Search NASA⌕ Search

SEARCH · Search NASA

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
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 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↗
NASA NTRS2023

Explainable deep learning for insights in El Niño and river flows

The El Niño Southern Oscillation (ENSO) is a semi-periodic fluctuation in sea surface temperature (SST) over the tropical central and eastern Pacific Ocean that influences interannual variability in regional hydrology across the world through long-range dependence or teleconnections. Recent research has demonstrated the value of Deep Learning (DL) methods for improving ENSO prediction as well as Complex Networks (CN) for understanding teleconnections. However, gaps in predictive understanding of ENSO-driven river flows include the black box nature of DL, the use of simple ENSO indices to describe a complex phenomenon and translating DL-based ENSO predictions to river flow predictions. Here we show that eXplainable DL (XDL) methods, based on saliency maps, can extract interpretable predictive information contained in global SST and discover SST information regions and dependence structures relevant for river flows which, in tandem with climate network constructions, enable improved predictive understanding. Our results reveal additional information content in global SST beyond ENSO indices, develop understanding of how SSTs influence river flows, and generate improved river flow prediction, including uncertainty estimation. Observations, reanalysis data, and earth system model simulations are used to demonstrate the value of the XDL-CN based methods for future interannual and decadal scale climate projections.

SST↗
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 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 OSTI2025

Explaining drivers of housing prices with nonlinear hedonic regressions

Housing markets play a critical role in shaping the spatial and demographic evolution of urban areas. Simulating housing price dynamics can enhance projections of future urban development outcomes. However, traditional hedonic regressions for housing prices, which neglect nonlinear interactions among explanatory variables, often exhibit limited predictive performance. While machine learning (ML) methods can provide a more flexible representation of the relationships between predictors, they are often regarded as “black boxes” due to their complexity and lack of transparency. Interpretable ML techniques provide a promising route by combining the flexibility of ML methods with approaches to analyze the relationships between inputs and outputs. In this study, we employ interpretable ML to analyze the patterns driving the housing market in Baltimore, Maryland, USA. We train an Artificial Neural Network (ANN) to predict Baltimore housing prices based on structural characteristics (e.g., home size, number of stories) and locational attributes (e.g., distance to the city center). We then conduct sensitivity and Partial Dependence Plot (PDP) analyses to interpret the fitted ANN model. We find that the ML model achieves higher predictive accuracy and explains 16 % more of housing price variance than a traditional linear regression model. The interpretable ML model also reveals more nuanced and realistic nonlinear relationships between housing sales price and predictors as well as interactive effects underlying Baltimore home price dynamics. For instance, while the linear model indicates a steady housing price increase over time, our interpretable ML model detects a post-2008 decline, with smaller properties experiencing the sharpest drop.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Detecting thermodynamic phase transition via explainable machine learning of photoemission spectroscopy

Identifying thermodynamic signatures of electronic phases, such as superconductivity, is challenging in low-dimensional materials due to strong fluctuations and low probing volume. Spectroscopic methods are often used to identify new bulk phases, but their main measurable quantity—electronic energy gaps—is no longer an effective order parameter in low-dimensional and fluctuating systems. Combining angle-resolved photoemission with a domain-adversarial neural network, we report a data-driven method to identify thermodynamic phase transitions solely based on single-particle spectra. We demonstrate 97.6% accuracy in cuprate superconductor Bi 2 Sr 2 CaCu 2 O 8+δ with strong superconducting fluctuations. This model notably compensates for the scarcity of experimental data by leveraging virtually inexhaustible simulated data. Further, its explainability reveals the crucial role of in-gap spectral weight in detecting phase fluctuations and thermodynamic transitions. Our work pinpoints the spectroscopic signatures of fluctuating orders and enables using spectroscopy for machine-learning-assisted material discovery for low-dimensional and strong coupling systems.

2D materials↗
DOE OSTI2025

Increasing the Scale of the Mass Spectrometry Query Language Compendium with Explainable AI

