Tree species explain only half of explained spatial variability in plant water sensitivity
Explore the source record for details and available documents.
Alexandra G. Konings↗
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.
Evaluating the Trustworthiness of Explainable Artificial Intelligence (XAI) Methods Applied to Regression Predictions of Arctic Sea Ice Motion
Abstract Recent advances in explainable artificial intelligence (XAI) methods show promise for understanding predictions made by machine learning (ML) models. XAI explains how the input features are relevant or important for the model predictions. We train linear regression (LR) and convolutional neural network (CNN) models to make 1-day predictions of sea ice velocity in the Arctic from inputs of present-day wind velocity and previous-day ice velocity and concentration. We apply XAI methods to the CNN and compare explanations to variance explained by LR. We confirm the feasibility of using a novel XAI method [i.e., global layerwise relevance propagation (LRP)] to understand ML model predictions of sea ice motion by comparing it to established techniques. We investigate a suite of linear, perturbation-based, and propagation-based XAI methods in both local and global forms. Outputs from different explainability methods are generally consistent in showing that wind speed is the input feature with the highest contribution to ML predictions of ice motion, and we discuss inconsistencies in the spatial variability of the explanations. Additionally, we show that the CNN relies on both linear and nonlinear relationships between the inputs and uses nonlocal information to make predictions. LRP shows that wind speed over land is highly relevant for predicting ice motion offshore. This provides a framework to show how knowledge of environmental variables (i.e., wind) on land could be useful for predicting other properties (i.e., sea ice velocity) elsewhere. Significance Statement Explainable artificial intelligence (XAI) is useful for understanding predictions made by machine learning models. Our research establishes trustability in a novel implementation of an explainable AI method known as layerwise relevance propagation for Earth science applications. To do this, we provide a comparative evaluation of a suite of explainable AI methods applied to machine learning models that make 1-day predictions of Arctic sea ice velocity. We use explainable AI outputs to understand how the input features are used by the machine learning to predict ice motion. Additionally, we show that a convolutional neural network uses nonlinear and nonlocal information in making its predictions. We take advantage of the nonlocality to investigate the extent to which knowledge of wind on land is useful for predicting sea ice velocity elsewhere.
Hoffman, Lauren [Scripps Institution of Oceanograp↗
Leveraging explainable AI to characterize floating-point exceptions in linear solvers
Linear solver packages are central to many scientific, engineering, and machine learning applications. When floating-point exceptions occur in these solvers, e.g., division by zero or overflow, numerical results are compromised and become unreliable. Existing static and dynamic analysis tools can detect such exceptions, but they do not explain why the exceptions occur in terms of the solver inputs. Here, we present a study to characterize the inputs that cause numerical exceptions in linear solver packages. Our approach uses explainable AI (XAI) to find the most relevant characteristics of input matrices that explain the occurrence of exceptions in the solvers. Since training data in this domain is scarce, we perform extensive data gathering and data augmentation to obtain exception-inducing inputs. Our approach uses a repair strategy on the features blamed by XAI to validate that such features indeed explain the exceptions. We compare the LIME and SHAP XAI techniques using a dozen matrix features with three classifiers. We evaluate the approach on three widely used linear solver packages and find that some input characteristics can explain the occurrence of exceptions 100% of the time, in specific solvers and preconditioners.
Explainable AI↗
Heavy fermion behavior explained by bosons
Conventional heavy fermion (HF) theories require existence of massive fermions. We show that heavy fermion phenomena can also be simply explained by existence of bosons with moderate mass but temperature dependent concentration below the formation temperature T(sub B), which in turn is close to room temperature. The bosons B(++) are proposed to be in chemical equilibrium with a system of holes h(+): B(++) = h(+) + h(+). This equilibrium is governed by a boson breaking function f(T), which determines the decreasing boson density and the increasing fermion density with increasing temperature. Since HF-compounds are hybridized from minimum two elements, we assume in addition existence of another fermion component h(sub s)(+) with temperature independent density. This spectator component is thought to be the main agent in binding the bosons in analogy with electronic or muonic molecules. Using a linear boson breaking function we can explain temperature dependence of the giant linear specific heat coefficient gamma(T) coming essentially from bosons. The maxima in resistivity, Hall coefficient, and susceptibility are explained by boson localization effects due to the Wigner crystallization. The antiferromagnetic transitions in turn are explained by similar localization of the pairing fermion system when their density n(sub h)(T(sub FL)) becomes lower than n(sub WC), the critical density of Wigner crystallization. The model applies irrespective whether a compound is superconducting or not. The same model explains the occurrence of low temperature antiferromagnetism also in high-T(sub c) superconductors. The double transition in UPt3 is proposed to be due to the transition of the pairing fermion liquid from spin polarized to unpolarized state.
