical integration scheme used to generate the training data. However, the machine fails to generalize predictions on unseen test data generated by different numerical integration schemes, despite the underlying dynamical system being the same. This result provides a word of caution for the growing field of machine learning emulation of weather and climate dynamics. Furthermore, we illustrate using NVAR that training on temporally coarsened data may increase the required complexity of ML models and potentially introduce new numerical challenges. Finally, we discover that empirical integration schemes with arbitrary time-stepping sizes can be constructed directly from the data, which implies a potential for the development of empirical numerical integration schemes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Leveraging public AI tools to explore systems biology resources in mathematical modeling

Predictive mathematical modeling is an essential part of systems biology and is interconnected with information management. Systems biology information is often stored in specialized formats to facilitate data storage and analysis. These formats are not designed for easy human readability and thus require specialized software to visualize and interpret results. Therefore, comprehending modeling and underlying networks and pathways is contingent on mastering systems biology tools, which is particularly challenging for users with no or little background in data science or system biology. To address this challenge, we investigated the usage of public Artificial Intelligence (AI) tools in exploring systems biology resources in mathematical modeling. We tested public AI’s understanding of mathematics in models, related systems biology data, and the complexity of model structures. Our approach can enhance the accessibility of systems biology for non-system biologists and help them understand systems biology without a deep learning curve.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Visual Analytics of Crosstalk in Quantum Hardware

Crosstalk remains a major obstacle to building scalable and fault-tolerant quantum computers. Conventional diagnostic techniques-often based on numerical simulation or statistical modeling-struggle to scale with hardware complexity and offer limited interpretability. In this work, we present a visual analytics framework for diagnosing qubit crosstalk using lightweight, circuit-based models integrated with an interactive user interface. Our approach quantifies correlations between active and idle qubits under parameterized single- and twoqubit operations, enabling detection of both spatial and gateinduced crosstalk. The system incorporates qubit topology and gate performance data to support sector-based exploration and correlation mapping. This tool assists users in identifying correlated error sources, informing qubit placement strategies, and guiding noise-aware circuit design.

Chae, Junghoon [ORNL] (ORCID:0000000206016746)↗
DOE OSTI2026

Reduced-Order Modeling of Hydrogen Releases from Vent Stacks and with Wind Effects

Here, the physical release behavior of hydrogen is important to understand from a safety and design perspective. The consequences of unignited pressurized gaseous hydrogen plumes exiting vent stacks were considered by extending and modifying existing general hydrogen plume models. Entrainment, vent stack backpressure, and the flow regime of hydrogen exiting the vent were found to be significant factors affecting plume shape and size, but further investigation and validation with unchoked, low-Froude-number flows is recommended to improve the model’s robustness. Additionally, models for the effects of wind on unignited plume momentum and entrainment were added to explore this behavior. Wind was assumed to increase mixing of hydrogen with the ambient air, and to affect the momentum of the released jet. Introducing wind into the plume model led to a shorter plume for all wind and jet directions. A high counter-flowing wind led to non-physical results and challenges in interpreting the visualization. The proposed jet plume wind sub-models (specifically entrainment coefficients) were fit and compared to experimental data of different releases of hydrogen into a wind tunnel, but the quantity of data available and experimental conditions were limited. Thus, collection of more empirical data and for a wider range of conditions is recommended for improvement of the proposed computational models. Developing reduced-order models for these physical phenomena can improve accessibility to predicted physical behavior and the rate at which hydrogen systems can be safely designed and deployed.

entrainment↗
DOE OSTI2025

Landscaper v1

Understanding the inner workings of machine learning models through their loss landscapes offers crucial insights into model properties, optimization dynamics, and generalizability. However, accessing these insights has traditionally required specialized mathematical expertise, limiting broader adoption. Landscaper is an open-source Python package designed to bridge this gap. Landscaper seamlessly integrates a suite of multi-dimensional loss landscape analyses with cutting-edge topological data analysis (TDA) methods. This powerful combination makes both fundamental loss landscape analysis and advanced TDA techniques accessible to the broader scientific ML community, without requiring deep pre-existing mathematical knowledge. Landscaper offers three key functionalities: * Construction: Builds detailed loss landscape representations through versatile low and high-dimensional sampling techniques. * Quantification: Applies advanced metrics, including a novel topological data analysis (TDA) based smoothness metric, enabling new perspectives on model behavior. * Visualization: Offers intuitive tools to visualize and interpret loss landscapes, providing actionable insights beyond traditional performance metrics.