A significant bottleneck in metabolomics data interpretation is the effective use of domain knowledge to assign structural information based on fragmentation patterns. The mass spectrometry query language (MassQL) aims to make this process accessible and applicable across multiple analysis platforms. While advanced computational methods are capable of predicting compound structures from fragmentation data, AI/ML approaches often rely on complex, opaque criteria that are difficult to interpret or modify. As a result, their predictive patterns cannot be readily translated into human-readable rules, such as those used in MassQL. Here, in this study, we introduce ChemEcho, a machine learning embedding method that converts tandem mass spectrometry data into sparse feature vectors containing peak and neutral mass subformulae to enhance explainable AI/ML-based methods. An advantage of this approach is that decision trees trained using these feature vectors can be directly translated to MassQL. Using a battery of decision trees trained using ChemEcho embeddings to predict molecular attributes, we generated over 1500 MassQL queries for 765 molecular features and evaluated their precision and recall. From these queries, the 50 highest-performing queries were integrated into the MassQL compendium. This set of generated MassQL queries included environmentally and biologically relevant classes such as PFAS and molecules containing phosphate or sulfate substructures. To illustrate the impact these queries would have on a typical metabolomics experiment, these MassQL queries were applied to a public metabolomics data set─resulting in a marked increase in the structural information derived from tandem mass spectra. Access and reuse of these queries is expected to enhance structural annotation in untargeted experiments, leading to more specific claims and advancing many applications in metabolomics.

Harwood, Thomas V. [USDOE Joint Genome Institute (↗
DOE OSTI2025

Photolytic activation of Ni (II) X 2 L explains how Ni-mediated cross coupling begins

Nickel photocatalysis has recently become vital to organic synthesis, but how the Ni (II) X 2 L pre-catalyst (X = Cl, Br; L = bidentate ligand) becomes activated to Ni (I) XL has remained puzzling and is typically addressed on a case-by-case basis. Here, we reveal a general mechanism where light induces photolysis of the Ni (II) -X bond, either via direct excitation or triplet energy transfer. Photolysis produces Ni (I) XL and a halogen radical, X*. Subsequent hydrogen atom abstraction, often from the solvent, produces a C(sp 3 ) radical, R*, that recombines with Ni (I) to form organonickel(II) complexes, Ni (II) XRL. Rather than acting as a loss pathway, Ni (II) XRL behaves as a light-activated reservoir of Ni (I) via photolysis of the Ni (II) -C bond. These results explain the role of the solvent in protecting the catalyst from off-cycle dimerization, demonstrate that two photons are often required to drive the reaction, and show how tuning the ligand can control the concentration of active Ni (I) species.

08 HYDROGEN↗
DOE OSTI2024

Global burned area increasingly explained by climate change

Fire behaviour is changing in many regions worldwide. However, nonlinear interactions between fire weather, fuel, land use, management and ignitions have impeded formal attribution of global burned area changes. Here, in this work, we demonstrate that climate change increasingly explains regional burned area patterns, using an ensemble of global fire models. The simulations show that climate change increased global burned area by 15.8% (95% confidence interval (CI) [13.1–18.7]) for 2003–2019 and increased the probability of experiencing months with above-average global burned area by 22% (95% CI [18–26]). In contrast, other human forcings contributed to lowering burned area by 19.1% (95% CI [21.9–15.8]) over the same period. Moreover, the contribution of climate change to burned area increased by 0.22% (95% CI [0.22–0.24]) per year globally, with the largest increase in central Australia. Our results highlight the importance of immediate, drastic and sustained GHG emission reductions along with landscape and fire management strategies to stabilize fire impacts on lives, livelihoods and ecosystems.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Changes in sea ice concentration explain half of the winter warming of the Arctic surface

Arctic winter warming is stronger than in summer, but its driving mechanisms remain debated, particularly the roles of local processes, like sea-ice loss, versus remote factors, like atmospheric heat transport. Here we introduce a novel decomposition framework that characterizes Arctic warming as a function of historical atmospheric circulation, sea ice concentration, and carbon dioxide changes using observational and reanalysis data. We show that sea ice changes explain about 55% of the winter Arctic near-surface temperature trend during 1959–2015, after removing the effects directly connected to atmospheric circulation. Dynamically induced warming accounts for about 20% at surface and up to 80% in mid-troposphere. The remaining ~25% is attributed to the increase in carbon dioxide, though it also indirectly affects sea-ice loss and circulation-related warming. These findings highlight the dominant role of sea ice loss and change in atmospheric dynamics in affecting the historical Arctic winter warming.

Arctic Sea Ice change↗
DOE OSTI2026

Attention-based explainability for structure–property relationships

Machine learning methods are emerging as a universal paradigm for constructing correlative structure–property relationships in materials science based on multimodal characterization. However, this necessitates the development of methods for the physical interpretability of the resulting correlative models. Here, we demonstrate the potential of attention-based neural networks for revealing structure–property relationships and the underlying physical mechanisms, using the ferroelectric properties of PbTiO3 thin films as a case study. Through the analysis of attention scores, we disentangle the influence of distinct domain patterns on the polarization switching process. The attention-based Transformer model is explored both as a direct interpretability tool and as a surrogate for explaining representations learned via unsupervised machine learning, enabling the identification of physically grounded correlations. We compare attention-derived interpretability scores with classical SHapley Additive exPlanations analysis and show that, in contrast to applications in natural language processing, attention mechanisms in materials science exhibit high efficiency in highlighting meaningful structural features.

