Results for “Learning control” — Page 81

DOE OSTI2024

Quantifying wildfire drivers and predictability in boreal peatlands using a two-step error-correcting machine learning framework in TeFire v1.0

Abstract. Wildfires are becoming an increasing challenge to the sustainability of boreal peatland (BP) ecosystems and can alter the stability of boreal carbon storage. However, predicting the occurrence of rare and extreme BP fires proves to be challenging, and gaining a quantitative understanding of the factors, both natural and anthropogenic, inducing BP fires remains elusive. Here, we quantified the predictability of BP fires and their primary controlling factors from 1997 to 2015 using a two-step correcting machine learning (ML) framework that combines multiple ML classifiers, regression models, and an error-correcting technique. We found that (1) the adopted oversampling algorithm effectively addressed the unbalanced data and improved the recall rate by 26.88 %–48.62 % when using multiple datasets, and the error-correcting technique tackled the overestimation of fire sizes during fire seasons; (2) nonparametric models outperformed parametric models in predicting fire occurrences, and the random forest machine learning model performed the best, with the area under the receiver operating characteristic curve ranging from 0.83 to 0.93 across multiple fire datasets; and (3) four sets of factor-control simulations consistently indicated the dominant role of temperature, air dryness, and climate extreme (i.e., frost) for boreal peatland fires, overriding the effects of precipitation, wind speed, and human activities. Our findings demonstrate the efficiency and accuracy of ML techniques in predicting rare and extreme fire events and disentangle the primary factors determining BP fires, which are critical for predicting future fire risks under climate change.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Simulating a Reactor with PID Temperature Control

A Simulation of a Reactor, Built Using CrowPis, which are simple and accessible programmable systems of various electronics, as ground stations and a Box containing heaters as the reactor. The goal of this project is to learn various skills and to demonstrate the feasibility of a simulated reactor, utilizing a PID control and wireless connectivity.

42 - ENGINEERING↗

DOE OSTI2021

The phylogenetic roots of addiction: compulsive drug seeking, natural and drug-sensitive reward, and the acquisition of learned habits

Our rational faculties permit us humans to maximize the utility of our actions. We perform a fundamental type of cost-benefit analysis in which we frame a problem, assign values to the different paths, and then choose from among a set of available options, the course that promises the most favorable outcome. So why then does addiction appear to be so impervious to the associated costs, so unaffected by undesired consequences, and ultimately so resistant to cognitive oversight? The answer may likely be found in the fact that the drivers for compulsive drug seeking and drug taking are located in affective brain circuits, circuits that are structured and patterned by learning with repeated activation. These deep processes exhibit significant resistance to control by our cognitive faculties. The general consensus is that addiction arises from mechanisms that overvalue the magnitude of reward, discount the associated risks, and thereby bias individuals towards compulsive pursuit of addictive drugs. Behavioral disruption and dependence appear to arise at the intersection of a number of connected but separate phenomena: expectations for the occurrence of specific events, behaviors that seek encounters with them, the ability to notice and learn nonrandom, co-occurring conditions, the prediction and valuation of consequences, the forming of enduring memories, and the drivers of focused behavior through compulsion, habits, and acquired routines. It is important to recognize that each one of these individual faculties are present and well developed across the entire phylogenetic tree of bilateral metazoans. The goal of this special volume is dedicated to exploring the degree to which inherent elements can account for addiction and addiction-associated phenomena. In much of the literature on addiction, the underlying processes are often viewed as distinctly mammalian, arising, in part, from the strong cognitive capacities of this taxon. Some phenomena may even be regarded to exist only in primates, or even solely in humans. This supposition arises from the fact that studies are conducted almost exclusively in mammals and primates, while evolutionary antecedents of the behavior are rarely considered. A more comprehensive perspective that examines drug reward and reinforcement in a wider range of organisms demonstrates that many of the component traits are actually well developed across the greater metazoan lineage, and they may well predate the emergence of a mammalian clade by a wide margin. The collection of papers assembled here supports the notion that the capacity to associate cues and quences has not arisen in mammals de novo. Rather, the neural mechanisms for detecting contingencies and for predicting future outcomes are very deeply rooted across broad phylogenetic divisions. Our understanding of an ability to associate paired events has been enriched by work in invertebrate preparations in both classical and operant conditioning scenarios [Cook and Carew, 1986, 1989a, 1989b]. The ability to learn allows us to connect cues and behavioral actions to their associated consequences. Pavlovian conditioning enriches surrounding cues with predictive value. Outcomes with positive valence generate appetitive responses and approach to the associated cues, while those perceived as aversive bring cue avoidance and withdrawal. Humans are not the only life forms capable of such short- and long-term modulations of behavior