Weber, Gunther [Lawrence Berkeley National Laborat↗
DOE OSTI2026

REV-INR: Regularized Evidential Implicit Neural Representation for Uncertainty-Aware Volume Visualization

Applications of Implicit Neural Representations (INRs) have emerged as a promising deep learning approach for compactly representing large volumetric datasets. These models can act as surrogates for volume data, enabling efficient storage and on-demand reconstruction via model predictions. However, conventional deterministic INRs only provide value predictions without insights into the model’s prediction uncertainty or the impact of inherent noisiness in the data. This limitation can lead to unreliable data interpretation and visualization due to prediction inaccuracies in the reconstructed volume. Identifying erroneous results extracted from model-predicted data may be infeasible, as raw data may be unavailable due to its large size. To address this challenge, we introduce REV-INR, Regularized Evidential Implicit Neural Representation, which learns to predict data values accurately along with the associated coordinate-level data uncertainty and model uncertainty using only a single forward pass of the trained REV-INR during inference. By comprehensively comparing and contrasting REV-INR with existing well-established deep uncertainty estimation methods, we show that REV-INR achieves the best volume reconstruction quality with robust data (aleatoric) and model (epistemic) uncertainty estimates using the fastest inference time. Consequently, we demonstrate that REV-INR facilitates assessment of the reliability and trustworthiness of the extracted isosurfaces and volume visualization results, enabling analyses to be solely driven by model-predicted data.

Saklani, Shanu [Indian Institute of Technology, Ka↗
DOE OSTI2026

Data Summarization and Inference at Scale

This is the final report for the DOE ASCR grant SC-0022260, Data Summarization and Inference at Scale, PI: Alex Pothen, Purdue University. The goal of the project was to solve data-intensive and compute-intensive problems in the physical sciences, engineering, information science, data science, etc. by designing and implementing new algorithms that could work with a subset of the data. The four subgoals were: (a) The solution of problems where the data is too large to be stored in the memory of a computer. In this streaming model of computation, the data arrives as a stream of elements to the computer, each element is processed as it arrives, and a decision is made to discard the data or to store it; only a small subset of the data proportional to the size of the output solution is stored, and when all the data has been streamed, a solution to the problem is computed from the stored subset. (b) The use of machine learning methods to compute solutions to data-intensive problems. The use of GPUs is critical to obtain high performance on machine learning tasks, but their memory sizes are smaller relative to that of CPUs. For large-scale problems, the data is sampled many times, and small samples are used with repetition, for robustness, to compute solutions to inference tasks. This sampling reduces the memory required to solve the problem, but attention is needed to avoid slow convergence to the solutions, and reduced accuracy of inference. We propose submodular optimization, Large Language Models, and physics-informed neural networks to enable GPU computations here. (c) Modeling and visualization of high-dimensional data using interpretable features. Clinical proteomic data sets from immunology for the detection of cancer and other diseases are temporal and high-dimensional, and algorithms for visualizing these data sets using clinically interpretable features are lacking. We propose methods that compute distances based on the optimal transportation problem and graph edit distances to address this problem. We also propose the use of optimal transport-based distances, spatial statistics, and network structure to classify image data sets, We apply these algorithms to electron micrographs of the peripheral nervous system in the digestive tract. (d) The design of data-intensive algorithms on emerging architectures, specifically, noisy, intermediate-scale quantum (NISQ) devices. Quantum computers offer the possibility of exploring large solution spaces due to the principle of superposition, but current quantum computers are limited by few qubits, short coherence times due to noise, poor interconections among the qubits, etc. We propose the use of the divide and conquer paradigm to solve large-scale problems, wherein collections of small subproblems are solved on the quantum devices, and the solutions to the subproblems are integrated into a solution for the original problem on a classical computer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

elm-diagnostics

elm-diagnostics is a Python package for computing diagnostic analyses and visualizations for the E3SM Land Model (ELM) component and is meant to support new feature development in ELM. The tool reads model history files and performs quantitative analyses including budget-closure checking, variable transformations, temporal aggregations, and statistical summaries to support model evaluation, validation, and scientific interpretation. The framework is designed for extensibility, with modular architecture enabling straightforward addition of new diagnostic methods, derived variables, analysis types, visualization approaches, and model-specific adaptations

Hoffman, Matt [Los Alamos National Laboratory]↗
DOE OSTI2025

Q -score as a reliability measure for protein, nucleic acid and small-molecule atomic coordinate models derived from 3DEM maps

Atomic coordinate models are important for the interpretation of 3D maps produced with cryoEM and cryoET (3D electron microscopy; 3DEM). In addition to visual inspection of such maps and models, quantitative metrics can inform about the reliability of the atomic coordinates, in particular how well the model is supported by the experimentally determined 3DEM map. A recently introduced metric, Q-score, was shown to correlate well with the reported resolution of the map for well fitted models. Here, we present new statistical analyses of Q-score based on its application to ∼10 000 maps and models archived in the EMDB (Electron Microscopy Data Bank) and PDB (Protein Data Bank). Further, we introduce two new metrics based on Q-score to represent each map and model relative to all entries in the EMDB and those with similar resolution. We explore through illustrative examples of proteins, nucleic acids and small molecules how Q-scores can indicate whether the atomic coordinates are well fitted to 3DEM maps and also whether some parts of a map may be poorly resolved due to factors such as molecular flexibility, radiation damage and/or conformational heterogeneity. These examples and statistical analyses provide a basis for how Q-scores can be interpreted effectively in order to evaluate 3DEM maps and atomic coordinate models prior to publication and archiving.

