Search NASA⌕ Search

SEARCH · Search NASA

Results for “Domain knowledge”

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 127 records · Page 7

SANE: strategic autonomous non-smooth exploration for multiple optima discovery in multi-modal and non-differentiable black-box functions

Both computational and experimental material discovery bring forth the challenge of exploring multidimensional and multimodal parameter spaces, such as phase diagrams of Hamiltonians with multiple interactions, composition spaces of combinatorial libraries, material structure image spaces, and molecular embedding spaces. Often these systems are black-boxes and time-consuming to evaluate, which resulted in strong interest towards active learning methods such as Bayesian optimization (BO). However, these systems are often noisy which make the black box function severely multi-modal and non-differentiable, where a vanilla BO can get overly focused near a single or faux optimum, deviating from the broader goal of scientific discovery. To address these limitations, here we developed Strategic Autonomous Non-Smooth Exploration (SANE) to facilitate an intelligent Bayesian optimized navigation with a proposed cost-driven probabilistic acquisition function to find multiple global and local optimal regions, avoiding the tendency to becoming trapped in a single optimum. To distinguish between a true and false optimal region due to noisy experimental measurements, a human (domain) knowledge driven dynamic surrogate gate is integrated with SANE. We implemented the gate-SANE into pre-acquired piezoresponse spectroscopy data of a ferroelectric combinatorial library with high noise levels in specific regions, and piezoresponse force microscopy (PFM) hyperspectral data. SANE demonstrated better performance than classical BO to facilitate the exploration of multiple optimal regions and thereby prioritized learning with higher coverage of scientific values in autonomous experiments. Our work showcases the potential application of this method to real-world experiments, where such combined strategic and human intervening approaches can be critical to unlocking new discoveries in autonomous research.

Biswas, Arpan [University of Tennessee, Knoxville,↗

Synergy of semiempirical models and machine learning in computational chemistry

Catalyzed by enormous success in the industrial sector, many research programs have been exploring data-driven, machine learning approaches. Performance can be poor when the model is extrapolated to new regions of chemical space, e.g., new bonding types, new many-body interactions. Another important limitation is the spatial locality assumption in model architecture, and this limitation cannot be overcome with larger or more diverse datasets. The outlined challenges are primarily associated with the lack of electronic structure information in surrogate models such as interatomic potentials. Given the fast development of machine learning and computational chemistry methods, we expect some limitations of surrogate models to be addressed in the near future; nevertheless spatial locality assumption will likely remain a limiting factor for their transferability. Here, we suggest focusing on an equally important effort—design of physics-informed models that leverage the domain knowledge and employ machine learning only as a corrective tool. In the context of material science, we will focus on semi-empirical quantum mechanics, using machine learning to predict corrections to the reduced-order Hamiltonian model parameters. The resulting models are broadly applicable, retain the speed of semiempirical chemistry, and frequently achieve accuracy on par with much more expensive ab initio calculations. These early results indicate that future work, in which machine learning and quantum chemistry methods are developed jointly, may provide the best of all worlds for chemistry applications that demand both high accuracy and high numerical efficiency.

36 MATERIALS SCIENCE↗

Reinforcement Learning for Anomaly Detection in Nuclear Power Plant Operation and Maintenance