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2019

Memristor design rules for dynamic learning and edge processing applications

The ability to dynamically learn and adapt to changes in the environment is one of the hallmarks of biological systems. In this work, we identify the subset of the design space of memristive materials that is optimal for dynamic learning applications. Using an architecture inspired on the learning center of the insect brain, we implement a model system consisting of a discrete implementation of spiking neurons where dynamic learning takes place on a set of plastic synapses formed by memristor pairs in a crossbar array. Using two separate benchmarks, one comprising the dynamic learning of the Modified National Institute of Standards and Technology dataset and another one targeting one shot learning, we have identified the key properties that memristive materials should have to be optimal dynamic learners. The results obtained show that a fine degree of control of the memristor internal state is key to achieve high classification accuracy during dynamic learning but that within this optimal region learning is extremely robust both to device variability and to errors in the writing of the internal state, in all cases allowing for 2 sigma variations greater than 40% without significant loss of accuracy, hence overcoming two of the perceived limitations of memristors. By additionally requiring that learning takes place concurrently to information processing, we are able to derive a set constraints to the memristor dynamics.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Multi-contrast machine learning improves schistosomiasis diagnostic performance

Schistosomiasis currently affects over 250 million people and remains a public health burden despite ongoing global control efforts. Conventional microscopy is a practical tool for diagnosis and screening ofSchistosoma haematobium, but identification of eggs requires a skilled microscopist. Here we present a machine learning (ML)-based strategy for automated detection ofS. haematobiumthat combines two imaging contrasts, brightfield (BF) and darkfield (DF), to improve diagnostic performance. We collected BF and DF images of urine samples, many of them containingS. haematobiumeggs, during two different field studies in Côte d’Ivoire using a mobile phone-based microscope, the SchistoScope. We then trained separate egg-detection ML models and compared the patient-level performance of BF and DF models alone to combinations of BF and DF models, using annotations from trained microscopists as the gold standard. We found that models trained on DF images, and almost all BF and DF combinations, performed significantly better than models trained on BF images only. When models were trained on images from the first field study (n = 349 patients, 748 images of each contrast), patient-level classification performance on patient images from the second study (n = 375 patients, 752 images of each contrast) met the WHO Diagnostic Target Product Profile (TPP) sensitivity and specificity for the monitoring and evaluation use case (sensitivity for all models and combinations was >75% when evaluated at a confidence score threshold that resulted in specificity >96.5%). When we used images from both field studies for the training set, performance of the models was improved. Overall, this work shows that the use of DF and BF increases the performance of ML models on images from devices with low-cost optics, while retaining the portability, power, and time-to-results of the WHO’s diagnostic TPP. DF requires no additional sample preparation and does not increase the complexity of the imaging system. It thus offers a practical means to improve performance of automated diagnostics forS. haematobiumas well as other microscopy-based diagnostics.