Kallio, A.↗
Investigation of the Performance and Explainability Tradeoffs for Machine-Learning Models for Predictive Maintenance of Circulating Water Systems in Nuclear Power Plants
Predictive maintenance (PdM) has shown great potential for achieving substantial cost savings and enhancing the economic competitiveness of nuclear power plants (NPPs) in today's energy market. Among the different modeling approaches that exist, machine learning (ML) tools in particular have a demonstrated ability to handle high dimensional and multivariate data and to extract hidden relationships within data in industrial environments. While ML methods show great potential, their lack of explainability---especially for black-box models---is a major hurdle to their adoption. Moreover, considering the supposed trade-off between explainability and performance challenges, careful consideration must be made as to which of these quality aspects takes precedence in light of multiple modeling options, resource availability, and domain characteristics. The present work evaluates the performance of six ML models, each with a different degree of explainability, in classifying the conditions of circulating water pumps (CWPs) by utilizing sensor data from nuclear power plants. To determine the drivers behind the trade-offs presented by this array of models, this work also tests different combinations of CWP units as the training and testing data, degrees of data imbalance, and objective functions for hyperparameter tuning. It was found that black-box models tend to afford superior performance in cases where there are far more instances of one type of labeled data than of any other type. It is recommended that a guided procedure be followed for designing and delivering an ML system that is sufficiently explainable to all involved stakeholders.
22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
Moving beyond post hoc explainable artificial intelligence: a perspective paper on lessons learned from dynamical climate modeling
AI models are criticized as being black boxes, potentially subjecting climate science to greater uncertainty. Explainable artificial intelligence (XAI) has been proposed to probe AI models and increase trust. In this review and perspective paper, we suggest that, in addition to using XAI methods, AI researchers in climate science can learn from past successes in the development of physics-based dynamical climate models. Dynamical models are complex but have gained trust because their successes and failures can sometimes be attributed to specific components or sub-models, such as when model bias is explained by pointing to a particular parameterization. We propose three types of understanding as a basis to evaluate trust in dynamical and AI models alike: (1) instrumental understanding, which is obtained when a model has passed a functional test; (2) statistical understanding, obtained when researchers can make sense of the modeling results using statistical techniques to identify input–output relationships; and (3) component-level understanding, which refers to modelers' ability to point to specific model components or parts in the model architecture as the culprit for erratic model behaviors or as the crucial reason why the model functions well. We demonstrate how component-level understanding has been sought and achieved via climate model intercomparison projects over the past several decades. Such component-level understanding routinely leads to model improvements and may also serve as a template for thinking about AI-driven climate science. Currently, XAI methods can help explain the behaviors of AI models by focusing on the mapping between input and output, thereby increasing the statistical understanding of AI models. Yet, to further increase our understanding of AI models, we will have to build AI models that have interpretable components amenable to component-level understanding. We give recent examples from the AI climate science literature to highlight some recent, albeit limited, successes in achieving component-level understanding and thereby explaining model behavior. The merit of such interpretable AI models is that they serve as a stronger basis for trust in climate modeling and, by extension, downstream uses of climate model data.
54 ENVIRONMENTAL SCIENCES↗
Enhancing Neural Network Explainability with Variational Autoencoders
Machine intelligence has been used to tackle increasingly complex problems and deep learning solutions are at the forefront of tackling these problems. In general, these architectures have a great number of parameters that are methodically updated in training. The vast number and complexity of deep neural networks makes it very difficult to decipher the inner workings of the neurons and layers that make up the network. This paper posits that trustworthiness and trust in autonomous systems are increased through eXplainable Artificial Intelligence (XAI) and presents a method that enhances the explainability and understanding of a neural network decision. We leverage variational autoencoders to produce human interpretable features from complex data sets. We show that the explainable features can then be used for machine learning applications. Explainability inspires trust in autonomous systems that use deep learning, which is necessary for safety critical systems.
