Search NASA⌕ Search

SEARCH · Search NASA

Results for “causality training”

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 73 records · Page 4

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

Improving Grid Resilience through Informed Decision-making (IGRID)

The transformation of the distribution grid from a centralized to decentralized architecture, with bi-directional power and data flows, is made possible by a surge in network intelligence and grid automation. While changes are largely beneficial, the interface between grid operator and automated technologies is not well understood, nor are the benefits and risks of automation. Quantifying and understanding the latter is an important facet of grid resilience that needs to be fully investigated. The work described in this document represents the first empirical study aimed at identifying and mitigating the vulnerabilities posed by automation for a grid that for the foreseeable future will remain a human-in-the-loop critical infrastructure. Our scenario-based methodology enabled us to conduct a series of experimental studies to identify causal relationships between grid-operator performance and automated technologies and to collect measurements of human performance as a function of automation. Our findings, though preliminary, suggest there are predictive patterns in the interplay between human operators and automation, patterns that can inform the rollout of distribution automation and the hiring and training of operators, and contribute in multiple and significant ways to the field of grid resilience.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Team Performance and Error Management in Chinese and American Simulated Flight Crews: The Role of Cultural and Individual Differences

This report describes results of a study conducted for NASA-Langley Research Center. This study is part of a program of research conducted for NASA-LARC that has focused on identifying the influence of national culture on the performance of flight crews. We first reviewed the literature devoted to models of teamwork and team performance, crew resource management, error management, and cross-cultural psychology. Davis (1999) reported the results of this review and presented a model that depicted how national culture could influence teamwork and performance in flight crews. The second study in this research program examined accident investigations of foreign airlines in the United States conducted by the National Transportation Safety Board (NTSB). The ability of cross-cultural values to explain national differences in flight outcomes was examined. Cultural values were found to covary in a predicted way with national differences, but the absence of necessary data in the NTSB reports and limitations in the research method that was used prevented a clear understanding of the causal impact of cultural values. Moreover, individual differences such as personality traits were not examined in this study. Davis and Kuang (2001) report results of this second study. The research summarized in the current report extends this previous research by directly assessing cultural and individual differences among students from the United States and China who were trained to fly in a flight simulator using desktop computer workstations. The research design used in this study allowed delineation of the impact of national origin, cultural values, personality traits, cognitive style, shared mental model, and task workload on teamwork, error management and flight outcomes. We briefly review the literature that documents the importance of teamwork and error management and its impact on flight crew performance. We next examine teamwork and crew resource management training designed to improve teamwork. This is followed by discussion of the potential influence of national culture on teamwork and crew resource management. We then examine the influence of other individual and team differences, such as personality traits, cognitive style, shared mental model, and task workload. We provide a heuristic model that depicts the influence of national culture and individual differences on teamwork, error management and flight outcomes. The results demonstrate the usefulness of the model for future research.

Davis, Donald D.↗

Research requirements to improve safety of civil helicopters

Helicopter and fixed-wing accident data were reviewed and major accident causal factors were established. The impact of accidents on insurance rates was examined and the differences in fixed-wing and helicopter accident costs discussed. The state of the art in civil helicopter safety was compared to military helicopters. Goals were established based on incorporation of known technology and achievable improvements that require development, as well as administrative-type changes such as the impact of improved operational planning, training, and human factors effects. Specific R and D recommendations are provided with an estimation of the payoffs, timing, and development costs.

Waters, K. T.↗

Transformational Phenomena as Predictors of Aircraft Accidents: What Goes Around Comes Around