Infectious Diseases↗

DOE OSTI2023

Predicting the superconducting critical temperature in transition metal carbides and nitrides using machine learning

Transition metal carbides and nitrides have unique mechanical and chemical characteristics. At low temperatures many of them also exhibit superconductivity, which can be controlled by substitutions into both the transition metal and carbon/nitrogen sites. To investigate the factors governing the superconducting state, we apply machine learning methods. Here we collected a dataset containing 147 materials, which was used to create a pipeline for predicting their superconducting critical temperature. When this pipeline is applied to a randomly selected test set, it shows a good performance, with of 0.82 and RMSE of 1.9 K. To explore the limits of the machine learning approach, we also use it to predict entire substitution series within the dataset. This represents a realistic test for the predictive models, which can be extremely useful when applied to new substitutions in materials systems. The performance of the pipeline in this case is much more uneven, with good predictions for some series, while for others the model shows minimal predictive power. We discuss possible reasons for these results, as well as methods to estimate the performance of machine learning on new substitution series.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

NASA NTRS2007

Lessons Learned from the Node 1 Sample Delivery Subsystem Design

This paper will provide an overview of the International Space Station (ISS) Environmental Control and Life Support (ECLS) design of the Node 1 Sample Delivery Subsystem (SDS) and it will document some of the lessons that have been learned to date for this part of the subsystem.

Williams, David E.↗

NASA NTRS2002

Spatial learning and memory is preserved in rats after early development in a microgravity environment

This study evaluated the cognitive mapping abilities of rats that spent part of their early development in a microgravity environment. Litters of male and female Sprague-Dawley rat pups were launched into space aboard the National Aeronautics and Space Administration space shuttle Columbia on postnatal day 8 or 14 and remained in space for 16 days. These animals were designated as FLT groups. Two age-matched control groups remained on Earth: those in standard vivarium housing (VIV) and those in housing identical to that aboard the shuttle (AGC). On return to Earth, animals were tested in three different tasks that measure spatial learning ability, the Morris water maze (MWM), and a modified version of the radial arm maze (RAM). Animals were also tested in an open field apparatus to measure general activity and exploratory activity. Performance and search strategies were evaluated in each of these tasks using an automated tracking system. Despite the dramatic differences in early experience, there were remarkably few differences between the FLT groups and their Earth-bound controls in these tasks. FLT animals learned the MWM and RAM as quickly as did controls. Evaluation of search patterns suggested subtle differences in patterns of exploration and in the strategies used to solve the tasks during the first few days of testing, but these differences normalized rapidly. Together, these data suggest that development in an environment without gravity has minimal long-term impact on spatial learning and memory abilities. Any differences due to development in microgravity are quickly reversed after return to earth normal gravity.

NASA Discipline Neuroscience↗

DOE OSTI2022

Multifidelity Ensemble Kalman Filtering Using Surrogate Models Defined by Theory-Guided Autoencoders

Data assimilation is a Bayesian inference process that obtains an enhanced understanding of a physical system of interest by fusing information from an inexact physics-based model, and from noisy sparse observations of reality. The multifidelity ensemble Kalman filter (MFEnKF) recently developed by the authors combines a full-order physical model and a hierarchy of reduced order surrogate models in order to increase the computational efficiency of data assimilation. The standard MFEnKF uses linear couplings between models, and is statistically optimal in case of Gaussian probability densities. This work extends the MFEnKF into to make use of a broader class of surrogate model such as those based on machine learning methods such as autoencoders non-linear couplings in between the model hierarchies. We identify the right-invertibility property for autoencoders as being a key predictor of success in the forecasting power of autoencoder-based reduced order models. We propose a methodology that allows us to construct reduced order surrogate models that are more accurate than the ones obtained via conventional linear methods. Numerical experiments with the canonical Lorenz'96 model illustrate that nonlinear surrogates perform better than linear projection-based ones in the context of multifidelity ensemble Kalman filtering. We additionality show a large-scale proof-of-concept result with the quasi-geostrophic equations, showing the competitiveness of the method with a traditional reduced order model-based MFEnKF.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Network Reconfiguration for Enhanced Operational Resilience Using Reinforcement Learning

