Search NASA⌕ Search

SEARCH · Search NASA

Results for “Explainable machine learning”

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 325 records · Page 18

Software for Partly Automated Recognition of Targets

The Feature Analyst is a computer program for assisted (partially automated) recognition of targets in images. This program was developed to accelerate the processing of high-resolution satellite image data for incorporation into geographic information systems (GIS). This program creates an advanced user interface that embeds proprietary machine-learning algorithms in commercial image-processing and GIS software. A human analyst provides samples of target features from multiple sets of data, then the software develops a data-fusion model that automatically extracts the remaining features from selected sets of data. The program thus leverages the natural ability of humans to recognize objects in complex scenes, without requiring the user to explain the human visual recognition process by means of lengthy software. Two major subprograms are the reactive agent and the thinking agent. The reactive agent strives to quickly learn the user s tendencies while the user is selecting targets and to increase the user s productivity by immediately suggesting the next set of pixels that the user may wish to select. The thinking agent utilizes all available resources, taking as much time as needed, to produce the most accurate autonomous feature-extraction model possible.

Opitz, David↗

A Review on the State of the Art of Machine Learning and Satellite Imaging: Detecting Scene Changes in Selected Nuclear Fuel Cycle Datasets

The timely detection of clandestine nuclear facilities is one of the greatest challenges faced by the International Atomic Energy Agency’s (IAEA). Idaho National Laboratory is currently applying machine learning (ML) to existing satellite imagery (SI) datasets to find facilities within the nuclear fuel life cycle, with primary focus placed on identifying critical predecessor (i.e., fuel fabrication and fuel enrichment) and successor (i.e., nuclear power plants) facilities. This could provide a satellite image methodology that the IAEA could leverage to discover clandestine facilities. The work presented in this paper describes the evolution of a workflow developed by this team for object detection related to critical infrastructure by expanding that workflow for the purpose of identifying nuclear fuel cycle components and automating dependency assessments. This will be done using two methods housed within a single pipeline. The first method involves implementing a DenseNet161 convolutional neural network to classify the images and explain the results using Local Interpretable Model-Agnostic Explanations (LIME). The second method implements You Only Look Once version 5 (YoloV5), to detect objects within images, provide a probability for the detection, and provide a bounding box that corresponds to the object of interest. The results of this work are anticipated to provide a clear picture of this portion of the nuclear fuel cycle and perform as a stand-alone tool for image assessment that can be expanded to additional fuel cycle components and implemented in international safeguards and national security domains. This capability addresses the IAEA’s need to detect undeclared nuclear materials and activities within a state while encompassing the entire nuclear fuel cycle.

97 MATHEMATICS AND COMPUTING↗

Nonnegative canonical tensor decomposition with linear constraints: nnCANDELINC

Abstract There is an emerging interest for tensor factorization applications in big‐data analytics and machine learning. To speed up the factorization of extra‐large datasets, organized in multidimensional arrays (also known as tensors), easy to compute compression‐based tensor representations, such as, Tucker and tensor train formats, are used to approximate the initial large‐tensor. Further, tensor factorization is used to extract latent features that can facilitate discoveries of new mechanisms and signatures hidden in the data, where the explainability of the latent features is of principal importance. Nonnegative tensor factorization extracts latent features that are naturally sparse and parts of the data, which makes them easily interpretable. However, to take into account available domain knowledge and subject matter expertise, often additional constraints need to be imposed, which lead us to canonical decomposition with linear constraints (CANDELINC), a canonical polyadic decomposition with rank deficient factors. In CANDELINC, Tucker compression is used as a preprocessing step, which lead to a larger residual error but to more explainable latent features. Here, we propose a nonnegative CANDELINC (nnCANDELINC) accomplished via a specific nonnegative Tucker decomposition; we refer to as minimal or canonical nonnegative Tucker. We derive several results required to understand the specificity of nnCANDELINC, focusing on the difficulties of preserving the nonnegative rank of a tensor to its Tucker core and comparing the real valued to nonnegative case. Finally, we demonstrate nnCANDELINC performance on synthetic and real‐world examples.

97 MATHEMATICS AND COMPUTING↗

TriGORank: A Gene Ontology Enriched Learning-to-Rank Framework for Trigenic Fitness Prediction

Machine learning (ML) has been gaining interest in the metabolic engineering community as a means to automate prediction tasks. In this work, we introduce and study the task of using ML to recommend high-fitness triplet mutants as candidates for wet-lab experiments. We first utilize individual fitness and digenic fitness scores as features and train machine learning models that produce a ranked list, from high to low fitness scores, for triplet gene mutants of S. cerevisiae. Then, we incorporate prior metabolic knowledge from an existing gene ontology, by designing a novel graph representation and deducing features that can capture gene similarity and gene interactions. Lastly, experimental results show that our proposed gene ontology enriched model, termed TriGORank, improves both performance and explainability.

