Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “explainability”

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 OSTI2026

Explainable physics-based constraints on reinforcement learning for accelerator optimization

We present a reinforcement learning (RL) framework for optimizing particle accelerator experiments that builds explainable physics-based constraints on agent behavior. The goal is to increase transparency and trust by letting users verify that the agent’s decision-making process incorporates suitable physics. Our algorithm uses a learnable surrogate function for physical observables, such as energy, and uses them to fine-tune how actions are chosen. This surrogate can be represented by a neural network or by an interpretable sparse dictionary model. We test our algorithm on a range of particle accelerator optimization environments designed to emulate the Continuous Electron Beam Accelerator Facility at Jefferson Lab. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment. In addition, we find that the introduction of a physics-based surrogate enables our RL algorithms to reliably converge for difficult high-dimensional accelerator optimization environments.

explainability↗
DOE OSTI2023

Assessing decadal variability of subseasonal forecasts of opportunity using explainable AI

Abstract Identifying predictable states of the climate system allows for enhanced prediction skill on the generally low-skill subseasonal timescale via forecasts with higher confidence and accuracy, known as forecasts of opportunity. This study takes a neural network approach to explore decadal variability of subseasonal predictability, particularly during forecasts of opportunity. Specifically, this work quantifies subseasonal prediction skill provided by the tropics within the Community Earth System Model Version 2 (CESM2) Large Ensemble and assesses how this skill evolves on decadal timescales. Utilizing the networks’ confidence and explainable artificial intelligence, physically meaningful sources of predictability associated with periods of enhanced skill are identified. Using these networks, we find that tropically-driven subseasonal predictability varies on decadal timescales during forecasts of opportunity. Further, we investigate the drivers of the low frequency modulation of the tropical-extratropical teleconnection and discuss the implications. Analysis is extended to ECMWF Reanalysis v5 data, revealing that the relationships learned within the CESM2-Large Ensemble holds in modern reanalysis data. These results indicate that the neural networks are capable of identifying predictable decadal states of the climate system within CESM2 that are useful for making confident, accurate subseasonal precipitation predictions in the real world.

54 ENVIRONMENTAL SCIENCES↗
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 OSTI2021

Leveraging Community and Author Context to Explain the Performance and Bias of Text-Based Deception Detection Models

Deceptive news posts shared in online communities can be detected with NLP models, and much recent research has focused on the development of such models. In this work, we use characteristics of online communities and authors --- the context of how and where content is posted --- to explain the performance of a neural network deception detection model and identify sub-populations who are disproportionately affected by model accuracy or failure. We examine who is posting the content, and where the content is posted to. We find that while author characteristics are better predictors of deceptive content than community characteristics, both characteristics are strongly correlated with model performance. Traditional performance metrics such as F1 score may fail to capture poor model performance on isolated sub-populations such as specific authors, and as such, more nuanced evaluation of deception detection models is critical.

machine learning (ML), machine learning explanatio↗
DOE OSTI2025

Explainable Machine Learning for Functional Data

Black-box machine learning models are recognized as useful tools for prediction applications, but the algorithmic complexity of some models causes interpretation challenges. Explainability methods have been proposed to provide insight into these models, but there is little research focused on supervised modeling with functional data inputs. We argue that, especially in applications of high consequence, it is important to explicitly model the functional dependence in a black-box analysis to not obscure or misrepresent patterns in explanations. As such, we propose the V ariable importance E xplainable E lastic S hape A nalysis (VEESA) pipeline for training supervised machine learning models with functional inputs. The pipeline is an analysis process that includes the data preprocessing, modeling, and post-hoc explanations. The preprocessing is done using elastic functional principal components analysis, which accounts for vertical and horizontal variability in functional data and, ultimately, allows for explanations in the original data space that identify the important functional variability without bias due to correlated variables. Here, we demonstrate the pipeline on two high-consequence applications: explosives classification for national security and inkjet printer identification in forensic science. The applications exhibit the VEESA pipeline’s ability to provide an understanding of the characteristics of the functional data useful for prediction. Code for implementing the pipeline is available in the veesa R package (and supplemental python code).