Slautin, Boris [Independent Researcher]↗
DOE OSTI2025

Competition response of cloud supersaturation explains diminished Twomey effect for smoky aerosol in the tropical Atlantic

The Twomey effect brightens clouds by increasing aerosol concentrations, which activates more droplets and decreases cloud supersaturation in response to more competition for water vapor. To quantify this competition response, we used marine low cloud observations in clean and smoky conditions at Ascension Island in the tropical South Atlantic during the Layered Aerosol Smoke Interactions with Cloud (LASIC) campaign. These observations show similar increases in droplet number for increased accumulation-mode particles from surface-based and satellite cloud retrievals, demonstrating the importance of below-cloud aerosol measurements for retrieving aerosol–cloud interactions (ACI) in clean and smoky aerosol conditions. Four methods for estimating cloud supersaturation from aerosol–cloud measurements were compared, with cloud scene-based and parcel-based methods showing sufficient variability for a strong dependence on both aerosol accumulation number concentration and cloud-base updraft velocities. Decomposing aerosol-related changes in cloud albedo and optical depth shows the calculated competition response accounts for dampening the activation response by 12 to 35%, explaining the diminished Twomey effect at high aerosol concentrations observed for smoky conditions at LASIC and previously around the world. This result was consistent for independent supersaturation retrievals by cloud scene-based droplet number and cloud condensation nuclei and parcel-based multimode size-resolving Lagrangian methods. Translating aerosol effects to local radiative forcing with clean conditions as a proxy for preindustrial and smoky conditions for present-day showed that the competition response reduces cooling from the Twomey radiative forcing by 12 to 35%, providing an essential process-specific constraint for improving the representation of aerosol competition in climate model simulation of indirect aerosol forcing.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Observed declines in leaf nitrogen explained by photosynthetic acclimation to CO 2

Widespread evidence of decreasing leaf nutrients has raised concerns about ecosystem productivity under global change. Interpreting trends in leaf nutrients has important implications for the fate of ecosystem services, particularly the role of forests in mitigating climate change and sustaining quality food sources. Here, we challenge the common interpretation that decreasing leaf nitrogen concentration (LNC) is evidence of increasing nutrient limitations on ecosystem primary productivity. Instead, we show that declines in LNC (4% decrease per 50 ppm CO 2 increase), observed across 409 European forest plots over 22 y, can be explained by reduced photosynthetic nitrogen demand. This regional trend is consistent with leaf acclimation to increasing atmospheric CO 2 according to optimality theory. This finding suggests that enhanced photosynthetic nitrogen use efficiency due to CO 2 fertilization may lead to less nitrogen uptake and/or reallocation of nitrogen for plant growth and other functions. Our results have large implications for understanding and simulating interactions between ecosystem nitrogen and carbon cycles and suggest nitrogen requirements for terrestrial carbon uptake under elevated CO 2 may be lower than previously thought.

CO2 fertilization↗
DOE OSTI2025

Explaining the extra crystal-field mode in 𝐴 ⁢Ce ⁢𝑋 2 (𝐴 = K, Rb, Na; 𝑋 = O, S, Se, Te)

A growing list of Ce-based magnets have shown an extra and heretofore unexplained crystal electric field (CEF) mode at high energies. We describe a process whereby an optical phonon can produce a split CEF mode well above the phonon energy. We use density functional theory and point-charge model calculations to estimate the phonon distortions and coupling to model this effect in KCeO 2 , showing that it accounts for the extra CEF mode observed. Furthermore, this mechanism is generic and may explain the extra modes observed on a variety of Ce 3+ compounds.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Explaining Snowball-in-Hell Phenomena in Heavy-Ion Collisions Using a Novel Thermodynamic Variable

A loosely bound hadronic molecule produced by a relativistic heavy-ion collision has been described as a “snowball in hell” since it emerges from a hadron resonance gas whose temperature is orders of magnitude larger than the binding energy of the molecule. This remarkable phenomenon can be explained in terms of a novel thermodynamic variable called the “contact” that is conjugate to the binding momentum of the molecule. The production rate of the molecule can be expressed in terms of the contact density at the kinetic freeze-out of the hadron resonance gas. It approaches a nonzero limit as the binding energy goes to 0.

Relativistic heavy-ion collisions↗