Loc Tran↗
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↗
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↗
Violent mergers can explain the inflated state of some of the fastest stars in the Galaxy
A significant number of hypervelocity stars with velocities between 1500 − 2500 km s −1 have recently been observed. The only plausible explanation so far is that they were produced through thermonuclear supernovae in white dwarf binaries. Since these stars are thought to be surviving donors of Type Ia supernovae, a surprising finding was that these stars are inflated, with radii an order of magnitude higher than expected for Roche-lobe-filling donors. Recent attempts at explaining them have combined 3D hydrodynamical supernova explosion simulations with 1D stellar modelling to explain the impact of supernova shocks on runaway white dwarfs. However, only the hottest and most compact of those runaway stars can so far marginally be reproduced by detailed models of runaways from supernova explosions. In this and a companion paper, we introduce a new AREPO simulation of two massive CO white dwarfs that explode via a violent merger. During the merger, the primary white dwarf ignites when the secondary is on its last orbit and plunging towards the primary. In the corresponding aftermath, the core of the secondary white dwarf of 0.16 M ⊙ remains bound, moving at a velocity of ∼2800 km s −1 . We mapped this object into MESA and show that this runaway star can explain the observations of two hypervelocity stars that were dubbed D6-1 and D6-3 based on their original discovery motivated by the D6 scenario, though the violent merger scenario presented here is somewhat distinct from the D6 scenario.
Astronomy and AstroPhysics↗
Global Explainability of A Deep Abstaining Classifier for Cancer Pathology Reports
We present a global explainability method to characterize sources of errors in a real-world multitask deep abstaining classifier (DAC), in the context of cancer histology prediction. Our multitask classifier, currently deployed for automated annotation of cancer pathology reports from NCI-SEER registries, was trained and evaluated on 1.04 million hand-annotated samples and makes simultaneous predictions of cancer site, subsite, histology, laterality, and behavior for each report. The DAC framework enables the model to abstain on ambiguous reports and confusing classes to achieve the target accuracy on the retained (non-abstained) samples, but at the cost of decreased coverage. Requiring 97% accuracy on the histology task caused our model to retain only 22% of all samples, mostly the less ambiguous and common classes. Local explainability with the GradInp technique provided a computationally efficient way of obtaining contextual reasoning for hundreds of thousands of individual predictions. Our method, involving dimensionality reduction of approximately 13000 aggregated local explanations (ALE), offers a tractable path to true global explainability. It enabled identification of sources of errors in histology classification, globally, as hierarchical complexity among classes, label noise, insufficient information, and conflicting evidence. This suggests several strategies for iterative improvement of our DAC, including well-designed exclusion criteria, focused annotation, and reduced penalties for errors involving hierarchically related classes.
59 BASIC BIOLOGICAL SCIENCES↗
Explainable expert systems: A research program in information processing
Our work in Explainable Expert Systems (EES) had two goals: to extend and enhance the range of explanations that expert systems can offer, and to ease their maintenance and evolution. As suggested in our proposal, these goals are complementary because they place similar demands on the underlying architecture of the expert system: they both require the knowledge contained in a system to be explicitly represented, in a high-level declarative language and in a modular fashion. With these two goals in mind, the Explainable Expert Systems (EES) framework was designed to remedy limitations to explainability and evolvability that stem from related fundamental flaws in the underlying architecture of current expert systems.
Paris, Cecile L.↗
An Electrochemical Framework to Explain Intergranular Stress Corrosion Cracking in an Al-5.4%Cu-0.5%Mg-0.5%Ag Alloy
A modified version of the Cu-depletion electrochemical framework was used to explain the metallurgical factor creating intergranular stress corrosion cracking susceptibility in an aged Al-Cu-Mg-Ag alloy, C416. This framework was also used to explain the increased resistance to intergranular stress corrosion cracking in the overaged temper. Susceptibility in the under aged and T8 condition is consistent with the grain boundary Cu-depletion mechanism. Improvements in resistance of the T8+ thermal exposure of 5000 h at 225 F (T8+) compared to the T8 condition can be explained by depletion of Cu from solid solution.