Flight crew confusion, excessive stressworkload, and ineffective Crew Resource Management among other issues arising from dependence on automated systems on the flight deck have been identified as major causal factors in multiple fatal accidents, significant incidents and near misses. Many Loss of Control events have been traced to display of erroneous flight data and auto-flight system mode status to the crew. Safety was compromised by not having sufficiently obvious and unambiguous information available in order to permit quick diagnosis of aircraft status and then appropriate action to regain control of the aircraft energy state or trajectory. Continually evolving training and operational requirements related to aircraft automation have also presented critical challenges to commercial aviation. During times of high demand and low supply of experienced pilots (which is today the case in South-East Asia, for instance), basic training in manual flight may be minimal and as low as a few hundred flight hours on light aircraft before beginning training on advanced, highly automated aircraft. Predominant use of automation may cause aircrew trained in this way to have trouble performing traditionally simple operations such as manually switching to other runways or overriding the autopilot in tight situations. Inadequate crew training andor experience coupled with attempted manual flight in highly automated airplanes may more easily lead to loss of aircraft control in unusual situations such as high-altitude stallsupsets, traffic avoidance or maneuvering. Loss of basic piloting skills through increasing dependence on automation may exacerbate this problem. Finally, design changes by nature take a long time and are very costly. Incorporating novel automated functionality into new aircraft designs is technically feasible and desirable. However, it may take many years for these changes to have a significant impact on tomorrows fleet, given the time it takes to develop a new aircraft and for these aircraft to become a significant fraction of the fleet. This paper will review and summarize the findings and recommendations from a 2004 study of the topic, Increasing reliance on flight deck automation conducted by the Future Aviation Safety Team at the behest of the Joint Safety Strategy Initiative (JSSI) within the Joint Aviation Authorities (JAA) organization that existed at the time. Although this study was conducted more than ten years ago, its findings and recommendations are as relevant now as then and into the future.

safety↗

A Metabolomics Assay to Diagnose Citrus Huanglongbing Disease and to Aid in Assessment of Treatments to Prevent or Cure Infection

Citrus greening disease, or Huanglongbing (HLB), has devastated citrus crops globally in recent years. The causal bacterium, ‘ Candidatus Liberibacter asiaticus’, presents a sampling issue for qPCR diagnostics and results in a high false negative rate. In this work, we compared six metabolomics assays to identify HLB-infected citrus trees from leaf tissue extracted from 30 control and 30 HLB-infected trees. A liquid chromatography-mass spectrometry-based assay was most accurate. A final partial least squares-discriminant analysis (PLS-DA) model was trained and validated on 690 leaf samples with corresponding qPCR measures from three citrus varieties (Rio Red grapefruit, Hamlin sweet orange, and Valencia sweet orange) from orchards in Florida and Texas. Trees were naturally infected with HLB transmitted by the insect vector Diaphorina citri. In a randomized validation set, the assay was 99.9% accurate to classify diseased from nondiseased samples. This model was applied to samples from trees receiving plant defense-inducer compounds or biological treatments to prevent or cure HLB infection. From two trials, HLB-related metabolite abundances and PLS-DA scores were tracked longitudinally and compared with those of control trees. We demonstrate how our assay can assess tree health and the efficacy of HLB treatments and conclude that no trialed treatment was efficacious.

Plant Sciences↗

Convoluted filtering for process cycle modeling

Principles of materials science and engineering, physics, mathematics, and information science are used to extract knowledge and insights from the process-structure–property-performance relationships hidden in materials data. The process-structure modeling can be accelerated without loss of interpretability, with artificial intelligence tools that mimic the salient features of the process and process-structure relations. In this work, a novel convoluted model-filtering technique was exploited to build and successfully train the Convoluted Filter (CoFi) artifacts for Fe-based alloy heat treatment cycles. The artifacts were pre-trained to filter out deep models that change the surrogate microstructure state after the heat treatment at ambient conditions. Direct representation of the thermal cycle features within knowledge Graph facilitated development of meaningful data models for microstructure evolution, which reduce overfitting to limited datasets.

36 MATERIALS SCIENCE↗

Preliminary Design of an 'Autonomous Medical Response Agent' Interface Prototype for Long Duration Spaceflight

