A Framework for Evaluating the Maturity Level of Machine Learning Explanations
Explore the source record for details and available documents.
Acquesta, Erin Carolyn Solfiell↗
SEARCH · Search NASA
Results for “machine learning explanation”
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.
Machine Learning for Explanation of Subgrid Convective Precipitation: A Case Study over CONUS Using a Convection-Allowing Model and SHAP Analysis
Explore the source record for details and available documents.
Hyoungseok Kang↗
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↗
Ca X ML: Chemistry‐informed machine learning explains mutual changes between protein conformations and calcium ions in calcium‐binding proteins using structural and topological features
Proteins' flexibility is a feature in communicating changes in cell signaling instigated by binding with secondary messengers, such as calcium ions, associated with the coordination of muscle contraction, neurotransmitter release, and gene expression. When binding with the disordered parts of a protein, calcium ions must balance their charge states with the shape of calcium-binding proteins and their versatile pool of partners depending on the circumstances they transmit. Accurately determining the ionic charges of those ions is essential for understanding their role in such processes. However, it is unclear whether the limited experimental data available can be effectively used to train models to accurately predict the charges of calcium-binding protein variants. Here, we developed a chemistry-informed, machine-learning algorithm that implements a game theoretic approach to explain the output of a machine-learning model without the prerequisite of an excessively large database for high-performance prediction of atomic charges. We used the ab initio electronic structure data representing calcium ions and the structures of the disordered segments of calcium-binding peptides with surrounding water molecules to train several explainable models. Network theory was used to extract the topological features of atomic interactions in the structurally complex data dictated by the coordination chemistry of a calcium ion, a potent indicator of its charge state in protein. Our design created a computational tool of Ca X ML, which provided a framework of explainable machine learning model to annotate ionic charges of calcium ions in calcium-binding proteins in response to the chemical changes in an environment. Our framework will provide new insights into protein design for engineering functionality based on the limited size of scientific data in a genome space.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
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↗
Explaining word embeddings with perfect fidelity: a case study in predicting research impact
The best-performing approaches for scholarly document quality prediction are based on embedding models. In addition to their performance when used in classifiers, embedding models can also provide predictions even for words that were not contained in the labelled training data for the classification model, which is important in the context of the ever-evolving research terminology. Although model-agnostic explanation methods, such as Local interpretable model-agnostic explanations, can be applied to explain machine learning classifiers trained on embedding models, these produce results with questionable correspondence to the model. We introduce a new feature importance method, Self-Model Entities Rated (SMER), for logistic regression-based classification models trained on word embeddings. We show that SMER has theoretically perfect fidelity with the explained model, as the average of logits of SMER scores for individual words (SMER explanation) exactly corresponds to the logit of the prediction of the explained model. Quantitative and qualitative evaluation is performed through five diverse experiments conducted on 50,000 research articles (papers) from the CORD-19 corpus. In conclusion, through an AOPC curve analysis, we experimentally demonstrate that SMER produces better explanations than LIME, SHAP and global tree surrogates.
Coarse-grained models↗
Analyzing the impact of design factors on solar module thermomechanical durability using interpretable machine learning techniques
Solar modules in utility-scale systems are expected to maintain decades of lifetime to rival conventional energy sources. However, cyclic thermomechanical loading often degrades their long-term performance, highlighting the importance of effective design to mitigate thermal expansion mismatches between module materials. Given the complex composition of solar modules, isolating the impact of individual components on overall durability remains a challenging task. In this work, we analyze a comprehensive data set that comprises bill-of-materials (BOM) and thermal cycling power loss from 251 distinct module designs to identify the predominant design factors and their impacts on the thermomechanical durability of modules. The methodology of our analysis combines machine learning modeling (random forest) and Shapley additive explanation (SHAP) to correlate design factors with power loss and interpret the model’s decision-making. The interpretation reveals that silicon type (monocrystalline or polycrystalline), encapsulant thickness, busbar numbers, and wafer thickness predominantly influence the degradation. With lower power loss of around 0.6% on average in the SHAP analysis, monocrystalline cells present better durability than polycrystalline cells. This finding is further substantiated by statistical testing on our raw data set. The SHAP analysis also demonstrates that while thicker encapsulants lead to reduced power loss, further increasing their thickness over around 0.6 to 0.7 mm does not yield additional benefits, particularly for the front side one. In addition, other important BOM features such as the number of busbars are analyzed. This study provides a blueprint for utilizing explainable machine learning techniques in a complex material system and can potentially guide future research on optimizing the design of solar modules.
