Search NASA⌕ Search

SEARCH · Search NASA

Results for “causal 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 127 records · Page 7

Investigation of a “Sharps” Incident

Special nuclear material research, process development, technology demonstration, and manufacturing capabilities are provided at the Los Alamos National Laboratory Plutonium Facility. Engineered barriers provide the most effective protection from radioactive and hazardous materials. The Worker Safety Security Team augments these passive safety feature by investigating incidents to identify appropriate prevention and mitigation measures. “Learning Teams” facilitate employee feedback loop and integration toward process improvement. Here, this article reports an investigation of a “Sharps” incident and reviews a case study of a technician that cuts his left thumb while making a gasket. Causal analysis of the sharps incident uncovered contributing factors that created the environment in which the incident occurred. Finally, latent organizational conditions that created error-likely situations or weakened defenses were identified and controlled. Effective improvements that reduce the probability or consequence of similar sharps incidents were implemented.

61 RADIATION PROTECTION AND DOSIMETRY↗

Unraveling complex causal processes that affect sustainability requires more integration between empirical and modeling approaches

Scientists seek to understand the causal processes that generate sustainability problems and determine effective solutions. Yet, causal inquiry in nature–society systems is hampered by conceptual and methodological challenges that arise from nature–society interdependencies and the complex dynamics they create. Here, we demonstrate how sustainability scientists can address these challenges and make more robust causal claims through better integration between empirical analyses and process- or agent-based modeling. To illustrate how these different epistemological traditions can be integrated, we present four studies of air pollution regulation, natural resource management, and the spread of COVID-19. The studies show how integration can improve empirical estimates of causal effects, inform future research designs and data collection, enhance understanding of the complex dynamics that underlie observed temporal patterns, and elucidate causal mechanisms and the contexts in which they operate. These advances in causal understanding can help sustainability scientists develop better theories of phenomena where social and ecological processes are dynamically intertwined and prior causal knowledge and data are limited. The improved causal understanding also enhances governance by helping scientists and practitioners choose among potential interventions, decide when and how the timing of an intervention matters, and anticipate unexpected outcomes. Methodological integration, however, requires skills and efforts of all involved to learn how members of the respective other tradition think and analyze nature–society systems.

42 ENGINEERING↗

Subseasonal Representation and Predictability of North American Weather Regimes Using Cluster Analysis

Abstract This study focuses on assessing the representation and predictability of North American weather regimes, which are persistent large-scale atmospheric patterns, in a set of initialized subseasonal reforecasts created using the Community Earth System Model, version 2 (CESM2). The k -means clustering was used to extract four key North American (10°–70°N, 150°–40°W) weather regimes within ERA5 reanalysis, which were used to interpret CESM2 subseasonal forecast performance. Results show that CESM2 can recreate the climatology of the four main North American weather regimes with skill but exhibits biases during later lead times with overoccurrence of the West Coast high regime and underoccurrence of the Greenland high and Alaskan ridge regimes. Overall, the West Coast high and Pacific trough regimes exhibited higher predictability within CESM2, partly related to El Niño. Despite biases, several reforecasts were skillful and exhibited high predictability during later lead times, which could be partly attributed to skillful representation of the atmosphere from the tropics to extratropics upstream of North America. The high predictability at the subseasonal time scale of these case-study examples was manifested as an “ensemble realignment,” in which most ensemble members agreed on a prediction despite ensemble trajectory dispersion during earlier lead times. Weather regimes were also shown to project distinct temperature and precipitation anomalies across North America that largely agree with observational products. This study further demonstrates that unsupervised learning methods can be used to uncover sources and limits of subseasonal predictability, along with systematic biases present in numerical prediction systems. Significance Statement North American weather regimes are large-scale atmospheric patterns that can persist for several days. Their skillful subseasonal (2 weeks or greater) prediction can provide valuable lead time to prepare for temperature and precipitation anomalies that can stress energy and water resources. The purpose of this study was to assess the climatological representation and subseasonal predictability of four key North American weather regimes using a research subseasonal prediction system and clustering analysis. We found that the Pacific trough and West Coast high regimes exhibited higher predictability than other regimes and that skillful representation of conditions across the tropics and extratropics can increase predictability during later lead times. Future work will quantify causal pathways associated with high predictability.