Major challenges for astronauts in future long-duration exploration missions (LDEMs) will be that crewmembers are not expected to be medical professionals, may be under high workload and stress, are facing physiological challenges caused by spaceflight, and will have limited, delayed voice communications with medical support from Earth. An autonomous medical response agent (AMRA) is envisioned to help astronauts address medical complaints, develop a differential diagnosis, and guide self-treatment until a healthy state is restored. AMRA develops a process of personalized diagnosis and treatment through a Bayesian predictive control system that recommends therapeutic control actions including diagnostic tests and treatments to crewmembers (Menon, 2020). The Human Computer Interaction (HCI) lab from NASA Ames Research Center’s Human Systems Integration Division (Code TH) has collaborated with Nahlia Inc in human-centered design augmentation research for AMRA. The project, titled Design of ‘Autonomous Medical Response Agent Interface Prototype for Long Duration Spaceflight, has been funded by the Translational Research Institute for Space Health (TRISH) and introduces an interactive user-interface prototype that guides astronauts through self-diagnosis, treatment, and rehabilitation while communicating with remote specialists in ground support (most notably a patient’s flight surgeon). Our project develops the interaction design for the crewmember using AMRA through user research, iterative design, and usability testing to evaluate the user interface and workflow designed. The interface design deliverable for this project, titled AMRA Aggregate Information Display (AMRA AID) is an integrated information display system for comprehensive autonomous medical guidance, diagnosis, and treatment of in-flight medical conditions experienced by crewmembers. AMRA AID demonstrates how we might ensure crew autonomy, increase the crew’s medical capabilities, and decrease cognitive burden within a front-end user interface. AMRA AID refrains from relying on input from ground or mission control for self-treatment of medical issues—though ground awareness and communication with ground is maintained as a means of ensuring trust between mission control and crew. AMRA AID demonstrates how the crew’s on-board medical system might integrate with information from vehicle monitoring and crew schedule, without assuming causal relationships. AMRA AID’s comprehensive view enables efficient information access for both crew and ground support, reducing cognitive burden in the event of an unplanned or emergency medical incident and enabling informed analytical decisions to be made based on both crew and vehicle health. Human-centered design augmentation advanced within the prototype included: enhanced workflow and treatment guidance for two medical scenarios for a non-specialist user base with various levels of medical training, interaction design which considered speech (conversational user interface) elements and on-screen interactions to be developed in future iterations of the project, communication design and functional requirements relevant to self-care versus caring for another astronaut, as well as user testing of the prototype with an international space medical community. This project arrives at critical findings regarding usability needs, communication requirements, and integrated information requirements for a future technology interface functioning to increase confidence between ground support and LDEM crewmembers.

TRISH↗

Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas

One of the biggest challenges to achieve the goal of producing fusion energy in tokamak devices is the necessity of avoiding disruptions of the plasma current due to instabilities. The disruption event characterization and forecasting (DECAF) framework has been developed in this purpose, integrating physics models of many causal events that can lead to a disruption. Two different machine learning approaches are proposed to improve the ideal magnetohydrodynamic (MHD) no-wall limit component of the kinetic stability model included in DECAF. First, a random forest regressor (RFR), was adopted to reproduce the DCON computed change in plasma potential energy without wall effects for a large database of equilibria from the national spherical torus experiment (NSTX). This tree-based method provides an analysis of the importance of each input feature, giving an insight into the underlying physics phenomena. Secondly, a fully-connected neural network has been trained on sets of calculations with the DCON code, to get an improved closed form equation of the no-wall β limit as a function of the relevant plasma parameters indicated by the RFR. The neural network has been guided by physics theory of ideal MHD in its extension outside the domain of the NSTX experimental data. The estimated value has been incorporated into the DECAF kinetic stability model and tested against a set of experimentally stable and unstable discharges. Moreover, the neural network results were used to simulate a real-time stability assessment using only quantities available in real-time. Finally, the portability of the model was investigated, showing encouraging results by testing the NSTX-trained algorithm on the mega ampere spherical tokamak (MAST).