Little, D. A.↗
Towards Explainability of UAV-Based Convolutional Neural Networks for Object Classification
f autonomous systems using trust and trustworthiness is the focus of Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR), a new NASA Convergent Aeronautical Solutions (CAS) Project. One critical research element of ATTRACTOR is explainability of the decision-making across relevant subsystems of an autonomous system. The ability to explain why an autonomous system makes a decision is needed to establish a basis of trustworthiness to safely complete a mission. Convolutional Neural Networks (CNNs) are popular visual object classifiers that have achieved high levels of classification performances without clear insight into the mechanisms of the internal layers and features. To explore the explainability of the internal components of CNNs, we reviewed three feature visualization methods in a layer-by-layer approach using aviation related images as inputs. Our approach to this is to analyze the key components of a classification event in order to generate component labels for features of the classified image at different layers of depths. For example, an airplane has wings, engines, and landing gear. These could possibly be identified somewhere in the hidden layers from the classification and these descriptive labels could be provided to a human or machine teammate while conducting a shared mission and to engender trust. Each descriptive feature may also be decomposed to a combination of primitives such as shapes and lines. We expect that knowing the combination of shapes and parts that create a classification will enable trust in the system and insight into creating better structures for the CNN.
Dolph, Chester V.↗
Using Explainable Scheduling for the Mars 2020 Rover Mission
Understanding the reasoning behind the behavior of an auto- mated scheduling system is essential to ensure that it will be trusted and consequently used to its full capabilities in critical applications. In cases where a scheduler schedules activities in an invalid location, it is usually easy for the user to infer the missing constraint by inspecting the schedule with the in- valid activity to determine the missing constraint. If a sched- uler fails to schedule activities because constraints could not be satisfied, determining the cause can be more challenging. In such cases it is important to understand which constraints caused the activities to fail to be scheduled and how to al- ter constraints to achieve the desired schedule. In this pa- per, we describe such a scheduling system for NASA’s Mars 2020 Perseverance Rover, as well as Crosscheck, an explain- able scheduling tool that explains the scheduler behavior. The scheduling system and Crosscheck are the baseline for oper- ational use to schedule activities for the Mars 2020 rover. As we describe, the scheduler generates a schedule given a set of activities and their constraints and Crosscheck: (1) provides a visual representation of the generated schedule; (2) analyzes and explains why activities failed to schedule given the con- straints provided; and (3) provides guidance on potential con- straint relaxations to enable the activities to schedule in future scheduler runs.
Chien, Steve↗
Using Explainable Artificial Intelligence to Predict Perovskite Solar Cell Electrical Metastability from Operando Photoluminescence Images in Accelerated Stress Testing
Metal halide perovskite (MHP) solar cells exhibit a metastable response to bias governed by coupled ionic–electronic processes, complicating the conventional reciprocity relation between luminescence intensity and device open-circuit voltage (V oc ). This limits the use of luminescence as a diagnostic for device screening or accelerated stress testing, motivating new approaches that can interpret photoluminescence (PL) signals under nonequilibrium conditions. From the artificial intelligence perspective, we develop an explainable deep learning framework that integrates convolutional neural networks (CNN), long short-term memory (LSTM) layers, and an attention mechanism to learn spatiotemporal features from operando photoluminescence PL image sequences. The model achieves a mean absolute error of ±0.027 V in predicting open-circuit voltage transients and reduces extreme-tail errors by up to 78% compared to physics-based reciprocity calculations. Gradient-weighted Class Activation Mapping (Grad-CAM) provides interpretability by highlighting physically meaningful regions such as electrode edges and emergent defect features. From the engineering application perspective, this framework enables accurate, contactless prediction of device V oc and identification of degradation-relevant features during accelerated aging of perovskite solar cells. This approach demonstrates how explainable AI can enhance operando diagnostics and reliability analysis in photovoltaic devices under nonequilibrium conditions.
14 SOLAR ENERGY↗
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↗
Machine Learning Explainability and Transferability for Path Navigation
Deep neural networks are powerful tools for machine perception. Unfortunately their decisions are difficult to explain due to the complexity and size of the networks. Previously we have alleviated this issue by using the representational portion of a deep neural network and combining it with a k-nearest neighbor (KNN) classifier. Through inspection of the decisions made by the KNN, we can directly see the training data responsible for the decisions, allowing us to determine the quality of the overall decision and the quality of the representational layer of the deep NN. While the technique worked well, it requires tens of thousands of latent vectors to be stored for classification. In addition, it lacks the ability to show how parts of an image influence the classification decision. Here we address these issues by 1) Using a radial basis function network (RBFN) in place of the KNN allowing far fewer images to be used in deployment and 2) Using an auto encoder network for explainability. In addition to these techniques, we examine the effects of transfer learning to determine that results are robust. All results are tested on a domain where an unmanned aerial vehicle (UAV) navigates a forest trail through a single camera.
explainable machine learning↗