SEARCH · Search NASA
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.
SAND2022-1748 O Romans is a library for implementing compression-based machine learning algorithms and algorithms for Human Constrained Machine Learning. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
The research team developed models of Attentional Control (AC) that are unique to existing modeling approaches in the literature. The goal was to enable the research team to (1) make predictions about AC and human performance in real-world scenarios and (2) to make predictions about individual characteristics based on human data. First, the team developed a proof-of-concept approach for representing an experimental design and human subjects data in a Bayesian model, then demonstrated an ability to draw inferences about conditions of interest relevant to real-world scenarios. Ultimately, this effort was successful, and we were able to make reasonable (meaning supported by behavioral data) inferences about conditions of interest to develop a risk model for AC (where risk is defined as a mismatch between AC and attentional demand). The team additionally defined a path forward for a human-constrained machine learning (HCML) approach to make predictions about an individual's state based on performance data. The effort represents a successful first step in both modeling efforts and serves as a basis for future work activities. Numerous opportunities for future work have been defined.
Recent improvements in natural language processing (NLP) enable metadata to be created programmatically from reused original metadata or even the dataset itself. Transfer-learning applied to NLP has greatly improved performance and reduced training data requirements. In this talk, we’ll compare machine-generated metadata to human-generated metadata and discuss characteristics of metadata and data archives that affect suitability for machine-learning reuse of metadata. Where as human-generated metadata is often populated once, populated from the perspective of data supplier, populated by many individuals with different words for the same thing, and limited in length, machine-generated metadata can be updated any number of times, generated from the perspective of any user, constrained to a standardized set of terms that can be evolved over time, and be any length required. Machine-learning generated metadata offers benefits but also additional needs in terms of version control, process transparency, human-computer interaction, and IT requirements. As a successful example, we’ll discuss how a dataset of abstracts and associated human-tagged keywords from a standardized list of several thousand keywords were used to create a machine-learning model that predicted keyword metadata for open-source code projects on code.nasa.gov. We’ll also discuss a less successful example from data.nasa.gov to show how data archive architecture and characteristics of initial metadata can be strong controls on how easy it is to leverage programmatic methods to reuse metadata to create additional metadata.
Volume of distribution at steady state (V D,ss ) is one of the key pharmacokinetic parameters estimated during the drug discovery process. Despite considerable efforts to predict V D,ss , accuracy and choice of prediction methods remain a challenge, with evaluations constrained to a small set (<150) of compounds. To address these issues, a series of in silico methods for predicting human V D,ss directly from structure were evaluated using a large set of clinical compounds. Machine learning (ML) models were built to predict V D,ss directly and to predict input parameters required for mechanistic and empirical V D,ss predictions. In addition, log D, fraction unbound in plasma (fup), and blood-to-plasma partition ratio (BPR) were measured on 254 compounds to estimate the impact of measured data on predictive performance of mechanistic models. Furthermore, the impact of novel methodologies such as measuring partition (Kp) in adipocytes and myocytes (n = 189) on V D,ss predictions was also investigated. In predicting V D,ss directly from chemical structures, both mechanistic and empirical scaling using a combination of predicted rat and dog V D,ss demonstrated comparable performance (62%–71% within 3-fold). The direct ML model outperformed other in silico methods (75% within 3-fold, r 2 = 0.5, AAFE = 2.2) when built from a larger data set. Scaling to human from predicted V D,ss of either rat or dog yielded poor results (<47% within 3-fold). Measured fup and BPR improved performance of mechanistic V D,ss predictions significantly (81% within 3-fold, r 2 = 0.6, AAFE = 2.0). Adipocyte intracellular Kp showed good correlation to the V D,ss but was limited in estimating the compounds with low V D,ss .
We report the design/discovery of new materials is highly nontrivial owing to the near-infinite possibilities of material candidates and multiple required property/performance objectives. Thus, machine learning tools are now commonly employed to virtually screen material candidates with desired properties by learning a theoretical mapping from material-to-property space, referred to as the forward problem. However, this approach is inefficient and severely constrained by the candidates that the human imagination can conceive. Thus, in this work on polymers, we tackle the materials discovery challenge by solving the inverse problem: directly generating candidates that satisfy desired property/performance objectives. We utilize syntax-directed variational autoencoders (VAE) in tandem with Gaussian process regression (GPR) models to discover polymers expected to be robust under three extreme conditions: (1) high temperatures, (2) high electric field, and (3) high temperature and high electric field, useful for critical structural, electrical, and energy storage applications. This approach to learn from and augment) human ingenuity is general and can be extended to discover polymers with other targeted properties and performance measures.