In nuclear power plants (NPPs), timely identification of sensor and human errors is critical to ensure safe and efficient plant operations. Anomaly detection models can be employed for this task. However, traditional anomaly detection approaches may have high dependency on labeled datasets and struggle with adaptability in complex, dynamic environments. Reinforcement learning (RL) has demonstrated significant potential in fault diagnosis and anomaly detection; however, its application to anomaly detection in NPPs remains a relatively underexplored research direction. Hence, to address this gap, in this study, we present a novel physics-informed reinforcement learning model, PIRL-AD: Physics-Informed Reinforcement Learning for Anomaly Detection, that integrates domain knowledge from calorimetric equations into the RL framework for enhanced sensor and human error anomaly detection. We evaluate the performance of PIRL-AD against a non-physics informed RL benchmark and a support vector machine (SVM) on data collected from a forced flow loop testbed. Experimental results suggest that PIRL-AD outperforms other baselines on a range of anomalous datasets that include both sensor and human-induced anomalies across key performance metrics, statistically outperforming the RL and SVM benchmarks with respect to geometric mean (respectively, 92.96% vs. 91.06% vs. 83.01%) and F1-score (respectively, 89.23% vs. 86.98% vs. 77.01%). Furthermore, the findings suggest the potential of physics-integrated reinforcement learning models for enhanced anomaly detection performance in NPPs.

Reinforcement learning↗

Explaining System-Level Prognostics with Established Machine Learning Methods

System-level prognostics is crucial for ensuring reliability and enabling predictive maintenance in complex systems with interconnected components. This study presents a framework that integrates data-driven methods to predict the remaining useful life (RUL) of a subsystem under multiple and concurrent faults within a nuclear power plant system with explainable artificial intelligence (XAI). A nuclear power plant (NPP) operation was simulated to model the degradation behavior of NPP components, and four machine learning models—Gradient Boosting Regressor (GBR), Support Vector Regressor (SVR), Fully Connected Neural Network (FCNN), and Long Short-Term Memory (LSTM)—were evaluated for prognostics with a novel system RUL parameter. The LSTM model demonstrated potential superior repeatability, while SHAP (SHapley Additive exPlanations) for explainability provided consistent and trustworthy global explanations. In contrast, LIME (Local Interpretable Model-agnostic Explanations) offered localized interpretability but showed reduced stability for sequential data. Key findings include the interplay between component-level degradation and system-wide performance, with LSTM effectively capturing these dynamics through sequence-level predictions. The XAI techniques enhanced transparency by identifying critical features influencing model predictions and aligning with domain knowledge. Furthermore, this framework has significant implications for improving trust and understanding in predictive maintenance, particularly in safety-critical industries like nuclear energy.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

A Graphical Approach to Diagnosing the Validity of the Conditional Independence Assumptions of a Bayesian Network Given Data

Bayesian networks have attained widespread use in data analysis and decision making. Well studied topics include: efficient inference, evidence propagation, parameter learning from data for complete and incomplete data scenarios, expert elicitation for calibrating Bayesian network probabilities, and structure learning. It is not uncommon for the researcher to assume the structure of the Bayesian network or to glean the structure from expert elicitation or domain knowledge. In this scenario, the model may be calibrated through learning the parameters from relevant data. There is a lack of work on model diagnostics for fitted Bayesian networks; this is the contribution of this paper. We key on the definition of (conditional) independence to develop a graphical diagnostic method which indicates if the conditional independence assumptions imposed when one assumes the structure of the Bayesian network are supported by the data. We develop the approach theoretically and describe a Monte Carlo method to generate uncertainty measures for the consistency of the data with conditional independence assumptions under the model structure. We describe how this theoretical information and the data are presented in a graphical diagnostic tool. We demonstrate the approach through data simulated from Bayesian networks under different conditional independence assumptions. We also apply the diagnostic to a real world data set. The results indicate that our approach is a reasonable way of visualizing and inspecting the conditional independence assumption of a Bayesian network given data.