Labhishetty, Sahiti↗

Process Anomaly Detection for Sparsely Labeled Events in Nuclear Power Plants

An essential aspect of online monitoring, subtle anomaly detection increases the detection lead time for equipment failure and enables a nuclear power plant (NPP) to mitigate unexpected partial or full outages, resulting in significant cost saving to the plant. Once an anomaly is detected by plant staff, its cause and severity are investigated. Because the vast majority of anomalies require some level of investigation, including some that require time-consuming examination, before they are passed over to the engineering organization for further analysis, plants are often equipped with tools to assist the staff in performing anomaly detection. Those tools operate as a black box and are often based on statistical methods that establish sensor correlations using preconfigured mathematical models and flag correlation deviations as anomalies. Due to the number of anomalies detected at a given NPP on a daily basis, a significant number of flagged anomalies usually await examination for days or weeks. A primary cause of this backlog is that the methods used by the tools generate many false positives. Though this is usually attributed to oversensitive model settings due to very narrow normal operation bands, it can also be associated with the model development being inadequate for the process being monitored, or with missing model inputs that could have explained misclassified positives. The performance of anomaly detection tools impacts their plant acceptance and utilization, especially when the effort to address false positives generated by the tool depletes the value or cost saved by using that tool. Thus, means to advance anomaly detection performance have been investigated by the Department of Energy’s Light Water Reactor Sustainability program. Previous and ongoing efforts have targeted unsupervised machine-learning (ML) methods, which do not require the labeling of any data fed into the ML model. By contrast, in supervised anomaly detection methods, every data point is labeled as either a normal or abnormal process condition, and the model is trained to replicate the classification process. Supervised methods usually outperform unsupervised methods, due to the added value in differentiating normal from anomalous states of the monitored process. An NPP’s corrective action program requires it to track and document, via a dedicated report, the resolution of any issues that occur within the plant. Once created, each report is reviewed by a plant screening committee, and several classifications and decisions are made. Recently, a collaborating NPP developed an artificial intelligence and ML-based classifier to categorize a condition report (CR) into classes that can serve to label the data as normal or anomalous. Applying CRs as labels represents a semi-supervised use case. Semi-supervised ML assumes that labels exist for some data points (i.e., labeled anomalies, in this case) but not for the rest. In this effort, semi-supervised ML methods were used to fuse data from CRs with anomaly detection methods in order to test the hypothesis that partially labeled anomalies would improve the accuracy of the anomaly detection methods. Specifically, two methods were used. The first is the deep Semi-supervised Anomaly Detection (deep SAD) method, which can handle labels ranging from fully unsupervised to fully supervised cases. The second is a newly designed ML method developed specifically for this effort and referred to as the high-order feature (HOF)-based method. To evaluate these two methods in controlled environments, synthetic data generators were developed and used. The first datasets used a spring-mass-damper (SMD) system simulator commonly found in mechanical engineering references. This was used to create two use cases: a one- and a three-mass system. Anomalies were introduced by changing the spring and damper coefficients while the system was actuated by random forces. The second datasets used the commercial Dymola-Modelica software to build a simplified nuclear reactor model. Anomalies were added in the form of corrupted sensor readings and/or control commands. The deep SAD method was tested using the SMD system, while the HOF method was tested using both datasets. Application of the deep SAD semi-supervised ML method demonstrated that labels can generate increased confidence in detecting true anomalies. This helped increase the number of true positives and decrease the number of false negatives—something that would aid in addressing the backlog of possible anomalies. Application of the HOF method demonstrated that labels can aid in down selecting from a candidate set of features to a more optimal subset in order to better differentiate between normal and anomalous conditions.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Comparison of metagenomes from fermentation of various agroindustrial residues suggests a common model of community organization