Machine learning techniques have received growing attention as an alternative strategy for developing general-purpose density functional approximations, augmenting the historically successful approach of human-designed functionals derived to obey mathematical constraints known for the exact exchange-correlation functional. More recently, efforts have been made to reconcile the two techniques, integrating machine learning and exact-constraint satisfaction. We continue this integrated approach, designing a deep neural network that exploits the exact constraint and appropriate norm philosophy to de-orbitalize the strongly constrained and appropriately normed (SCAN) functional. The deep neural network is trained to replicate the SCAN functional from only electron density and local derivative information, avoiding the use of the orbital-dependent kinetic energy density. The performance and transferability of the machine-learned functional are demonstrated for molecular and periodic systems.
Machine learning (ML) is transforming materials research, yet potential for biopolymer discovery remains constrained by fragmented data and nonstandardized reporting. Biopolymers differ significantly from synthetic polymers, requiring specialized approaches to represent their biosynthetic origins, hierarchical structures, and application-specific metrics. In this Perspective, we identify three core challenges limiting biopolymer representation: information encoding, data quality, and data sharing. We describe the most pressing issues and propose commensurate approaches to address each key challenge. Recommendations include the design and adoption of biopolymer-specific fingerprinting and representation frameworks, development of hybrid human-large language model (LLM) data extraction strategies, and expanding Findable, Accessible, Interoperable, Reusable (FAIR)-compliant repositories. We propose a robust foundation to define interoperable, high-quality data sets that capture the full context of biopolymer materials. Standardized metadata, shared ontologies, and community-driven infrastructure would enable scalable, reproducible workflows and accelerate the ML-driven development of biopolymers.
The fusion of experimental automation and machine learning has catalyzed a new era in materials research, prominently featuring Gaussian Process (GP) Bayesian Optimization (BO) driven autonomous experiments. Here we introduce a Dual-GP approach that enhances traditional GPBO by adding a secondary surrogate model to dynamically constrain the experimental space based on real-time assessments of the raw experimental data. This Dual-GP approach enhances the optimization efficiency of traditional GPBO by isolating more promising space for BO sampling and more valuable experimental data for primary GP training. We also incorporate a flexible, human-in-the-loop intervention method in the Dual-GP workflow to adjust for unanticipated results. We demonstrate the effectiveness of the Dual-GP model with synthetic model data and implement this approach in autonomous pulsed laser deposition experimental data. This Dual-GP approach has broad applicability in diverse GPBO-driven experimental settings, providing a more adaptable and precise framework for refining autonomous experimentation for more efficient optimization.
Quantifying the radioactive sources present in gamma spectra is an ever-present and growing national security mission and a time-consuming process for human analysts. While machine learning models exist that are trained to estimate radioisotope proportions in gamma spectra, few address the eventual need to provide explanatory outputs beyond the estimation task. In this work, we develop two machine learning models for a NaI detector measurements: one to perform the estimation task, and the other to characterize the first model’s ability to provide reasonable estimates. To ensure the first model exhibits a behavior that can be characterized by the second model, the first model is trained using a custom, semi-supervised loss function which constrains proportion estimates to be explainable in terms of a spectral reconstruction. The second auxiliary model is an out-of-distribution detection function (a type of meta-model) leveraging the proportion estimates of the first model to identify when a spectrum is sufficiently unique from the training domain and thus is out-of-scope for the model. In demonstrating the efficacy of this approach, we encourage the use of meta-models to better explain ML outputs used in radiation detection and increase trust.