B factors↗
DOE OSTI2026

model-of-perception

Algorithms for perceptually grounded evaluation of scientific visualizations, using neural reconstruction and embedding models to quantify clarity and interpretability.

Bujack, Roxana↗
DOE OSTI2025

Volumetric imaging of the 3D orientation of cellular structures with a polarized fluorescence light-sheet microscope

Polarized fluorescence microscopy is a valuable tool for measuring molecular orientations in biological samples, but techniques for recovering three-dimensional orientations and positions of fluorescent ensembles are limited. We report a polarized dual-view light-sheet system for determining the diffraction-limited three-dimensional distribution of the orientations and positions of ensembles of fluorescent dipoles that label biological structures. We share a set of visualization, histogram, and profiling tools for interpreting these positions and orientations. We model the distributions based on the polarization-dependent efficiency of excitation and detection of emitted fluorescence, using coarse-grained representations we call orientation distribution functions (ODFs). We apply ODFs to create physics-informed models of image formation with spatio-angular point-spread and transfer functions. We use theory and experiment to conclude that light-sheet tilting is a necessary part of our design for recovering all three-dimensional orientations. We use our system to extend known two-dimensional results to three dimensions in FM1-43-labeled giant unilamellar vesicles, fast-scarlet-labeled cellulose in xylem cells, and phalloidin-labeled actin in U2OS cells. Additionally, we observe phalloidin-labeled actin in mouse fibroblasts grown on grids of labeled nanowires and identify correlations between local actin alignment and global cell-scale orientation, indicating cellular coordination across length scales.

Science & Technology - Other Topics↗
DOE OSTI2025

Edge ML for CAN bus intrusion detection in AVs

Autonomous Vehicles (AVs) are revolutionizing transportation, but their reliance on interconnected cyber-physical systems exposes them to unprecedented cybersecurity risks. This study addresses the critical challenge of detecting real-time cyber intrusions in self-driving vehicles by leveraging a dataset from the Udacity self-driving car project. We simulate four high-impact attack vectors, Denial of Service (DoS), spoofing, replay, and fuzzy attacks, by injecting noise into spatial features (e.g., bounding box coordinates) to replicate adversarial scenarios. We develop and evaluate two lightweight neural network architectures (NN-1 and NN-2) alongside a logistic regression baseline (LG-1) for intrusion detection. The models achieve exceptional performance, with NN-2 attaining an AUC score of 93.15% and 93.15% accuracy, demonstrating their suitability for edge deployment in AV environments. Through explainable AI techniques, we uncover unique forensic fingerprints of each attack type, such as spatial corruption in fuzzy attacks and temporal anomalies in replay attacks, offering actionable insights for feature engineering and proactive defense. Visual analytics, including confusion matrices, ROC curves, and feature importance plots, validate the models' robustness and interpretability. This research sets a new benchmark for AV cybersecurity, delivering a scalable, field-ready toolkit for Original Equipment Manufacturers (OEMs) and policymakers. By aligning intrusion fingerprints with SAE J3061 automotive security standards, we provide a pathway for integrating machine learning into safety-critical AV systems. Our findings underscore the urgent need for security-by-design AI, ensuring that AVs not only drive autonomously but also defend autonomously. This work bridges the gap between theoretical cybersecurity and life-preserving engineering, offering a leap toward safer, more secure autonomous transportation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics With Temporal Fusion Transformer and Variational Autoencoders in Power Grid Event Diagnosis

Detecting and analyzing complex patterns in multivariate time-series data is crucial for decision-making in urban and environmental system operations. However, challenges arise from the high dimensionality, intricate complexity, and interconnected nature of complex patterns, which hinder the understanding of their underlying physical processes. Existing AI methods often face limitations in interpretability, computational efficiency, and scalability, reducing their applicability in real-world scenarios. This paper proposes a novel visual analytics framework that integrates two generative AI models, Temporal Fusion Transformer (TFT) and Variational Autoencoders (VAEs), to reduce complex patterns into lower-dimensional latent spaces and visualize them in 2D using dimensionality reduction techniques such as PCA, t-SNE, and UMAP with DBSCAN. These visualizations, presented through coordinated and interactive views and tailored glyphs, enable intuitive exploration of complex multivariate temporal patterns, identifying patterns’ similarities and uncover their potential correlations for a better interpretability of the AI outputs. The framework is demonstrated through a case study on power grid signal data, where it identifies multi-label grid event signatures, including faults and anomalies with diverse root causes. Additionally, novel metrics and visualizations are introduced to validate the models and assess the performance, efficiency, and consistency of latent maps generated by VAE, which have been utilized in prior studies for latent space cartography and used as a benchmark in this study, and the emerging TFT architecture under various configurations. These analyses provide actionable insights for model parameter tuning and reliability improvements. Comparative results highlight that TFT achieves shorter run times and superior scalability to diverse time-series data shapes compared to VAE. This work advances fault diagnosis in multivariate time series, fostering explainable AI to support critical system operations.