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

MO-G-BRE-08: Taxonomy of Corrective Actions in Radiotherapy

Purpose: Various causal taxonomies have been developed for healthcare incidents and for radiation therapy in particular. The causal analysis of incidents leads to corrective actions which can also be organized into a taxonomy. Such a corrective action classification system would provide information about the situational context, the action type, and the leverage of the action in order to detect patterns in the corrective actions frequently employed in radiation therapy. It would also provide practical guidance to the radiation therapy community for determining the appropriateness and potential effectiveness of proposed corrective actions. Materials: A review of causal analysis reports and corrective action plans was conducted using the following sources: US NRC medical event reports, IAEA reports, ROSIS submissions, US Veterans Health Administration reports, and singleincident report sources. The corrective actions presented in the published sources were then mapped onto four corrective action taxonomy prototypes: role-based, safety-context-based, responsibility-based, and hierarchy of hazard control. The resulting corrective action taxonomy was then validated through use of the published sources. Results: The responsibility-based taxonomy and hierarchy of hazard taxonomy provided more intuitive and sensible categories than the role-based taxonomy or the safety-context taxonomy. The most frequent corrective actions were added safety barriers, training, process standardization, and development of a quality improvement program where one was lacking. Conclusion: Published corrective action statements in radiation therapy emphasize what to do more so than whom the recipient is or which process step is affected. The hierarchy of hazard taxonomy provides a suitable framework for radiation therapy and has the advantage of providing insight into the likelihood that a particular corrective action will mitigate the recurrence of the error it was meant to correct. This information would be useful to medical center administration, safety personnel, and regulators who must assess the projected efficacy of corrective actions. Derek Brown is a director of TreatSafely, LLC.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Development and Testing of Data Mining Algorithms for Earth Observation

The new algorithms developed under this project included a principled procedure for classification of objects, events or circumstances according to a target variable when a very large number of potential predictor variables is available but the number of cases that can be used for training a classifier is relatively small. These "high dimensional" problems require finding a minimal set of variables -called the Markov Blanket-- sufficient for predicting the value of the target variable. An algorithm, the Markov Blanket Fan Search, was developed, implemented and tested on both simulated and real data in conjunction with a graphical model classifier, which was also implemented. Another algorithm developed and implemented in TETRAD IV for time series elaborated on work by C. Granger and N. Swanson, which in turn exploited some of our earlier work. The algorithms in question learn a linear time series model from data. Given such a time series, the simultaneous residual covariances, after factoring out time dependencies, may provide information about causal processes that occur more rapidly than the time series representation allow, so called simultaneous or contemporaneous causal processes. Working with A. Monetta, a graduate student from Italy, we produced the correct statistics for estimating the contemporaneous causal structure from time series data using the TETRAD IV suite of algorithms. Two economists, David Bessler and Kevin Hoover, have independently published applications using TETRAD style algorithms to the same purpose. These implementations and algorithmic developments were separately used in two kinds of studies of climate data: Short time series of geographically proximate climate variables predicting agricultural effects in California, and longer duration climate measurements of temperature teleconnections.

Glymour, Clark↗

Deep-freeze graph training for latent learning

Scientific and engineering advances are primarily driven by multi-tier conceptual constructs and conditional theoretical frameworks. The theories allow predictions of hypothetical system responses, given a set of approximate conditions (ranges of applicability) imposed on latent parameters that cannot be measured directly. Learning to estimate the latent variables (Latent Learning) helps to pinpoint the anticipated range-edge anomalies and improves the confidence in interpretation, interpolation and extrapolation of limited experimental data. Due to high dimensionality and extreme non-linearity of the materials science problems, very large datasets are typically required for conventional data-driven model development. The vital experimental data collection, particularly on microstructural phases, is very challenging, which makes it difficult to compile a high-quality database. Incorporation of the domain knowledge into the computational graph structure, initialization and optimization processes presents a viable mechanism for developing accurate models, with limited datasets. Furthermore, this study successfully utilized the approach to build the Deep Freeze Graph (DeepFreG) by mapping known causality relationships and by digitizing empirical domain knowledge for Latent Learning (LL), with specific applications in materials science.

36 MATERIALS SCIENCE↗

SU-E-P-07: Retrospective Analysis of Incident Reports at a Radiology Department: Feedback From Incident Reporting System