Bayesian Networks · Structural Model Diagnostics ·↗

NONPARAMETRIC BAYESIAN ESTIMATION OF PERIODIC LIGHT CURVES

Many astronomical phenomena exhibit patterns that have periodic behavior. An important step when analyzing data from such processes is the problem of identifying the period: estimating the period of a periodic function based on noisy observations made at irregularly spaced time points. This problem is still a difficult challenge despite extensive study in different disciplines. This paper makes several contributions toward solving this problem. First, we present a nonparametric Bayesian model for period finding, based on Gaussian Processes (GPs), that does not make assumptions on the shape of the periodic function. As our experiments demonstrate, the new model leads to significantly better results in period estimation especially when the light curve does not exhibit sinusoidal shape. Second, we develop a new algorithm for parameter optimization for GP which is useful when the likelihood function is very sensitive to the parameters with numerous local minima, as in the case of period estimation. The algorithm combines gradient optimization with grid search and incorporates several mechanisms to overcome the high computational complexity of GP. Third, we develop a novel approach for using domain knowledge, in the form of a probabilistic generative model, and incorporate it into the period estimation algorithm. Experimental results validate our approach showing significant improvement over existing methods.

79 ASTRONOMY AND ASTROPHYSICS↗

Augmented signal processing in Liquid Argon Time Projection Chambers with a deep neural network

The Liquid Argon Time Projection Chamber (LArTPC) is an advanced neutrino detector technology widely used in recent and upcoming accelerator neutrino experiments. It features a low energy threshold and high spatial resolution that allow for comprehensive reconstruction of event topologies. In current-generation LArTPCs, the recorded data consist of digitized waveforms on wires produced by induced signal on wires of drifting ionization electrons, which can also be viewed as two-dimensional (2D) (time versus wire) projection images of charged-particle trajectories. For such an imaging detector, one critical step is the signal processing that reconstructs the original charge projections from the recorded 2D images. For the first time, we introduce a deep neural network in LArTPC signal processing to improve the signal region of interest detection. By combining domain knowledge (e.g., matching information from multiple wire planes) and deep learning, this method shows significant improvements over traditional methods. This work details the method, software tools, and performance evaluated with realistic detector simulations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Architecture for interoperable software in biology

Understanding biological complexity demands a combination of high-throughput data and interdisciplinary skills. One way to bring to bear the necessary combination of data types and expertise is by encapsulating domain knowledge in software and composing that software to create a customized data analysis environment. To this end, simple flexible strategies are needed for interconnecting heterogeneous software tools and enabling data exchange between them. Drawing on our own work and that of others, we present several strategies for interoperability and their consequences, in particular, a set of simple data structures—list, matrix, network, table and tuple—that have proven sufficient to achieve a high degree of interoperability. We provide a few guidelines for the development of future software that will function as part of an interoperable community of software tools for biological data analysis and visualization.

59 BASIC BIOLOGICAL SCIENCES↗

Square Kilometre Array Science Data Challenge 1: analysis and results

ABSTRACT As the largest radio telescope in the world, the Square Kilometre Array (SKA) will lead the next generation of radio astronomy. The feats of engineering required to construct the telescope array will be matched only by the techniques developed to exploit the rich scientific value of the data. To drive forward the development of efficient and accurate analysis methods, we are designing a series of data challenges that will provide the scientific community with high-quality data sets for testing and evaluating new techniques. In this paper, we present a description and results from the first such Science Data Challenge 1 (SDC1). Based on SKA MID continuum simulated observations and covering three frequencies (560, 1400, and 9200 MHz) at three depths (8, 100, and 1000 h), SDC1 asked participants to apply source detection, characterization, and classification methods to simulated data. The challenge opened in 2018 November, with nine teams submitting results by the deadline of 2019 April. In this work, we analyse the results for eight of those teams, showcasing the variety of approaches that can be successfully used to find, characterize, and classify sources in a deep, crowded field. The results also demonstrate the importance of building domain knowledge and expertise on this kind of analysis to obtain the best performance. As high-resolution observations begin revealing the true complexity of the sky, one of the outstanding challenges emerging from this analysis is the ability to deal with highly resolved and complex sources as effectively as the unresolved source population.