Elastic Shape Analysis↗
DOE OSTI2020

Thermodynamic Properties and Molecular Packing Explain Performance and Processing Procedures of Three D18:NFA Organic Solar Cells

Abstract Organic solar cells (OSCs) based on D18:Y6 have recently exhibited a record power conversion efficiency of over 18%. The initial work is extended and the device performance of D18‐based OSCs is compared with three non‐fullerene acceptors, Y6, IT‐4F, and IEICO‐4Cl, and their molecular packing characteristics and miscibility are studied. The D18 polymer shows unusually strong chain extension and excellent backbone ordering in all films, which likely contributes to the excellent hole‐transporting properties. Thermodynamic characterization indicates a room‐temperature miscibility for D18:Y6 and D18:IT‐4F near the percolation threshold. This corresponds to an ideal quench depth and explains the use of solvent vapor annealing rather than thermal annealing. In contrast, D18:IEICO‐4Cl is a low‐miscibility system with a deep quench depth during casting and poor morphology control and low performance. A failure of ternary blends with PC 71 BM is likely due to the near‐ideal miscibility of Y6 to begin with and indicates that strategies for developing successful ternary or quaternary solar cells are likely very different for D18 than for other high‐performing donors. This work reveals several unique property–performance relations of D18‐based photovoltaic devices and helps guide design or fabrication of yet higher efficiency OSCs.

Wang, Zhen↗
DOE OSTI2021

Incorporating Electrochemical Halide Oxidation into Drift-Diffusion Models to Explain Performance Losses in Perovskite Solar Cells under Prolonged Reverse Bias

Partial shading of a solar module can induce a set of cells within the module to operate under reverse bias. Studies have shown that metal halide perovskite solar cells with a wide variety of compositions and contacts exhibit interesting behavior in reverse bias that includes both reversible performance loss and non-reversible degradation. In this paper, an advanced drift-diffusion approach incorporating an electrochemical term to explain the short-circuit, open circuit and fill factor losses that are experimentally measured after prolonged reverse bias is used. It is shown that holes can tunnel into the perovskite due to sharp band bending near the contact, accumulate within the bulk of the perovskite absorber, and trigger the oxidation of halides to form neutral halogens. The density of neutral halogens is much higher in reverse bias because there are hardly any electrons available to reduce the iodine. The resulting halogens act as bulk recombination centers. While the interstitial halogen density does decay when the cell is operated in forward bias, permanent degradation can occur if the iodine diffuses out of the perovskite layer. Finally, the ways in which changing parameters such as the mobile ion density or the series resistance at the contact can influence device performance and stability are discussed.

degradation↗
DOE OSTI2025

Explainable Synthesizability Prediction of Inorganic Crystal Polymorphs Using Large Language Models

Abstract We evaluate the ability of machine learning to predict whether a hypothetical crystal structure can be synthesized and explain those predictions to scientists. Fine‐tuned large language models (LLMs) trained on a human‐readable text description of the target crystal structure perform comparably to previous bespoke convolutional graph neural network methods, but better prediction quality can be achieved by training a positive‐unlabeled learning model on a text‐embedding representation of the structure. An LLM‐based workflow can then be used to generate human‐readable explanations for the types of factors governing synthesizability, extract the underlying physical rules, and assess the veracity of those rules. These explanations can guide chemists in modifying or optimizing non‐synthesizable hypothetical structures to make them more feasible for materials design.

Kim, Seongmin [Department of Chemical and Biologic↗
DOE OSTI2025

Explainable Synthesizability Prediction of Inorganic Crystal Polymorphs Using Large Language Models

Abstract We evaluate the ability of machine learning to predict whether a hypothetical crystal structure can be synthesized and explain those predictions to scientists. Fine‐tuned large language models (LLMs) trained on a human‐readable text description of the target crystal structure perform comparably to previous bespoke convolutional graph neural network methods, but better prediction quality can be achieved by training a positive‐unlabeled learning model on a text‐embedding representation of the structure. An LLM‐based workflow can then be used to generate human‐readable explanations for the types of factors governing synthesizability, extract the underlying physical rules, and assess the veracity of those rules. These explanations can guide chemists in modifying or optimizing non‐synthesizable hypothetical structures to make them more feasible for materials design.

Kim, Seongmin [Department of Chemical and Biologic↗
DOE OSTI2022

Embolism resistance explains mortality and recovery of five subtropical evergreen broadleaf trees to persistent drought