Purpose: To provide an overview of reported incidents that occurred in a radiology department and to describe the most common causal source of incidents. Methods: Incident reports from the radiology department at the University of the Ryukyus Hospital between 2008 and 2013 were collected and analyzed retrospectively. The incident report form contains the following items, causal factors of the incident and desirable corrective actions to prevent recurrence of similar incidents. These items allow the institution to investigate/analyze root causes of the incidents and suggest measures to be taken to prevent further, similar incidents. The ‘causal factors of the incident’ item comprises multiple selections from among 24 selections and includes some synonymous selections. In this study, this item was re-categorized into four causal source types: (i) carelessness, (ii) lack of skill or knowledge, (iii) deficiencies in communication, and (iv) external factors. Results: There were a total of 7490 incident reports over the study period and 276 (3.7%) were identified as originating from the radiology department. The most frequent causal source type was carelessness (62%). The other three types showed similar frequencies (10–14%). The staff members involved in incidents indicate three predominant desirable corrective actions to prevent or decrease the recurrence of similar incidents. These are ‘improvement in communication’ (24%), ‘staff training/education’ (19%), and ‘daily medical procedures’ (22%), and the most frequent was ‘improvement in communication’. Even though the most frequent causal factor was related to carelessness, the most desirable corrective action indicated by the staff members was related to communication. Conclusion: Our finding suggests that the most immediate causes are strongly related to carelessness. However, the most likely underlying causes of incidents would be related to deficiencies in effective communication. At our department, therefore, the primary action to prevent/reduce similar incidents should be ‘communication improvement’.

61 RADIATION PROTECTION AND DOSIMETRY↗

Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks and Operators in Scientific Computing: Fluid and Solid Mechanics

Abstract Advancements in computing power have recently made it possible to utilize machine learning and deep learning to push scientific computing forward in a range of disciplines, such as fluid mechanics, solid mechanics, materials science, etc. The incorporation of neural networks is particularly crucial in this hybridization process. Due to their intrinsic architecture, conventional neural networks cannot be successfully trained and scoped when data are sparse, which is the case in many scientific and engineering domains. Nonetheless, neural networks provide a solid foundation to respect physics-driven or knowledge-based constraints during training. Generally speaking, there are three distinct neural network frameworks to enforce the underlying physics: (i) physics-guided neural networks (PgNNs), (ii) physics-informed neural networks (PiNNs), and (iii) physics-encoded neural networks (PeNNs). These methods provide distinct advantages for accelerating the numerical modeling of complex multiscale multiphysics phenomena. In addition, the recent developments in neural operators (NOs) add another dimension to these new simulation paradigms, especially when the real-time prediction of complex multiphysics systems is required. All these models also come with their own unique drawbacks and limitations that call for further fundamental research. This study aims to present a review of the four neural network frameworks (i.e., PgNNs, PiNNs, PeNNs, and NOs) used in scientific computing research. The state-of-the-art architectures and their applications are reviewed, limitations are discussed, and future research opportunities are presented in terms of improving algorithms, considering causalities, expanding applications, and coupling scientific and deep learning solvers.

Computer Science↗

Detect and correct bias in multi-site neuroimaging datasets

The desire to train complex machine learning algorithms and to increase the statistical power in association studies drives neuroimaging research to use ever-larger datasets. The most obvious way to increase sample size is by pooling scans from independent studies. However, simple pooling is often ill-advised as selection, measurement, and confounding biases may creep in and yield spurious correlations. In this work, we combine 35,320 magnetic resonance images of the brain from 17 studies to examine bias in neuroimaging. In the first experiment, Name That Dataset, we provide empirical evidence for the presence of bias by showing that scans can be correctly assigned to their respective dataset with 71.5% accuracy. Given such evidence, we take a closer look at confounding bias, which is often viewed as the main shortcoming in observational studies. In practice, we neither know all potential confounders nor do we have data on them. Hence, we model confounders as unknown, latent variables. Kolmogorov complexity is then used to decide whether the confounded or the causal model provides the simplest factorization of the graphical model. Finally, we present methods for dataset harmonization and study their ability to remove bias in imaging features. In particular, we propose an extension of the recently introduced ComBat algorithm to control for global variation across image features, inspired by adjusting for unknown population stratification in genetics. Overall, our results demonstrate that harmonization can reduce dataset-specific information in image features. Further, confounding bias can be reduced and even turned into a causal relationship. However, harmonization also requires caution as it can easily remove relevant subject-specific information. Code is available at https://github.com/ai-med/Dataset-Bias.