58 GEOSCIENCES↗

Predicting Cognitive States Using Machine Learning Fusion Paradigms to Reduce Model Uncertainty

The development of a synergetic system between humans and technology is a challenge that the scientific community has been facing for many years. Our aeronautic research aims to enhance this synergy between humans and machines through predictive human performance modeling for systems to mitigate high-risk situations. By being able to predict and anticipate human states, the crew monitoring system should be able to adjust and support the pilot for aviation safety. Our work focusing on attention-related human performance-limiting states (AHPLS) that impact a pilot’s performance and introduce high-risk catastrophic situations [1]. For example, AHPLS has been cited as a causal factor in more than 50% of all loss control in flight and thus contributes significantly toward commercial aviation fatalities [1, 2]. Cognitive state and its physiological fingerprint can be valuable information for this detecting AHPLS, but human cognitive state detection is still a major limitation for these crew monitoring systems.

machine learning↗

Using Systems Theoretic Process Analysis and Causal Analysis to Map and Manage Organizational Information to Enable Digitalization and Information Automation

The overarching goal of this Light Water Reactor Sustainability Program–supported research and development project is to provide planning tools and comprehensive guidance to utilities considering or undertaking full nuclear plant modernization. The results of this research will provide the nuclear industry with a comprehensive and usable solution, including guidance, lessons learned, methods, and planning tools. This research is currently working to provide guidance on digitalization and information automation to enable the evolution of data to information, insight, and action—thereby allowing utilities to operate safely and cost-competitively with all other electrical generation sources. Light Water Reactor Sustainability Program researchers have also recently started investigating how human and technology integration principles, information automation, and digitalization enable data evolution. These researchers are currently in the process of validating the use of System-Theoretic Process Analysis to define high-level safety constraints in the United States Nuclear Regulatory Commission’s problem identification and resolution process (i.e., a plant compliance information gathering activity). The next step in this research, which is described in the following sections of this report, is to map out data evolution in a use case to identify inefficiencies in another aspect of plant compliance information gathering and communication activities—event investigations and root cause analyses.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

RingX: Scalable Parallel Attention for Long-Context Learning on HPC

The attention mechanism has become foundational for remarkable AI breakthroughs since the introduction of the Transformer, driving the demand for increasingly longer context to power frontier models such as large-scale reasoning language models and high-resolution image/video generators. However, its quadratic computational and memory complexities present substantial challenges. Current state-of-the-art parallel attention methods, such as ring attention, are widely adopted for long-context training but utilize a point-to-point communication strategy that fails to fully exploit the capabilities of modern HPC network architectures. In this work, we propose ringX, a scalable family of parallel attention methods optimized explicitly for HPC systems. By enhancing workload partitioning, refining communication patterns, and improving load balancing, ringX achieves up to 3.4 × speedup compared to conventional ring attention on the Frontier supercomputer. Optimized for both bi-directional and causal attention mechanisms, ringX demonstrates its effectiveness through training benchmarks of a Vision Transformer (ViT) on a climate dataset and a Generative Pre-Trained Transformer (GPT) model, Llama3 8B. Our method attains an end-to-end training speedup of approximately 1.5 × in both scenarios. To our knowledge, the achieved 38% model FLOPs utilization (MFU) for training Llama3 8B with a 1M-token sequence length on 4,096 GPUs represents one of the highest training efficiencies reported for long-context learning on HPC systems. Our code implementation is available at https://github.com/jqyin/ringX-attention.

Yin, Junqi [ORNL] (ORCID:0000000338435520)↗

InvestigationOrganizer: The Development and Testing of a Web-based Tool to Support Mishap Investigations

InvestigationOrganizer (IO) is a collaborative web-based system designed to support the conduct of mishap investigations. IO provides a common repository for a wide range of mishap related information, and allows investigators to make explicit, shared, and meaningful links between evidence, causal models, findings and recommendations. It integrates the functionality of a database, a common document repository, a semantic knowledge network, a rule-based inference engine, and causal modeling and visualization. Thus far, IO has been used to support four mishap investigations within NASA, ranging from a small property damage case to the loss of the Space Shuttle Columbia. This paper describes how the functionality of IO supports mishap investigations and the lessons learned from the experience of supporting two of the NASA mishap investigations: the Columbia Accident Investigation and the CONTOUR Loss Investigation.