Subtropical evergreen broadleaf forest (SEBF) is experiencing and expected to suffer more frequent and severe drought events. However, how the hydraulic traits directly link to the mortality and recovery of SEBF trees remains unclear. In this study, we conducted a drought-rewatering experiment on tree seedlings of five dominant species to investigate how the hydraulic traits were related to tree mortality and the resistance and recovery of photosynthesis (A) and transpiration (E) under different drought severities. Species with greater embolism resistance (P 50 ) survived longer than those with the weaker P 50 . However, there was no general hydraulic threshold associated with tree mortality, with the lethal hydraulic failure varying from 64% to 93% loss of conductance. Further, the photosynthesis and transpiration of tree species with greater P 50 were more resistant to and recovered faster from drought than those with lower P 50 . Other plant traits could not explain the interspecific variation in tree mortality and drought resistance and recovery. These results highlight the unique importance of embolism resistance in driving carbon and water process under persistent drought across different trees in SEBF. The absence of multiple efficient drought strategies in SEBF seedlings implies the difficulty of natural seedling regeneration under future droughts, which often occurs after destructive disturbances (e.g., extreme drought events and typhoon), suggesting that this biome may be highly vulnerable to co-occurring climate extremes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2018

The binding properties of cycloxaprid on insect native nAChRs partially explain the low cross‐resistance with imidacloprid in Nilaparvata lugens

Abstract BACKGROUND Neonicotinoids, such as imidacloprid, are selective agonists of insect nicotinic acetylcholine receptors (nAChRs) used to control Nilaparvata lugens , a major rice insect pest. High imidacloprid resistance has been reported in N. lugens both in the laboratory and in the field. Cycloxaprid (CYC), an oxa‐bridged cis ‐nitromethylene neonicotinoid, showed high insecticidal activity against N. lugens and low cross‐resistance in imidacloprid‐resistant strains and field populations. RESULTS Binding studies demonstrated that imidacloprid has two binding sites with different affinities ( K d = 3.18 ± 0.43 p m and 1.78 ± 0.19 n m ) in N. lugens nAChRs. CYC was poor at displacing [ 3 H]imidacloprid at its high‐affinity binding site ( K i = 159.38 ± 20.43 n m ), but quite efficient at the low‐affinity binding site ( K i = 1.27 ± 0.35 n m ). These data showed that CYC had overlapping binding sites with imidacloprid only at its low‐affinity binding site. Therefore, the low displacement ability of CYC against imidacloprid binding at its high‐affinity site could partially explain the low cross‐resistance of CYC in imidacloprid‐resistant populations. CONCLUSION The high insecticidal activity, low cross‐resistance and different binding properties on insect nAChRs of CYC show that it is a potential insecticide for the control of N. lugens and related insect pests, especially ones with high resistance to neonicotinoids. © 2018 Society of Chemical Industry

Zhang, Yixi↗
DOE OSTI2021

Explaining (g-2) μ with multi-TeV sleptons

We present a supersymmetric extension of the Standard Model in which the new physics contributions to the anomalous magnetic moment of the muon can be more than an order of magnitude larger than in the minimal supersymmetric Standard Model. The extended electroweak symmetry breaking sector of the model can consistently accommodate Higgs bosons and Higgsinos with O (1) couplings to muons. We find that sleptons with masses in the multi-TeV range can comfortably explain the recently confirmed discrepancy in the anomalous magnetic moment of the muon. We discuss additional phenomenological aspects of the model, including its effects on tau flavor changing decays.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Explainable AI classification for parton density theory

Quantitatively connecting properties of parton distribution functions (PDFs, or parton densities) to the theoretical assumptions made within the QCD analyses which produce them has been a longstanding problem in HEP phenomenology. To confront this challenge, we introduce an ML-based explainability framework, XAI4PDF, to classify PDFs by parton flavor or underlying theoretical model using ResNet-like neural networks (NNs). By leveraging the differentiable nature of ResNet models, this approach deploys guided backpropagation to dissect relevant features of fitted PDFs, identifying x-dependent signatures of PDFs important to the ML model classifications. By applying our framework, we are able to sort PDFs according to the analysis which produced them while constructing quantitative, human-readable maps locating the x regions most affected by the internal theory assumptions going into each analysis. This technique expands the toolkit available to PDF analysis and adjacent particle phenomenology while pointing to promising generalizations.

Artificial Intelligence↗
DOE OSTI2025

Explainable multi-fidelity Bayesian neural network for distribution system state estimation

Distribution System State Estimation (DSSE) is frequently constrained by limited real-time measurements, the uncertainties introduced by distributed energy resources, and the presence of bad data. To address them, this paper proposes an enhanced Multi-Fidelity Bayesian Neural Network (MFBNN) DSSE approach. A low-fidelity layer based on a Deep Neural Network (DNN) is first pre-trained on pseudo-measurement data to learn fundamental state features. Subsequently, a high-fidelity Bayesian Neural Network (BNN) layer leverages limited but high-quality real-time measurements to refine these features, thereby achieving accurate DSSE. Additionally, the deep SHapley Additive exPlanation (SHAP) is developed to quantify the influence of measurement data on DSSE through dual perspectives of global feature importance and local nodal contributions, establishing a hierarchical explainability framework for machine learning-based DSSE. Comparative studies conducted on the IEEE 13-bus system and a real-world 2135-node system from Dominion Energy demonstrate that the proposed method excels in estimation accuracy, even under situations of high noise levels, bad data, and missing data. Further comparisons with Weighted Least Squares (WLS) and other machine learning-based DSSE approaches verify that the proposed framework offers higher accuracy, improved interpretability, and enhanced robustness.