The liquid residue resulting from various agroindustrial processes is both rich in organic material and an attractive source to produce a variety of chemicals. Using microbial communities to produce chemicals from these liquid residues is an active area of research, but it is unclear how to deploy microbial communities to produce specific products from the different agroindustrial residues. To address this, we fed anaerobic bioreactors one of several agroindustrial residues (carbohydrate-rich lignocellulosic fermentation conversion residue, xylose, dairy manure hydrolysate, ultra-filtered milk permeate, and thin stillage from a starch bioethanol plant) and inoculated them with a microbial community from an acid-phase digester operated at the wastewater treatment plant in Madison, WI, United States. The bioreactors were monitored over a period of months and sampled to assess microbial community composition and extracellular fermentation products. We obtained metagenome assembled genomes (MAGs) from the microbial communities in each bioreactor and performed comparative genomic analyses to identify common microorganisms, as well as any community members that were unique to each reactor. Collectively, we obtained a dataset of 217 non-redundant MAGs from these bioreactors. This metagenome assembled genome dataset was used to evaluate whether a specific microbial ecology model in which medium chain fatty acids (MCFAs) are simultaneously produced from intermediate products (e.g., lactic acid) and carbohydrates could be applicable to all fermentation systems, regardless of the feedstock. MAGs were classified using a multiclass classification machine learning algorithm into three groups, organisms fermenting the carbohydrates to intermediate products, organisms utilizing the intermediate products to produce MCFAs, and organisms producing MCFAs directly from carbohydrates. This analysis revealed common biological functions among the microbial communities in different bioreactors, and although different microorganisms were enriched depending on the agroindustrial residue tested, the results supported the conclusion that the microbial ecology model tested was appropriate to explain the MCFA production potential from all agricultural residues.

60 APPLIED LIFE SCIENCES↗

Improving Low‐Cloud Fraction Prediction Through Machine Learning

Abstract In this study, we evaluated the performance of machine learning (ML) models (XGBoost) in predicting low‐cloud fraction (LCF), compared to two generations of the community atmospheric model (CAM5 and CAM6) and ERA5 reanalysis data, each having a different cloud scheme. ML models show a substantial enhancement in predicting LCF regarding root mean squared errors and correlation coefficients. The good performance is consistent across the full spectrums of atmospheric stability and large‐scale vertical velocity. Employing an explainable ML approach, we revealed the importance of including the amount of available moisture in ML models for representing spatiotemporal variations in LCF in the midlatitudes. Also, ML models demonstrated marked improvement in capturing the LCF variations during the stratocumulus‐to‐cumulus transition (SCT). This study suggests ML models' great potential to address the longstanding issues of “too few” low clouds and “too rapid” SCT in global climate models.

Geology↗

Recent developments in the PySCF program package

PySCF is a Python-based general-purpose electronic structure platform that supports first-principles simulations of molecules and solids as well as accelerates the development of new methodology and complex computational workflows. Here, we explain the design and philosophy behind PySCF that enables it to meet these twin objectives. With several case studies, we show how users can easily implement their own methods using PySCF as a development environment. We then summarize the capabilities of PySCF for molecular and solid-state simulations. Finally, we describe the growing ecosystem of projects that use PySCF across the domains of quantum chemistry, materials science, machine learning, and quantum information science.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Thinking Bayesian for plasma physicists

Bayesian statistics offers a powerful technique for plasma physicists to infer knowledge from the heterogeneous data types encountered. To explain this power, a simple example, Gaussian Process Regression, and the application of Bayesian statistics to inverse problems are explained. The likelihood is the key distribution because it contains the data model, or theoretic predictions, of the desired quantities. By using prior knowledge, the distribution of the inferred quantities of interest based on the data given can be inferred. Because it is a distribution of inferred quantities given the data and not a single prediction, uncertainty quantification is a natural consequence of Bayesian statistics. The benefits of machine learning in developing surrogate models for solving inverse problems are discussed, as well as progress in quantitatively understanding the errors that such a model introduces.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Resonant Vibrations Resulting from the Re-Engineering of a Constant-Speed 2-Bladed Turbine to a Variable-Speed 3-Bladed Turbine

The CART3 (Controls Advanced Research Turbine, 3-bladed) at the National Wind Technology Center has recently been converted from a 2-bladed constant speed machine to a 3-bladed variable speed machine designed specically for controls research. The purpose of this conversion was to develop an advanced controls field-testing platform which has the more typical 3-bladed configuration. A result ofthis conversion was the emergence of several resonant vibrations, some of which initially prevented operation of the turbine until they could be explained and resolved. In this paper, the investigations into these vibrations are presented as 'lessons-learned'. Additionally, a frequency-domain technique called waterfall plotting is discussed and its usefulness in this research is illustrated.