Carvalho, Robert F.↗

Analysis and Prediction of Weather Impacted Ground Stop Operations

When the air traffic demand is expected to exceed the available airport's capacity for a short period of time, Ground Stop (GS) operations are implemented by Federal Aviation Administration (FAA) Traffic Flow Management (TFM). The GS requires departing aircraft meeting specific criteria to remain on the ground to achieve reduced demands at the constrained destination airport until the end of the GS. This paper provides a high-level overview of the statistical distributions as well as causal factors for the GSs at the major airports in the United States. The GS's character, the weather impact on GSs, GS variations with delays, and the interaction between GSs and Ground Delay Programs (GDPs) at Newark Liberty International Airport (EWR) are investigated. The machine learning methods are used to generate classification models that map the historical airport weather forecast, schedule traffic, and other airport conditions to implemented GS/GDP operations and the models are evaluated using the cross-validations. This modeling approach produced promising results as it yielded an 85% overall classification accuracy to distinguish the implemented GS days from the normal days without GS and GDP operations and a 71% accuracy to differentiate the GS and GDP implemented days from the GDP only days.

Analysis↗

Earth as a Proxy Exoplanet: Deconstructing and Reconstructing Spectrophotometric Light Curves

Point-source spectrophotometric (single-point) light curves of Earth-like planets contain a surprising amount of information about the spatial features of those worlds. Spatially resolving these light curves is important for assessing time-varying surface features and the existence of an atmosphere, which in turn is critical to life on Earth and significant for determining habitability on exoplanets. Given that Earth is the only celestial body confirmed to harbor life, treating it as a proxy exoplanet by analyzing time-resolved spectral images provides a benchmark in the search for habitable exoplanets. The Earth Polychromatic Imaging Camera (EPIC) on the Deep Space Climate Observatory (DSCOVR) provides such an opportunity, with observations of ∼5000 full-disk sunlit Earth images each year at 10 wavelengths with high temporal frequency. We disk-integrate these spectral images to create single-point light curves and decompose them into principal components (PCs). Using machine-learning techniques to relate the PCs to six preselected spatial features, we find that the first and fourth PCs of the single-point light curves, contributing ∼83.23% of the light-curve variability, contain information about low and high clouds, respectively. Surface information relevant to the contrast between land and ocean reflectance is contained in the second PC, while individual land subtypes are not easily distinguishable (<0.1% total light-curve variation). We build an Earth model by systematically altering the spatial features to derive causal relationships to the PCs. This model can serve as a baseline for analyzing Earth-like exoplanets and guide wavelength selection and sampling strategies for future observations.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

The effects of cognitive and behavioral control on post-stress performance

A study was designed to investigate the effects of behavioral and cognitive control on post-stress performance. Half of the subjects exposed to loud unpredictable noise bursts were given 'behavioral' control (a button which would terminate the noise), while the other half had no behavioral control. In addition, subjects were provided with one of three levels of feedback (success, failure, or no feedback) regarding their performance during the noise. It was expected that information about performance would provide subjects with an increased sense of 'cognitive' control which would affect their appraisal of stressful events and their later performance. The results indicated that subjects given feedback performed better on subsequent tasks than those given no feedback. Perceived behavioral control had little effect on performance. The causal attributions made by subjects were used to interpret these effects. These findings were viewed as supportive of Averill's (1973) notion that various types of control are related to stress in a complex fashion. The data may also support the reformulation by Abramson et al. (1978) of learned helplessness theory.

Foushee, H. C.↗

Multiple Kernel Learning for Heterogeneous Anomaly Detection: Algorithm and Aviation Safety Case Study

The world-wide aviation system is one of the most complex dynamical systems ever developed and is generating data at an extremely rapid rate. Most modern commercial aircraft record several hundred flight parameters including information from the guidance, navigation, and control systems, the avionics and propulsion systems, and the pilot inputs into the aircraft. These parameters may be continuous measurements or binary or categorical measurements recorded in one second intervals for the duration of the flight. Currently, most approaches to aviation safety are reactive, meaning that they are designed to react to an aviation safety incident or accident. In this paper, we discuss a novel approach based on the theory of multiple kernel learning to detect potential safety anomalies in very large data bases of discrete and continuous data from world-wide operations of commercial fleets. We pose a general anomaly detection problem which includes both discrete and continuous data streams, where we assume that the discrete streams have a causal influence on the continuous streams. We also assume that atypical sequence of events in the discrete streams can lead to off-nominal system performance. We discuss the application domain, novel algorithms, and also discuss results on real-world data sets. Our algorithm uncovers operationally significant events in high dimensional data streams in the aviation industry which are not detectable using state of the art methods