42 ENGINEERING↗

Atmospheric Circulation Anomalies During Two Persistent North American Droughts: 1932-1939 and 1948-1957

We use an early twentieth century (1908-1958) atmospheric reanalysis, based on assimilation of surface and sea level pressure observations, to contrast atmospheric circulation during two periods of persistent drought in North America: 1932-1939 (the Dust Bowl) and 1948-1957. Primary forcing for both droughts is believed to come from anomalous sea surface temperatures (SSTs): a warm Atlantic and a cool eastern tropical Pacific. For boreal winter (October-March) in the 1950s, a stationary wave pattern originating from the tropical Pacific is present, with positive centers over the north Pacific and north Atlantic ocean basins and a negative center positioned over northwest North America and the tropical/subtropical Pacific. This wave train is largely absent for the 1930s drought; boreal winter height anomalies are organized much more zonally, with positive heights extending across northern North America. For boreal summer (April-September) during the 1930s, a strong upper level ridge is centered over the Great Plains; this feature is absent during the 1950s and appears to be linked to a weakening of the Great Plains low-level jet (GPLLJ). Subsidence anomalies are co-located over the centers of each drought: in the central Great Plains for the 1930s and in a band extending from the southwest to the southeastern United States for the 1950s. The location and intensity of this subsidence during the 1948-1957 drought is a typical response to a cold eastern tropical Pacific, but for 1932-1939 deviates in terms of the expected intensity, location, and spatial extent. Overall, circulation anomalies during the 1950s drought appear consistent with the expected response to the observed SST forcing. This is not the case for the 1930s, implying some other causal factor may be needed to explain the Dust Bowl drought anomalies. In addition to SST forcing, the 1930s were also characterized by massive alterations to the land surface, including regional-scale devegetation from crop failures and intensive wind erosion and dust storms. Incorporation of these land surface factors into a general circulation model greatly improves the simulation of precipitation and subsidence anomalies during this drought, relative to simulations with SST forcing alone. Even with additional forcing from the land surface, however, the model still has difficulty reproducing some of the other circulation anomalies, including weakening of the GPLLJ and strengthening of the upper level ridge during AMJJAS. This may be due to either weaknesses in the model or uncertainties in the boundary condition estimates. Still, analysis of the circulation anomalies supports the conclusion of an earlier paper (Cook et al. in Proc Natl Acad Sci 106:4997, 2009), demonstrating that land degradation factors are consistent with the anomalous nature of the Dust Bowl drought.

Cook, Benjamin↗

Deep Analysis Net with Causal Embedding for Coal-fired Power Plant Fault Detection and Diagnosis (DANCE4CFDD)

Fault detection and diagnosis is critical to power plant operation to ensure attaining high reliability while reducing operation cost. As more renewable power is introduced to the power grid, traditional fossil power plants take on the extra burden of excessive load cycling to compensate the generation variability from renewable power. Such load cycling will pose more reliability challenges to power plant operation. There are a number of challenges faced by today’s asset health management system in coal- fired (or gas) power plants: 1) high-dimensional nonlinear interaction among multiple time series measurements; 2) high measurement variance induced by operational conditions/modes; 3) variation among asset types and plant configurations; and 4) a small number of faulty events to learn from. To cope with these challenges, today’s fielded asset health management systems rely heavily on manual efforts from domain experts and hand-crafted features or rules based on domain knowledge. Despite its role in plant reliability, such a practice is costly and hinders its scalability and sustainability, particularly when a plant undergoes modifications. The objective of this project is to develop a novel end-to-end AI learning system that is trainable (i.e., the AI representation of a complex system behavior can be directly learned from properly labeled data) for accurate fault detection and root cause analysis. The ability to create a fault detection model directly from time series could alleviate the efforts associated with today’s asset management solution development. In the course of this project, we have achieved the following: Created an AI model development environment incorporating state-of-the-art neural network architectures for rapid model development and evaluation; Developed novel learning strategies for training of fault detection model; Developed special-purpose neural network architecture embedded with variable association graph aiming for better interpretability; Developed a learning strategy to leverage a small number of faulty events for enhanced fault detection capability; Conducted detailed experimental study based on public benchmark datasets and demonstrated the effectiveness of the proposed solution; and Validated the developed system with data from both a coal-fired plant boiler dynamic simulation model and real-world coal-fired power plant covering multiple asset and fault types. Overall, the project attained a technology readiness level of TRL 5 from TRL 2 at the beginning of the project.

20 FOSSIL-FUELED POWER PLANTS↗