17 WIND ENERGY↗

Quantifying Drivers of Methane Hydrobiogeochemistry in a Tidal River Floodplain System

The influence of coastal ecosystems on global greenhouse gas (GHG) budgets and their response to increasing inundation and salinization remains poorly constrained. In this study, we have integrated an uncertainty quantification (UQ) and ensemble machine learning (ML) framework to identify and rank the most influential processes, properties, and conditions controlling methane behavior in a freshwater floodplain responding to recently restored seawater inundation. Our unique multivariate, multiyear, and multi-site dataset comprises tidal creek and floodplain porewater observations encompassing water level, salinity, pH, temperature, dissolved oxygen (DO), dissolved organic carbon (DOC), total dissolved nitrogen (TDN), partial pressure of carbon dioxide (pCO 2 ), nitrous oxide (pN 2 O), methane (pCH 4 ), and the stable isotopic composition of methane (δ 13 CH 4 ). Additionally, we incorporated topographical data, soil porosity, hydraulic conductivity, and water retention parameters for UQ analysis using a previously developed 3D variably saturated flow and transport floodplain model for a physical mechanistic understanding of factors influencing groundwater levels and salinity and, therefore, CH 4 . Principal component analysis revealed that groundwater level and salinity are the most significant predictors of overall biogeochemical variability. The ensemble ML models and UQ analyses identified DO, water level, salinity, and temperature as the most influential factors for porewater methane levels and indicated that approximately 80% of the total variability in hourly water levels and around 60% of the total variability in hourly salinity can be explained by permeability, creek water level, and two van Genuchten water retention function parameters: the air-entry suction parameter α and the pore size distribution parameter m. These findings provide insights on the physicochemical factors in methane behavior in coastal ecosystems and their representation in local- to global-scale Earth system models.

54 ENVIRONMENTAL SCIENCES↗

Semi-supervised Bayesian Low-shot Learning

Deep neural networks (NNs) typically outperform traditional machine learning (ML) approaches for complicated, non-linear tasks. It is expected that deep learning (DL) should offer superior performance for the important non-proliferation task of predicting explosive device configuration based upon observed optical signature, a task which human experts struggle with. However, supervised machine learning is difficult to apply in this mission space because most recorded signatures are not associated with the corresponding device description, or “truth labels.” This is challenging for NNs, which traditionally require many samples for strong performance. Semi-supervised learning (SSL), low-shot learning (LSL), and uncertainty quantification (UQ) for NNs are emerging approaches that could bridge the mission gaps of few labels and rare samples of importance. NN explainability techniques are important in gaining insight into the inferential feature importance of such a complex model. In this work, SSL, LSL, and UQ are merged into a single framework, a significant technical hurdle not previously demonstrated. Exponential Average Adversarial Training (EAAT) and Pairwise Neural Networks (PNNs) are chosen as the SSL and LSL methods of choice. Permutation feature importance (PFI) for functional data is used to provide explainability via the Variable importance Explainable Elastic Shape Analysis (VEESA) pipeline. A variety of uncertainty quantification approaches are explored: Bayesian Neural Networks (BNNs), ensemble methods, concrete dropout, and evidential deep learning. Two final approaches, one utilizing ensemble methods and one utilizing evidential learning, are constructed and compared using a well-quantified synthetic 2D dataset along with the DIRSIG Megascene.

97 MATHEMATICS AND COMPUTING↗

Virtual Assistant for First Responders Using Natural Language Understanding and Optical Character Recognition

Commercial deep learning capabilities are available for many applications such as computer vision processing and intelligent chat bots. The Google Cloud Platform product Google Dialogflow provides lifelike conversational artificial intelligence (AI) using machine learning (ML) to generate natural conversations between computers and humans. This ML utilizes natural language understanding (NLU) to recognize a user’s intent and extracts key information into a form of entities. We have developed a user-friendly application through understanding the hazardous material database, first aid safety guidelines and observing the process of first responders who access this information in the field. We created the Trusted and Explainable Artificial Intelligence for Saving Lives (TruePAL) virtual assistant using Dialogflow1 and TensorFlow2 paired with EasyOCR.3 The chatbot supports first responders by providing voice interaction which helps limit additional steps such as browsing through multiple categories when searching for information. Using feedback from our field interviews, the voice interface has been developed to enable the first responder to focus on the immediate emergency. With less distractions, the first responder is able to engage the incident more effectively. The partial hands-free TruePAL chatbot assistant improves the accessibility to the correct guidance by an average of 1.9 seconds compared to the widely used application, NIH WISER, which requires full attention to operate. We combined this intelligent chatbot with a separate visual processing capability to produce hazardous signage analysis and generate the proper guidance for first responders. With the evolving functionality of AI tools, the use of virtual assistants in first responder technology will be an advancement, benefiting the safety of both first responders and civilians.