Das, Santanu↗

Unsupervised machine learning discovery of structural units and transformation pathways from imaging data

We show that unsupervised machine learning can be used to learn chemical transformation pathways from observational Scanning Transmission Electron Microscopy (STEM) data. To enable this analysis, we assumed the existence of atoms, a discreteness of atomic classes, and the presence of an explicit relationship between the observed STEM contrast and the presence of atomic units. With only these postulates, we developed a machine learning method leveraging a rotationally invariant variational autoencoder (VAE) that can identify the existing molecular fragments observed within a material. The approach encodes the information contained in STEM image sequences using a small number of latent variables, allowing the exploration of chemical transformation pathways by tracing the evolution of atoms in the latent space of the system. The results suggest that atomically resolved STEM data can be used to derive fundamental physical and chemical mechanisms involved, by providing encodings of the observed structures that act as bottom-up equivalents of structural order parameters. The approach also demonstrates the potential of variational (i.e., Bayesian) methods in the physical sciences and will stimulate the development of more sophisticated ways to encode physical constraints in the encoder–decoder architectures and generative physical laws and causal relationships in the latent space of VAEs.

97 MATHEMATICS AND COMPUTING↗

Machine Intelligence to Detect, Characterise, and Defend against Influence Operations in the Information Environment

Social media has enabled a new era of manipulation in the information and cognitive domains. Deceptive content—misleading, falsified, and fabricated—is routinely created and spread in the modern social media environment with the intent to create confusion and widen political and social divides, and exploit the societal conflict exacerbated by these divides in the real-world (aka physical domain). Such disinformation campaigns demonstrate a threat to the integrity of economic, political, cultural, public health, and national security institutions around the world. In this work we overview our artificial intelligence (AI) capabilities to detect, describe, and defend against information operations on Twitter as an example social platform to understand the influence of misleading and falsified content diffusion and better enable those charged with defending against such manipulation to enable responsive parties to counter it. We first present novel linguistically-informed deep learning (DL) models for misinformation and disinformation detection, and present an in-depth linguistic analysis of psycho-linguistic markers across broad deception categories. We then demonstrate how our models perform in the multilingual and multimodal setting and categorize falsified and misleading content based on the intent to deceive. We also provide a large-scale analysis to describe user behavior and spread patterns while engaging with deceptive content and report novel findings about the immediate diffusion of deceptive content by characterizing the vulnerable sub-populations and their demographics, and explicitly measuring speed and scale of deception spread to uncover who shares deceptive content, how quickly, how much, and how evenly. In addition, we measure audience reactions to misinformation and disinformation at scale, distinguishing the reactions of users identified as bots versus humans. Finally, we take advantage of deep translation and generation models to create unique solutions for real-time defense against digital deception and discuss how to apply causal inference to prescribe and intervene into strategic communications jointly across information, cognitive, and physical domains.

artificial intelligence, deep learning, neural lan↗

Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems

Fault detection and diagnosis (FDD) technologies are critical to ensure satisfactory building performance, such as reducing energy wastes and negative impacts on occupant comfort and productivity. Existing FDD technologies mainly focus on component-level FDD solutions, which could lead to mis-diagnosis of cross-level faults in heating, ventilating, and air-conditioning (HVAC) systems. Cross-level faults are those faults that occur in one component or subsystem, but cause operational abnormalities in other components or subsystems, and result in a building level performance degradation. How to effectively diagnose the root cause of a cross-level fault is the focus of this study. Here, this paper presents a novel discrete Bayesian Network (DisBN)-based method for diagnosing cross-level faults in an HVAC system commonly used in commercial buildings. A two-level DisBN structure model is developed in this study. The parameters used in the DisBN model are obtained either from expert knowledge or through machine-learning strategies from normal system operation data. Meanwhile, the probability parameters are discretized to incorporate the uncertainties associated with typical expert knowledge. Thus, the developed DisBN method addresses the challenges many other BN based FDD methods face, i.e., the lack of fault data for BN parameter training. The developed DisBN represents causal relationships between a fault and its cross-level system impacts (i.e., fault symptoms or fault indicators) by considering how fault impacts propagate across different levels in an HVAC system. A weather and schedule information-based Pattern Matching (WPM) method is employed to automatically create WPM baseline data sets for each incoming real time snapshot data from the building systems. Consequently, BN inference and real-time diagnostics are achieved by comparing incoming snapshot data and the WPM baseline data set. The proposed method is evaluated using experimental fault data collected in a campus building. Fault diagnosis results demonstrate that the WPM-DisBN method is effective at locating the root causes of cross-level faults in an HVAC system.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