14 SOLAR ENERGY↗
Contrasting Carbon–Water–Energy Dynamics in Perennial and Annual Bioenergy Agroecosystems Using Eddy Covariance and Interpretable Machine Learning
Understanding how agroecosystems respond to environmental variability is fundamental to predicting productivity and sustainability under a changing climate. We analyzed 55 site-years of high-frequency eddy covariance observations from five agroecosystems—two perennial grasses (miscanthus and switchgrass), two annual rotation systems (maize–soybean and sorghum–soybean), and a restored native prairie—to examine ecosystem-scale carbon, water, and energy fluxes. Using an interpretable machine-learning framework with regression tree ensembles, Shapley Additive Explanations, and Accumulated Local Effects, we quantified how environmental and temporal factors regulate gross primary productivity (GPP), evapotranspiration (ET), water-use efficiency, and the Bowen ratio. Perennials exhibited stronger physiological buffering and maintained fluxes across a broader range of temperature and moisture conditions, reflecting deeper rooting and persistent canopy cover. Annuals, in contrast, showed greater short-term variability and stronger coupling to atmospheric demand, with GPP and ET declining rapidly under low humidity or soil moisture. Differences in temperature sensitivity of Bowen ratio further revealed that perennials sustained proportionally greater sensible heat flux under cool conditions, whereas annuals exhibited constrained energy exchange when evaporative demand was low. Together, these results demonstrate that crop life cycle and canopy structure are fundamental determinants of ecosystem-scale carbon–water–energy coupling. By integrating long-term flux observations with interpretable machine learning, this study identifies the environmental drivers that shape agroecosystem function and highlights how conversion from annual to perennial feedstocks can enhance climatic resilience and alter land–atmosphere energy feedbacks. These findings provide a data-driven basis for improving crop and Earth-system models and for guiding bioenergy landscape design under future climate scenarios.
Accumulated Local Effects↗
Aerosol Influences on Cloud Water: Insights From ARM EPCAPE Observations With Explainable Machine Learning
This study employs an explainable machine learning (ML) framework (XGBoost-SHapley Additive exPlanations analysis) to investigate controlling factors on cloud liquid water path (LWP) using EPCAPE observations near the California coast. Aerosols are found to be the dominant factor explaining LWP variability, surpassing meteorological factors (MFs). By isolating aerosol effects from meteorological influences, the ML reveals a negative linear relationship between LWP and cloud droplet number concentration (Nd) in log space, likely driven by entrainment drying via evaporation-entrainment feedback. This aligns with the negative regime of the inverted-V relationship reported in previous studies, while no positive LWP responses are found due to a limited number of precipitating cases in EPCAPE. Furthermore, the sensitivity of LWP to Nd shows a non-linear dependence on MFs like moisture contrast between surface and free troposphere and lower-tropospheric stability. This occurs due to the interplay between the MFs' direct effects on entrainment drying and indirect effects through LWP adjustments.
EPCAPE observations↗
Leveraging large language models to automate the identification of healthcare access barriers for veterans
Objective: To develop and evaluate an automated system for identifying healthcare barriers focusing on transportation issues in veterans’ clinical notes using large language models (LLMs) and to assess the impact of different prompting strategies on classification performance and explanation consistency. Methods: We developed a hybrid system combining pattern matching for templated notes with LLM analysis for free-text notes. Using 2000 manually annotated clinical notes, we compared four prompting strategies (dual-role short, dual-role long, analysis-first, analysis-only) across Mistral-7B and Llama-3.1 models. We evaluated classification performance using standard metrics and assessed explanation consistency through embedding similarity analysis. Results: The analysis-first strategy achieved superior performance, with Mistral-7B reaching an F1 score of 0.914, outperforming traditional machine learning approaches (GBM: 0.786, BERT: 0.811). LLMs demonstrated higher explanation consistency within models (mean cosine similarity 0.887–0.908) compared to cross-model similarities (0.767–0.872). Pattern matching successfully handled 6.7% of templated notes deterministically. Mistral-7B showed greater internal consistency but higher abstention rates compared to Llama-3.1. Conclusion: Requiring LLMs to analyze evidence before classification improves both accuracy and explanation consistency for identifying transportation barriers in clinical notes. This approach enables automated barrier detection at scale while providing clinically relevant explanations, supporting both population-level healthcare planning and individual patient care decisions.