Chow, Edward↗

A machine-learning apprentice for the completion of repetitive forms

Forms of all types are used in businesses and government agencies, and most of them are filled in by hand. Yet much time and effort has been expended to automate form-filling by programming specific systems or computers. The high cost of programmers and other resources prohibits many organizations from benefiting from efficient office automation. A learning apprentice can be used for such repetitious form-filling tasks. In this paper, we establish the need for learning apprentices, describe a framework for such a system, explain the difficulties of form-filling, and present empirical results of a form-filling system used in our department from September 1991 to April 1992. The form-filling apprentice saves up to 87 percent in keystroke effort and correctly predicts nearly 90 percent of the values on the form.

Hermens, Leonard A.↗

Phase Diagram of a Deep Potential Water Model

Using the Deep Potential methodology, we construct a model that reproduces accurately the potential energy surface of the SCAN approximation of density functional theory for water, from low temperature and pressure to about 2400 K and 50 GPa, excluding the vapor stability region. The computational efficiency of the model makes it possible to predict its phase diagram using molecular dynamics. Satisfactory overall agreement with experimental results is obtained. Here, the fluid phases, molecular and ionic, and all the stable ice polymorphs, ordered and disordered, are predicted correctly, with the exception of ice III and XV that are stable in experiments, but metastable in the model. The evolution of the atomic dynamics upon heating, as ice VII transforms first into ice VII" and then into an ionic fluid, reveals that molecular dissociation and breaking of the ice rules coexist with strong covalent fluctuations, explaining why only partial ionization was inferred in experiments.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Model-free estimation of completeness, uncertainties, and outliers in atomistic machine learning using information theory

Abstract An accurate description of information is relevant for a range of problems in atomistic machine learning (ML), such as crafting training sets, performing uncertainty quantification (UQ), or extracting physical insights from large datasets. However, atomistic ML often relies on unsupervised learning or model predictions to analyze information contents from simulation or training data. Here, we introduce a theoretical framework that provides a rigorous, model-free tool to quantify information contents in atomistic simulations. We demonstrate that the information entropy of a distribution of atom-centered environments explains known heuristics in ML potential developments, from training set sizes to dataset optimality. Using this tool, we propose a model-free UQ method that reliably predicts epistemic uncertainty and detects out-of-distribution samples, including rare events in systems such as nucleation. This method provides a general tool for data-driven atomistic modeling and combines efforts in ML, simulations, and physical explainability.

36 MATERIALS SCIENCE↗

Ion correlations explain kinetic selectivity in diffusion-limited solid-state synthesis reactions

Establishing viable solid-state synthesis pathways for novel inorganic materials remains a major challenge in materials science. Previous pathway design methods using pairwise reaction approaches have navigated the thermodynamic landscape with first-principles data but lack kinetic information, limiting their effectiveness. This gap leads to suboptimal precursor selection and predictions, especially for reactions forming competing phases with similar formation energies, where ion diffusion is a critical influence. Here we demonstrate an inorganic synthesis framework by incorporating machine learning-derived transport properties through ‘liquid-like’ product layers into a thermodynamic cellular reaction model. In the Ba–Ti–O system, known for its competitive polymorphism, we obtain accurate predictions of phase formation with varying BaO:TiO2 ratios as a function of time and temperature. We find that diffusion–thermodynamics interplay governs phase compositions, with cross-ion transport coefficients critical for predicting diffusion-limited selectivity. This work bridges length scales and timescales by integrating solid-state reaction kinetics with first-principles thermodynamics and spatial reactivity.

Atomistic models↗

Regressing Nuclear Reactor Power Level Using Low-Cost Sensor Network Data

Multisensor networks deployed at nuclear facilities can be leveraged to collect data used as inputs to machine learning models predicting nuclear safeguard relevant information. This work demonstrates an application of this idea by regressing nuclear reactor power levels, a key indicator for nuclear safeguard verification, at the McClellan Nuclear Research Center using data collected by five Merlyn multisensor platforms with LASSO and LSTM models. This work also demonstrates the use of Leave One Node Out to measure the importance of each multisensor for this regression problem providing insight into model explainability and allowing inferential hypotheses about the nuclear facility to be made. This work can be used as a starting point for future development of methods for regression on reactor power levels at nuclear facilities using multisensor network data.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