Over the last 15 years, compressive sensing techniques have been developed which have the potential to greatly reduce the amount of data collected by systems while preserving the amount of information obtained. A cost of this efficiency is that a computationally-intensive optimization routine must be used to put the sensed data into a form that a person can interpret. At the same time, machine learning techniques have experienced tremendous growth as well. Machines have demonstrated the ability learn how to effectively perform tasks such as detection and classification at speeds much faster than humanly possible. Our goal in this project was to study the feasibility of using compressive sensing systems "at the edge." That is, how can compressive sensing sensors be deployed such that information is created at the remote sensor rather than sending raw data to a central processing location? Studies were performed to analyze whether machine learning could be done on the compressively sensed data in its raw form. If a machine is performing the task, is it possible to do so without putting the data into a human interpretable form? We show that this is possible for some systems, in particular a compressive sensing snapshot imaging spectrometer. Machine learning tasks were demonstrated to be more effective and more robust to noise when the machine learning algorithm worked on data in its raw form. This system is shown to outperform a traditional spectrometer. Techniques for reducing the complexity of the reconstruction routine were also analyzed. Techniques for such as data regularization, deep neural networks, and matrix completion were studied and shown to have benefits over traditional reconstruction techniques. In this project we showed that compressive sensing sensors are indeed feasible at the edge. As always, sensors and algorithms must be carefully tuned to work in the constrained environment. In this project we developed tools and techniques to enable those analyses.
Clinical deep phenotyping and phenotype annotation play a critical role in both the diagnosis of patients with rare disorders as well as in building computationally-tractable knowledge in the rare disorders field. These processes rely on using ontology concepts, often from the Human Phenotype Ontology, in conjunction with a phenotype concept recognition task (supported usually by machine learning methods) to curate patient profiles or existing scientific literature. With the significant shift in the use of large language models (LLMs) for most NLP tasks, we examine the performance of the latest Generative Pre-trained Transformer (GPT) models underpinning ChatGPT as a foundation for the tasks of clinical phenotyping and phenotype annotation. The experimental setup of the study included seven prompts of various levels of specificity, two GPT models (gpt-3.5-turbo and gpt-4.0) and two established gold standard corpora for phenotype recognition, one consisting of publication abstracts and the other clinical observations. The best run, using in-context learning, achieved 0.58 document-level F1 score on publication abstracts and 0.75 document-level F1 score on clinical observations, as well as a mention-level F1 score of 0.7, which surpasses the current best in class tool. Without in-context learning, however, performance is significantly below the existing approaches. Our experiments show that gpt-4.0 surpasses the state of the art performance if the task is constrained to a subset of the target ontology where there is prior knowledge of the terms that are expected to be matched. While the results are promising, the non-deterministic nature of the outcomes, the high cost and the lack of concordance between different runs using the same prompt and input make the use of these LLMs challenging for this particular task.
Next Generation Air Transportation System (NextGen) has begun the modernization of the nation’s air transportation system (NAS), with goals to improve system safety, increase operation efficiency and capacity, provide enhanced predictability, resilience and robustness [1]. The overall objective of the Air Traffic Management-eXploration (ATM-X) project is to facilitate the goals of NextGen by conducting research to enable the growing demand of new, mission variant, air vehicles with safe access to the NAS. The implementation and utilization of new and burgeoning technologies that are both flexible, scalable, and systematically user-focused are requisite for ATM-X to achieve its intention of NAS safe entry [2]. Researchers from NASA Langley’s Flight Deck Integration Team have developed a system architecture that would allow ATM-X to leverage the necessary capabilities of an Increasingly Autonomous System (IAS), machine-agent that will promote the safe access and operation of air vehicles within what has become the byproduct of NextGen modernization, a Net-Centric airspace architecture and an Urban Air Mobility (UAM) community. Conducting flight operations within this type of architecture constrains the human-agent’s natural ability by data management. When the massive volume of data, its types, and the acquisition speed at which the data is ingested is observed it becomes evident that the human-agent will be functioning at an operational disadvantage. Therefore, the development and integration of intelligent machine-agents into the flight deck are a necessary implementation to achieve ATM-X overall objective of safe access and operation in the NAS.