Bonaldi, A.↗

Anomaly detection in the Zwicky Transient Facility DR3

We present results from applying the SNAD anomaly detection pipeline to the third public data release of the Zwicky Transient Facility (ZTF DR3). The pipeline is composed of three stages: feature extraction, search of outliers with machine learning algorithms, and anomaly identification with followup by human experts. Our analysis concentrates in three ZTF fields, comprising more than 2.25 million objects. A set of four automatic learning algorithms was used to identify 277 outliers, which were subsequently scrutinized by an expert. From these, 188 (68 per cent) were found to be bogus light curves – including effects from the image subtraction pipeline as well as overlapping between a star and a known asteroid, 66 (24 per cent) were previously reported sources whereas 23 (8 per cent) correspond to non-catalogued objects, with the two latter cases of potential scientific interest (e.g. one spectroscopically confirmed RS Canum Venaticorum star, four supernovae candidates, one red dwarf flare). Moreover, using results from the expert analysis, we were able to identify a simple bi-dimensional relation that can be used to aid filtering potentially bogus light curves in future studies. We provide a complete list of objects with potential scientific application so they can be further scrutinised by the community. These results confirm the importance of combining automatic machine learning algorithms with domain knowledge in the construction of recommendation systems for astronomy. Our code is publicly available.

79 ASTRONOMY AND ASTROPHYSICS↗

Machine learning of Kondo physics using variational autoencoders and symbolic regression

In this work, we employ variational autoencoders to extract physical insight from a dataset of one-particle Anderson impurity model spectral functions. Autoencoders are trained to find a low-dimensional, latent space representation that faithfully characterizes each element of the training set, as measured by a reconstruction error. Variational autoencoders, a probabilistic generalization of standard autoencoders, further condition the learned latent space to promote highly interpretable features. In our study, we find that the learned latent variables strongly correlate with well known, but nontrivial, parameters that characterize emergent behaviors in the Anderson impurity model. In particular, one latent variable correlates with particle-hole asymmetry, while another is in near one-to-one correspondence with the Kondo temperature, a dynamically generated low-energy scale in the impurity model. Using symbolic regression, we model this variable as a function of the known bare physical input parameters and "rediscover" the nonperturbative formula for the Kondo temperature. The machine learning pipeline we develop suggests a general purpose approach, which opens opportunities to discover new domain knowledge in other physical systems.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

ROI-Finder : machine learning to guide region-of-interest scanning for X-ray fluorescence microscopy

The microscopy research at the Bionanoprobe (currently at beamline 9-ID and later 2-ID after APS-U) of Argonne National Laboratory focuses on applying synchrotron X-ray fluorescence (XRF) techniques to obtain trace elemental mappings of cryogenic biological samples to gain insights about their role in critical biological activities. The elemental mappings and the morphological aspects of the biological samples, in this instance, the bacterium Escherichia coli ( E. Coli ), also serve as label-free biological fingerprints to identify E. coli cells that have been treated differently. The key limitations of achieving good identification performance are the extraction of cells from raw XRF measurements via binary conversion, definition of features, noise floor and proportion of cells treated differently in the measurement. Automating cell extraction from raw XRF measurements across different types of chemical treatment and the implementation of machine-learning models to distinguish cells from the background and their differing treatments are described. Principal components are calculated from domain knowledge specific features and clustered to distinguish healthy and poisoned cells from the background without manual annotation. The cells are ranked via fuzzy clustering to recommend regions of interest for automated experimentation. The effects of dwell time and the amount of data required on the usability of the software are also discussed.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Cyber-attack detection and accommodation algorithm for energy delivery systems

Cyber-attack accommodation in a cyber-physical system is to ensure system operation, integrity and availability while maintaining a reasonable operational performance under attack. In this paper, we present a novel cyber-attack accommodation algorithm by estimating the true operational states of the system with new boundary & performance constrained resilient estimators while the system is continuously operating and is under attack. Our approach is based on combining data driven machine learning and physics based domain knowledge with traditional resilient estimation. The results were evaluated using a high fidelity model-based simulation environment.