Healthcare access barriers↗
Mapping wall-to-wall fractional cover of Arctic tundra plant functional types in Alaska using 20-m spatial resolution satellite imagery and harmonized plot observations
Estimates of fractional cover (fCover) across given land surfaces are used to assess, and often model, vegetation composition and diversity, which are crucial for understanding the health and functioning of terrestrial ecosystems. Remote sensing provides a useful means for scaling local, plot-measured fCover estimates to regional scales. Leveraging a recently synthesized and harmonized plot database, this study generated wall-to-wall maps of fCover for six Alaskan-Arctic plant functional types (PFT), including non-vascular plants, forbs, graminoids, and deciduous and evergreen shrubs, using 20-m satellite data (Sentinel-1, Sentinel-2, ArcticDEM) using a machine learning regression approach, specifically the random forest (RF) algorithm, which is well-suited for handling nonlinear relationships and high-dimensional satellite datasets. This study additionally addressed the spatio-temporal inconsistencies e.g., sampling scale, plot size, and collection year in plot measured fCover by adopting a multivariate outlier detection approach—Cook’s distance—to identify high-quality plots for model training and validation. Our approach achieves high accuracy (R 2 = 0.59–0.93, root mean squared errors = 0.02–0.10 for all PFTs) between plot-observed and satellite-derived fCover when using high-quality plot samples. The mapped fCover characterizes the spatial patterns of different PFTs across the tundra biome at a 20-m resolution, providing key information needed for improved representation of Arctic tundra vegetation in terrestrial biosphere models to better understand climate-vegetation feedback across the Arctic tundra.
Arctic tundra↗
On the minimum number of radiation field parameters to specify gas cooling and heating functions
Fast and accurate approximations of gas cooling and heating functions are needed for hydrodynamic galaxy simulations. We use machine learning to analyze atomic gas cooling and heating functions in the presence of a generalized incident local radiation field computed by Cloudy. We characterize the radiation field through binned radiation field intensities instead of the photoionization rates used in our previous work. We find a set of 6 energy bins whose intensities exhibit relatively low correlation. We use these bins as features to train machine learning models to predict Cloudy cooling and heating functions at fixed metallicity. We compare the relative SHapley Additive exPlanation (SHAP) value importance of the features. From the SHAP analysis, we identify a feature subset of 3 energy bins (0.5-1, 1-4, and 13-16Ry) with the largest importance and train additional models on this subset. We compare the mean squared errors and distribution of errors on both the entire training data table and a randomly selected 20% test set withheld from model training. The machine learning models trained with 3 and 6 bins, as well as 3 and 4 photoionization rates, have comparable accuracy everywhere, with errors ≳10 times smaller than for the interpolation table of Gnedin and Hollon (2012). We conclude that 3 energy bins (or 3 analogous photoionization rates: molecular hydrogen photodissociation, neutral hydrogen HI, and fully ionized carbon CVI) are sufficient to characterize the dependence of the gas cooling and heating functions on our assumed incident radiation field model.
79 ASTRONOMY AND ASTROPHYSICS↗
On the minimum number of radiation field parameters to specify gas cooling and heating functions
Fast and accurate approximations of gas cooling and heating functions are needed for hydrodynamic galaxy simulations. We use machine learning to analyze atomic gas cooling and heating functions computed by Cloudy in the presence of a generalized incident local radiation field. We characterize the radiation field through binned radiation field intensities instead of the photoionization rates used in our previous work. We find a set of 6 energy bins whose intensities exhibit relatively low correlation. We use these bins as features to train machine learning models to predict Cloudy cooling and heating functions at fixed metallicity. We compare the relative SHapley Additive exPlanation (SHAP) value importance of the features. From the SHAP analysis, we identify a feature subset of 3 energy bins ($0.5-1, 1-4$, and $13-16 \, \mathrm{Ry}$) with the largest importance and train additional models on this subset. We compare the mean squared errors and distribution of errors on both the entire training data table and a randomly selected 20% test set withheld from model training. The machine learning models trained with 3 and 6 bins, as well as 3 and 4 photoionization rates, have comparable accuracy everywhere, with errors $\gtrsim 10$ times smaller than for the interpolation table of Gnedin and Hollon (2012). We conclude that 3 energy bins (or 3 analogous photoionization rates: molecular hydrogen photodissociation, neutral hydrogen HI, and fully ionized carbon CVI) are sufficient to characterize the dependence of the gas cooling and heating functions on our assumed incident radiation field model.
79 ASTRONOMY AND ASTROPHYSICS↗
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↗
Utilizing Gamma Signals to Find Optimal Uranium Wells
Uranium is a very important resource when using nuclear power. Only a small fraction of the uranium we use in the US is domestically sourced. Our goal is to effectively find and mine uranium in a way that is generally accurate and not difficult. Using computer science and machine learning, we want to automate a reasoning system that geologists use to analyze where the uranium ore bodies are. Presenting a general explanation of the goals and impacts of this project for the High School Intern showcase.