Our understanding of water cycles on the Moon has significantly enhanced recent observations by Chang E-5, Lunar Prospector, and Chandrayaan-1 missions indicating the existence of an active water cycle on the Moon. In a new partnership between Delaware State University (DSU) and NASA Goddard Space Flight Center, enabled through the NASA’s M-STAR (MUREP Space Technology Artemis Research) program, we are developing low mass and power lunar rover payloads to enable long-duration human exploration missions. Payload technologies include wavelength modulation absorption spectroscopy to simultaneously detect water (H16OH) and isotopes (H16OD) in the (6700 nm) mid-infrared region using a closed path in compact Herriot cell optical design and wavelength modulation spectroscopy, and (2) Laser-induced breakdown spectroscopy (LIBS) to simultaneously detect and correlate water isotopes with characteristics elemental composition of lunar regolith. Due to the airless atmosphere of the Moon, we will utilize Artificial intelligence (AI) and Machine learning (ML) approaches to discriminate spectral interference with instrument drifts and correlate mid-IR trace gas profile with LIBS spectral information. This partnership will initiate a STEM engagement space program, e.g., Lander and CubeSat payload technology development for students and the next-generation NASA workforce for future lunar and Mars missions. DSU, a Historically Black University, prides itself in its proven excellence in teaching and research. It enrolls a diverse population of students (~5000) traditionally underrepresented in STEM disciplines. DSU has established itself at the forefront of optics and photonics research that transcends multidisciplinary fields of earth sciences, environmental, defense, and biomedical sensing applications.
Radiation exposure poses a significant threat to human health. Emerging research indicates that even low-dose radiation once believed to be safe, may have harmful effects. This perception has spurred a growing interest in investigating the potential risks associated with low-dose radiation exposure across various scenarios. To comprehensively explore the health consequences of low-dose radiation, our study employs a robust statistical framework that examines whether specific groups of genes, belonging to known pathways, exhibit coordinated expression patterns that align with the radiation levels. Notably, our findings reveal the existence of intricate yet consistent signatures that reflect the molecular response to radiation exposure, distinguishing between low-dose and high-dose radiation. Moreover, we leverage a pathway-constrained variational autoencoder to capture the nonlinear interactions within gene expression data. By comparing these two analytical approaches, our study aims to gain valuable insights into the impact of low-dose radiation on gene expression patterns, identify pathways that are differentially affected, and harness the potential of machine learning to uncover hidden activity within biological networks. This comparative analysis contributes to a deeper understanding of the molecular consequences of low-dose radiation exposure.
INTRODUCTION We use artificial neural networks (ANNs) as an example machine learning (ML) tool to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is attentional set-shifting (ATSET) test scores from a rodent model exposed to ≤15 cGy of individual galactic cosmic radiation (GCR) ions: 4He, 28Si, or 56Fe, expected for a Lunar or Mars mission [1]. This work investigates rats at a subject-based level and uses applied dose and performance scores taken before irradiation to predict whether a rat will be impaired when irradiated. The results of this study are significant to crewed space missions as they support the potential of predicting an astronaut’s impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. METHODS Data used in this work are scores from the ATSET, a multi-stage constrained cognitive flexibility test [2]. Our computational model utilizes the number of attempts to reach the criterion to pass a stage as a behavioral performance measure for rats. We use the post-irradiation scores, generate thresholds from cumulative distribution plots of non-irradiated rats, and calculate the percent of irradiated rats whose scores fall below the threshold to infer how each radiation type/dose affects a population. Rats scoring above the threshold are labeled impaired while the others are non-impaired. We then employ ANNs as a typical ML technique, and use each subject’s individual scores taken before radiation along with the applied dose, to predict their personal susceptibility to cognitive impairment due to space radiation exposure. RESULTS AND CONCLUSION A significant finding is the exhibition of a dose-dependent increasing probability of impairment for 1 to 10 cGy of 28Si or 56Fe in the simple discrimination (SD) stage of the ATSET, and for 1 to 10 cGy of 56Fe in the compound discrimination (CD) stage. On a subject-based level, implementing ML classifiers such as ANNs identifies rats that have a higher tendency for impairment after GCR exposure [1]. The receiver operating characteristic (ROC) and the precision-recall (PR) curves of the ML models show a better prediction of impairment when 56Fe is the ion in question in both SD (Figure 1) and CD stages. They, however, do not depict impairment due to 4He in SD (Figure 1) and 28Si in CD, suggesting no dose-dependent impairment response in these cases. In this work, “good” prediction pertains to “better-than-random-chance”, due to the limited sample size and the high inter- and intra-individual variabilities in response to brain stimulation paradigms, as applicable to both animals and humans. More behavioral tests and biomarkers should be investigated on the same subjects, to be fed to the ML models to capture the agents responsible for performance alterations of some individuals versus others.