The relationship between below average cognitive ability at age 5 years and the child’s experience of school at age 9

Background At age 5, while only embarking on their educational journey, substantial differences in children’s cognitive ability will already exist. The aim of this study was to examine the causal association between below average cognitive ability at age 5 years and child-reported experience of school and self-concept, and teacher-reported class engagement and emotional-behavioural function at age 9 years. Methods This longitudinal cohort study used data from 7,392 children in the Growing Up in Ireland Infant Cohort, who had completed the Picture Similarities and Naming Vocabulary subtests of the British Abilities Scales at age 5. Principal components analysis was used to produce a composite general cognitive ability score for each child. Children with a general cognitive ability score more than 1 standard deviation (SD) below the mean at age 5 were categorised as ‘Below Average Cognitive Ability’ (BACA), and those scoring above this as ‘Typical Cognitive Development’ (TCD). The outcomes of interest, measured at age 9, were child-reported experience of school, child’s self-concept, teacher-reported class engagement, and teacher-reported emotional behavioural function. Binary and multinomial logistic regression models were used to examine the association between BACA and these outcomes. Results Compared to those with TCD, those with BACA had significantly higher odds of never liking school [Adjusted odds ratio (AOR) 1.82, 95% CI 1.37–2.43, p < 0.001], of being picked on (AOR 1.27, 95% CI 1.09–1.48) and of picking on others (AOR 1.53, 95% CI 1.27–1.84). They had significantly higher odds of experiencing low self-concept (AOR 1.20, 95% CI 1.02–1.42) and emotional-behavioural difficulties (AOR 1.34, 95% CI 1.10–1.63, p = 0.003). Compared to those with TCD, children with BACA had significantly higher odds of hardly ever or never being interested, motivated and excited to learn (AOR 2.29, 95% CI 1.70–3.10). Conclusion Children with BACA at school-entry had significantly higher odds of reporting a negative school experience and low self-concept at age 9. They had significantly higher odds of having teacher-reported poor class engagement and problematic emotional-behavioural function at age 9. The findings of this study suggest BACA has a causal role in these adverse outcomes. Early childhood policy and intervention design should be cognisant of the important role of cognitive ability in school and childhood outcomes.

Bowe, Andrea K.↗

Machine learning to extend and understand the sources and limits of water cycle predictability on subseasonal-to-decadal timescales in the Earth system

This white paper provides initial insight on how artificial intelligence (AI) and machine learning (ML), including interpretability and explainable AI (XAI) methods, can be leveraged to glean insight from complex data for a paradigm-changing improvement in Earth system predictability on subseasonal-to-seasonal (S2S) and seasonal-to-decadal (S2D) timescales. The application of AI to extend and improve predictability, in combination with causal inference and uncertainty quantification, could lead to a transformative understanding of the integrative water cycle and associated extremes.

54 ENVIRONMENTAL SCIENCES↗

Operation Optimization using Reinforcement Learning with Integrated Artificial Reasoning Framework

In large and complex systems, operational decision-making requires a systematic analysis with a vast amount of data from both process parameters and component status monitoring. In this paper, we present an integrated artificial reasoning approach for system state transition models that can help operational decision-making with explainable and traceable reasoning. The integrated artificial reasoning framework is a physics-based approach of defining the system structure in a Bayesian network, so we leveraged it in a Markov decision process (MDP) for finding optimal operational solutions. In our proposed framework, the MDP is implemented on a dynamic Bayesian network (DBN), which represents causalities in a system. The multilevel flow modeling was utilized in order to extract these causalities in a more efficient and objective manner. Since multilevel flow modeling is based on the fundamental energy and mass conservation laws, the target system is decomposed into several mass, energy, and information structures, which serve as the basis for a DBN. The MDP consists of the processes of finding a solution for the Bellman equation, which can be derived from the conditional probability equations of the constructed DBN. System operators can capture stochastic system dynamics as multiple subsystem state transitions based on their physical relations and uncertainties coming from the component degradation process or random failures. We analyzed a simplified example system to illustrate finding an optimal operational policy with this approach.

99 GENERAL AND MISCELLANEOUS↗