97 MATHEMATICS AND COMPUTING↗

Shopping For Danger: E-commerce techniques applied to collaboration in cyber security

Collaboration among cyber security analysts is essential to a successful protection strategy on the Internet today, but it is uncommonly practiced or encouraged in operating environments. Barriers to productive collaboration often include data sensitivity, time and effort to communicate, institutional policy, and protection of domain knowledge. We propose an ambient collaboration framework, Vulcan, designed to remove the barriers of time and effort and mitigate the others. Vulcan automated data collection, collaborative filtering, and asynchronous dissemination, eliminating the effort implied by explicit collaboration among peers. We instrumented two analytic applications and performed a mock analysis session to build a dataset and test the output of the system.

99 GENERAL AND MISCELLANEOUS↗

Combining Tensor Decompositions and Graph Analytics to Provide Cyber Situational Awareness at HPC Scale

This paper describes MADHAT (Multidimensional Anomaly Detection fusing HPC, Analytics, and Tensors), an integrated workflow that demonstrates the applicability of HPC resources to the problem of maintaining cyber situational awareness. MADHAT combines two high-performance packages: ENSIGN for large-scale sparse tensor decompositions and HAGGLE for graph analytics. Tensor decompositions isolate coherent patterns of network behavior in ways that common clustering methods based on distance metrics cannot. Parallelized graph analysis then uses directed queries on a representation that combines the elements of identified patterns with other available information (such as additional log fields, domain knowledge, network topology, whitelists and blacklists, prior feedback, and published alerts) to confirm or reject a threat hypothesis, collect context, and raise alerts. MADHAT was developed using the collaborative HPC Architecture for Cyber Situational Awareness (HACSAW) research environment and evaluated on structured network sensor logs collected from Defense Research and Engineering Network (DREN) sites using HPC resources at the U.S. Army Engineer Research and Development Center DoD Supercomputing Resource Center (ERDC DSRC). To date, MADHAT has analyzed logs with over 650 million entries.

Cyber security, Tensor decomposition, graph analyt↗

DOC-DICAM: Domain Aware One Class Defect Identification in Composite Aerostructure Material

Fiber-reinforced composites are a common material used in the design of aircraft structures due to their good tensile strength and resistance to compression. During the manufacturing process, these structures are thoroughly inspected for flaws and defects to ensure structural integrity during commercial use. Non-destructive testing (NDT) is a collection of inspection methods that allow inspectors to evaluate material without altering it. Due to the high safety standards in aerospace manufacturing, the NDT process is done manually and can be a significant bottleneck in the development workflow. In this paper, we develop an AI-based assistance tool to drastically reduce inspection time. Typical AI workflows require large amounts of annotated data, but defects rarely occur resulting in strong class imbalance. To overcome this, we formulate the problem of defect identification as an anomaly detection task in which our primary focus is learning non-defect characteristics. To do this, we develop a multi-task self-supervised learning framework that embeds problem specific domain knowledge into the deep learning model. We verify our method using fuselage data generated in a production environment. As a result, we show that our method can effectively identify defects and requires minimal training and inference time.

anomaly detection↗

Feature Tracking and Visualization of Madden-Julian Osciallation in Climate Simulation

Madden-Julian Oscillation (MJO) is one of the less understood aspects of tropical meteorology, which plays a significant role in tropical intra-seasonal variations in rain, temperature and winds over the Indian and Pacific Oceans. In this paper, we present an integrated analysis and visualization framework for MJO episodes simulated by a high resolution regional model. To distinguish MJOs from other weather phenomena, our framework utilizes domain knowledge to track MJOs as finding the globally optimized properties in the data. In addition to enhancing the animation with feature tracking, our visualization system also integrates different visualization components such as Virtual Globe and Hovmoller Diagrams to visualize large scale events both in space and time. By linking all of these visualization components on a web-based interface, scientists can identify cloud and environmental processes associated with the initiation and eastward propagation of MJO more easily.

big-data visualization↗