Explainable AI↗
DOE OSTI2026

A procedure for rule extraction from a Self-Organising plasma disruption predictor for JET

In a previous paper, a Self-Organizing Map had proven to be able to identify the regions of the plasma operative space characterizing the pre-disruptive phase at JET without relying on any a priori information. One of the strengths of this disruption predictor lies in its inherent self-organization capability. The Self-Organizing Map discovers non-trivial relationships and captures the complicated interplay of device diagnostics on the internal plasma states directly from the experimental data. Moreover, the provided model allows the visualization of high-dimensional plasma parameters and facilitates easy interrogation of the model to understand the reasons behind its correlations. In this paper, an additional step is taken towards the interpretability of models for predicting disruptions by training a Decision Tree to classify the plasma states according to the interpretation provided by the Self-Organizing Map (stable or at high risk of disruptions). The Decision tree provides a set of rules which describe the transition of the plasma towards the pre-disruptive phase as visualized in the Self-Organizing Map. The obtained rules for the database explored in the study identify four regions in the map, two of which are at risk of disruption. These regions correspond to partitions of a 3D space based on the peaking factors of the core and divertor radiation, as well as the Locked Mode. The agreement between the Self-Organizing Map answers and the rules supplied by the Decision Tree is confirmed by the comparison of the performance exhibited by the two models in the prediction of disruptions.

Setzu, Samuele [Univ. of Cagliari, Monserrato, Cag↗
DOE OSTI2025

I Can’t Read All That! Improving the Usability of Semantic Models Using Concise, Ontology-Agnostic, Building-Specific Schemas

Semantic ontologies have enabled the creation of formalized, machine-readable descriptions of heterogenous building systems by providing dictionaries of well defined concepts that can be applied to model them. Within a semantic model of a particular building, a subset of an ontology's concepts may be applied in different ways to represent a particular perspective of the building's systems. How the concepts were applied can only be understood by examining the large amount of instance data within a semantic model, which leads to usability challenges. We propose a concise, ontology-agnostic method for defining building-specific schema (b-schema) graphs that summarize the structure and content of a semantic model. This approach provides a queryable and concise representation of the model's contents, separate from the instance data within a model, that can mitigate the challenges posed by the size and complexity of semantic models in processes such as visualization, querying, validation, and the use of large language models (LLMs). We validate our approach on semantic models based on the Brick and ASHRAE S223 ontologies. Results demonstrate that b-schemas significantly reduce the complexity of visual interpretation, accelerate SPARQL queries and SHACL validation, and improve LLM-based knowledge graph question answering.

Paul, Lazlo [Lawrence Berkeley National Laboratory↗
DOE OSTI2025

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

Decoding visual experiences from fMRI offers a powerful avenue to understand human perception and develop advanced brain-computer interfaces. However, current progress often prioritizes maximizing reconstruction fidelity while overlooking interpretability, an essential aspect for deriving neuroscientific insight. To address this gap, we propose MoRE-Brain, a neuro-inspired framework designed for high-fidelity, adaptable, and interpretable visual reconstruction. MoRE-Brain uniquely employs a hierarchical Mixture-of-Experts architecture where distinct experts process fMRI signals from functionally related voxel groups, mimicking specialized brain networks. The experts are first trained to encode fMRI into the frozen CLIP space. A finetuned diffusion model then synthesizes images, guided by expert outputs through a novel dual-stage routing mechanism that dynamically weighs expert contributions across the diffusion process. MoRE-Brain offers three main advancements: First, it introduces a novel Mixture-of-Experts architecture grounded in brain network principles for neuro-decoding. Second, it achieves efficient cross-subject generalization by sharing core expert networks while adapting only subject-specific routers. Third, it provides enhanced mechanistic insight, as the explicit routing reveals precisely how different modeled brain regions shape the semantic and spatial attributes of the reconstructed image. Extensive experiments validate MoRE-Brain’s high reconstruction fidelity, with bottleneck analyses further demonstrating its effective utilization of fMRI signals, distinguishing genuine neural decoding from over-reliance on generative priors. Consequently, MoRE-Brain marks a substantial advance towards more generalizable and interpretable fMRI-based visual decoding.

Wei, Yuxiang [Georgia Institute of Technology]↗