58 - GEOSCIENCES↗
A high-throughput experimentation platform for data-driven discovery in electrochemistry
Automating electrochemical analyses combined with artificial intelligence is poised to accelerate discoveries in renewable energy sciences and technologies. This study presents an automated high-throughput electrochemical characterization (AHTech) platform as a cost-effective and versatile tool for rapidly assessing liquid analytes. The Python-controlled platform combines a liquid handling robot, potentiostat, and customizable microelectrode bundles for diverse, reproducible electrochemical measurements in microtiter plates, minimizing chemical consumption and manual effort. To showcase the capability of AHTech, we screened a library of 180 small molecules as electrolyte additives for aqueous zinc metal batteries, generating data for training machine learning models to predict Coulombic efficiencies. Key molecular features governing additive performance were elucidated using Shapley Additive exPlanations and Spearman’s correlation, pinpointing high-performance candidates like cis-4-hydroxy-d-proline, which achieved an average Coulombic efficiency of 99.52% over 200 cycles. The workflow established herein is highly adaptable, offering a powerful framework for accelerating the exploration and optimization of extensive chemical spaces across diverse energy storage and conversion fields.
Lin, Dian-Zhao [Johns Hopkins University, Baltimor↗
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]↗
Data, model inputs, and analysis scripts associated with a manuscript on stream intermittency controls across spatial scales in Pacific Northwest watersheds
NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the manuscript "Hydroclimatic Memory and Watershed Template Shape Stream Intermittency: Multi-scale Attribution Using Process-based Simulation and Explainable ML" by Niroula et al. (2026), submitted to Water Resources Research (WRR). The study investigates the dominant controls on stream intermittency across local, reach, and watershed scales using a coupled process-based simulation and explainable machine-learning framework. Long-term daily simulations from the Advanced Terrestrial Simulator (ATS) were used to generate wetness states and ponded-depth responses over river-corridor cells. These ATS outputs were then aggregated across scales and used to train XGBoost (eXtreme Gradient Boosting) models. SHAP (SHapley Additive exPlanations) was applied to quantify the relative importance of hydroclimatic forcings, watershed template attributes, and antecedent-memory effects in shaping intermittency behavior. The analysis is carried out for three contrasting Pacific Northwest watersheds: Oak Creek (OCW), American River Watershed (ARW), and H.J. Andrews (HJA). Across these testbeds, the package contains ATS-ready watershed inputs, ATS run configuration and selected output files, model-evaluation data products, intermittency-analysis datasets, machine-learning target-feature tables, SHAP outputs, and notebooks used to organize, analyze, and visualize results. At a high level, the package documents a workflow in which ATS provides the physically based simulation backbone and explainable machine learning is used as a post-processing attribution tool. The contents are intended to support interpretation of the manuscript figures and results, provide context for how intermittency metrics were generated at multiple scales, and preserve the key artifacts needed to understand and reuse the analysis workflow. The package contains a high-level directory summary file (`summary.txt`) and four main content folders (1) `evaluation_plots` contains evaluation figures and supporting evaluation datasets; (2) `intermittency_plots` contains intermittency-focused analysis notebook and prepared datasets; (3) `ml-training-and-shap_values_plots` contains ML training inputs, SHAP outputs, and figure-generation notebooks; and (4) `watershed_mesh_and_ats_input` contains ATS model setup materials, forcing inputs, geometry, and selected run files. More specifically, the `evaluation_plots` folder contains the notebook used for ATS evaluation plotting and site-specific evaluation datasets. These include evapotranspiration and water-balance products for three watersheds, as well as an Oak Creek field-measurement discharge file. The `intermittency_plots` folder contains the notebook used for intermittency analysis and the prepared datasets used to analyze intermittent and non-intermittent wetness behavior across the study watersheds. The `ml-training-and-shap_values_plots` folder contains notebooks and outputs for the machine-learning and explainability workflow. This includes the main XGBoost and SHAP notebook(s), a beeswarm plotting notebook, target-feature tables for machine-learning training, SHAP summary tables, and per-sample SHAP value archives. The `watershed_mesh_and_ats_input` folder contains ATS-related watershed inputs and supporting materials. This includes mesh and shape products, ATS-readable LAI and meteorological forcing inputs, selected ATS spinup and transient-run files, and a watershed workflow example notebook. Subdirectories are organized by watershed where applicable.All files are .cpg (codepage files), .csv (comma-separated values), .dbf (database files), .exo (Exodus mesh format), .h5 (HDF5 format), .ipynb (Jupyter notebooks), .pkl (Python pickle), .prj (projection files), .sh (shell scripts), .shp (shapefile geometry), .shx (shapefile index), .txt (text files), or .xml (markup data).
Advanced Terrestrial Simulator↗