INTRODUCTION We use artificial neural networks (ANNs) as an example machine learning (ML) tool to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is attentional set-shifting (ATSET) test scores from a rodent model exposed to ≤15 cGy of individual galactic cosmic radiation (GCR) ions: 4He, 28Si, or 56Fe, expected for a Lunar or Mars mission [1]. This work investigates rats at a subject-based level and uses applied dose and performance scores taken before irradiation to predict whether a rat will be impaired when irradiated. The results of this study are significant to crewed space missions as they support the potential of predicting an astronaut’s impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. METHODS Data used in this work are scores from the ATSET, a multi-stage constrained cognitive flexibility test [2]. Our computational model utilizes the number of attempts to reach the criterion to pass a stage as a behavioral performance measure for rats. We use the post-irradiation scores, generate thresholds from cumulative distribution plots of non-irradiated rats, and calculate the percent of irradiated rats whose scores fall below the threshold to infer how each radiation type/dose affects a population. Rats scoring above the threshold are labeled impaired while the others are non-impaired. We then employ ANNs as a typical ML technique, and use each subject’s individual scores taken before radiation along with the applied dose, to predict their personal susceptibility to cognitive impairment due to space radiation exposure. RESULTS AND CONCLUSION A significant finding is the exhibition of a dose-dependent increasing probability of impairment for 1 to 10 cGy of 28Si or 56Fe in the simple discrimination (SD) stage of the ATSET, and for 1 to 10 cGy of 56Fe in the compound discrimination (CD) stage. On a subject-based level, implementing ML classifiers such as ANNs identifies rats that have a higher tendency for impairment after GCR exposure [1]. The receiver operating characteristic (ROC) and the precision-recall (PR) curves of the ML models show a better prediction of impairment when 56Fe is the ion in question in both SD (Figure 1) and CD stages. They, however, do not depict impairment due to 4He in SD (Figure 1) and 28Si in CD, suggesting no dose-dependent impairment response in these cases. In this work, “good” prediction pertains to “better-than-random-chance”, due to the limited sample size and the high inter- and intra-individual variabilities in response to brain stimulation paradigms, as applicable to both animals and humans. More behavioral tests and biomarkers should be investigated on the same subjects, to be fed to the ML models to capture the agents responsible for performance alterations of some individuals versus others.
To date, disinformation research has focused largely on the production of false information ignoring the suppression of select information. We term this alternative form of disinformation information suppression. Information suppression occurs when facts are withheld with the intent to mislead. In order to detect information suppression, we focus on understanding the actors who withhold information. In this research, we use knowledge of human behavior to find signatures of different gatekeeping behaviors found in text. Specifically, we build a model to classify the different types of edits on Wikipedia using the added text alone and compare a human-informed feature engineering approach to a featureless algorithm. Being able to computationally distinguish gatekeeping behaviors is a first step towards identifying when information suppression is occurring.
This dissertation describes efforts towards understanding the Higgs boson at the highest energies humanly accessible, using the CMS experiment at the Large Hadron Collider and advances in artificial intelligence (AI) and machine learning (ML). We present searches for resonant and nonresonant Higgs-boson (H) pair production in the all-hadronic two beauty-quark and two vector boson (V) final state, using a novel strategy to measure the quartic HHVV coupling and search for new Higgs-like bosons. By targeting highly Lorentz-boosted Higgs pairs, we probe effects of potential new physics in the high energy Higgs sector, which could hold answers to fundamental mysteries of nature such as baryon asymmetry. To enable these and future searches, we introduce as well significant developments in AI/ML, including in the identification of boosted H$\rightarrow$VV decays with deep transformer networks and advances in AI-accelerated fast simulations of the CMS detector. The latter notably includes the development of the first, highly performant generative models for point-cloud data in high energy physics, which have the potential to improve CMS' computational efficiency by up to three orders of magnitude. We also highlight novel solutions to the important and challenging problems of calibrating and validating these ML techniques. Finally, we present new approaches to search for new physics in a model-agnostic manner, using physics-informed ML methods equivariant to Lorentz transformations. The quartic HHVV coupling is observed (expected) to be constrained to $[-0.04, 2.05]$ ($[0.05, 1.98]$) at the 95% confidence level relative to the standard model prediction, representing the second-most sensitive measurement of this coupling by CMS to date. Exclusion limits on the production cross section of new heavy resonances decaying to two Higgs-like bosons are expected to be as low as 0.3 fb for high resonance masses.