Bad data↗
DOE OSTI2012

Structural Basis and Sequence Rules for Substrate Recognition by Tankyrase Explain the Basis for Cherubism Disease

The poly(ADP-ribose)polymerases Tankyrase 1/2 (TNKS/TNKS2) catalyze the covalent linkage of ADP-ribose polymer chains onto target proteins, regulating their ubiquitylation, stability, and function. Dysregulation of substrate recognition by Tankyrases underlies the human disease cherubism. Tankyrases recruit specific motifs (often called RxxPDG hexapeptides) in their substrates via an N-terminal region of ankyrin repeats. These ankyrin repeats form five domains termed ankyrin repeat clusters (ARCs), each predicted to bind substrate. Here we report crystal structures of a representative ARC of TNKS2 bound to targeting peptides from six substrates. Using a solution-based peptide library screen, we derive a rule-based consensus for Tankyrase substrates common to four functionally conserved ARCs. This 8-residue consensus allows us to rationalize all known Tankyrase substrates and explains the basis for cherubism-causing mutations in the Tankyrase substrate 3BP2. Structural and sequence information allows us to also predict and validate other Tankyrase targets, including Disc1, Striatin, Fat4, RAD54, BCR, and MERIT40.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Machine learning in materials science: From explainable predictions to autonomous design

The advent of big data and algorithmic developments in the field of machine learning (and artificial intelligence, in general) have greatly impacted the entire spectrum of physical sciences, including materials science. Materials data, measured or computed, combined with various techniques of machine learning have been employed to address a myriad of challenging problems, such as, development of efficient and predictive surrogate models for a range of materials properties, screening and down-selection of novel candidate materials for targeted applications, new methodologies to improve and further expedite molecular and atomistic simulations, with likely many more important developments to come in the foreseeable future. While the applications thus far have provided a glimpse of the true potential data-enabled routes have to offer, it has also become clear that further progress in this direction hinges on our ability to understand, explain and rationalize findings of a machine learning model in light of the domain-knowledge. This focused review provides an overview of the main areas where machine learning has been widely and successfully used in materials science. Subsequently, a brief discussion of several techniques that have been helpful in extracting physically-meaningful insights, causal relationships and design-centric knowledge from materials data is provided. Finally, we identify some of the imminent opportunities and challenges that materials community faces in this exciting and rapidly growing field.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Towards physics-informed explainable machine learning and causal models for materials research

From emergent material descriptions to estimation of properties stemming from structures to optimization of process parameters for achieving best performance – all key facets of materials science and related fields have experienced tremendous growth with the introduction of data-driven models. This gradual progression goes at par with developments of machine learning workflows, from purely data-driven shallow models to those that are well-capable in encoding more complex graphs, symbolic representations, invariances, and positional embeddings. Furthermore, this perspective aims at summarizing strategic aspects of such transitions while providing insights into the requirements of bringing in explainable, interpretable predictive models, and causal learning to aid in materials design and discovery. Although the focus remains on a variety of functional materials by providing a handful of case studies, the applications of such integrated methodologies are universal to facilitate fundamental understandings of materials physics while enabling autonomous experiments.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Can exascale computing and explainable artificial intelligence applied to plant biology deliver on the United Nations sustainable development goals?

Human population growth and accelerated climate change necessitate agricultural improvements using designer crop ideotypes (idealized plants that can grow in niche environments). Diverse and highly skilled research groups must integrate efforts to bridge the gaps needed to achieve international goals toward sustainable agriculture. Given the scale of global agricultural needs and the breadth of multiple types of omics data needed to optimize these efforts, explainable artificial intelligence (AI with a decipherable decision making process that provides a meaningful explanation to humans) and exascale computing (computers that can perform 1018 floating-point operations per second, or exaflops) are crucial. Accurate phenotyping and daily-resolution climatype associations are equally important for refining ideotype production to specific environments at various levels of granularity. In this article, we review advances toward tackling technological hurdles to solve multiple United Nations Sustainable Development Goals and discuss a vision to overcome gaps between research and policy.

59 BASIC BIOLOGICAL SCIENCES↗