This paper proposes a reinforcement learning-based approach for distribution network reconfiguration(DNR) to enhance the resilience of the electric power supply. Resilience enhancements usually require solving large-scale stochastic optimization problems that are computationally expensive and sometimes infeasible. The exceptional performance of reinforcement learning techniques has encouraged their adoption in various power system control studies, specifically resilience-based real-time applications. In this paper, a single agent framework is developed using an Actor-Critic algorithm (ACA) to determine statuses of tie-switches in a distribution feeder impacted by an extreme weather event. The proposed approach provides a fast-acting control algorithm that reconfigures the feeder topology to reduce or even avoid load shedding. The problem is formulated as a discrete Markov decision process in such a way that a system state captures the system topology and its operational characteristics. An action is made to open or close a specific set of tie-switches after which a reward is calculated to evaluate the practicality and advantage of that action. The iterative Markov process is used to train the proposed ACA under diverse failure scenarios and is demonstrated on the 33-node distribution feeder system. Results show the capability of the proposed ACA to determine proper switching action of tie-switches with accuracy exceeding 93%.

actor critic↗

DOE OSTI2023

MHD mode tracking using high-speed cameras and deep learning

Abstract We present a new algorithm to track the amplitude and phase of rotating magnetohydrodynamic (MHD) modes in tokamak plasmas using high speed imaging cameras and deep learning. This algorithm uses a convolutional neural network (CNN) to predict the amplitudes of the n = 1 sine and cosine mode components using solely optical measurements from one or more cameras. The model was trained and tested on an experimental dataset consisting of camera frame images and magnetic-based mode measurements from the High Beta Tokamak - Extended Pulse (HBT-EP) device, and it outperformed other, more conventional, algorithms using identical image inputs. The effect of different input data streams on the accuracy of the model’s predictions is also explored, including using a temporal frame stack or images from two cameras viewing different toroidal regions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2023

The ARENA Test Bed – A Versatile Resource for I&C Development and Validation

The Accelerated and Real-time Experimental Nodal Assessment (ARENA) Test Bed at the Pacific Northwest National Laboratory (PNNL) is a versatile resource for development and validation of instrumentation and control (I&C) technologies. This capability was created to facilitate in-situ testing of nuclear electrical cables in various simulated operational environments. Using cable trays, a control box, and selected test components, low voltage cables can be staged to experience local adverse environments such as elevated temperature and water immersion. Cable condition can be continuously monitored over time to track the effect of local stresses using nondestructive assessment tools. A heads-up display (ARENA TV) plots key data in real-time for users. The ARENA Test Bed has recently been used to evaluate the potential for spread spectrum time domain reflectometry (SSTDR) to monitor thermal aging of a portion of live cable powering a three-phase motor. The arrangement provided the opportunity to directly compare the performance of the novel online SSTDR method with offline results from the more standard frequency domain reflectometry (FDR) method. The ability of SSTDR and FDR to identify the presence of water in immersed shielded and unshielded cables and to detect ground faults was also assessed. A digital twin is being developed to track and predict FDR signals from a thermally aging conceptual cable region to compare with measured signals from the ARENA physical counterpart. The test bed concept addresses an important need in nuclear I&C monitoring tool development. New tools and techniques can be developed in the test bed and validated versus known methods and physical measurements. Digital twins and machine learning engines can be populated with measured data in a controlled environment that would not be readily available in the actual nuclear power plant. Proposed monitoring strategies can be confirmed for effectiveness through objective evaluation. It is anticipated that the PNNL ARENA Test Bed will be a valuable resource in advancing nuclear plant instrumentation.

nuclear electrical cables, ARENA Test Bed, conditi↗

NASA NTRS1988

Emulating a flexible space structure: Modeling

Control Dynamics, in conjunction with Marshall Space Flight Center, has participated in the modeling and testing of Flexible Space Structures. Through the series of configurations tested and the many techniques used for collecting, analyzing, and modeling the data, many valuable insights have been gained and important lessons learned. This paper discusses the background of the Large Space Structure program, Control Dynamics' involvement in testing and modeling of the configurations (especially the Active Control Technique Evaluation for Spacecraft (ACES) configuration), the results from these two processes, and insights gained from this work.

Waites, H. B.↗

NASA NTRS2010

Inspiring the Next Generation in Space Life Sciences

Competitive summer internships in space life sciences at NASA are awarded to college students every summer. Each student is aligned with a NASA mentor and project that match his or her skills and interests, working on individual projects in ongoing research activities. The interns consist of undergraduate, graduate, and medical students in various majors and disciplines from across the United States. To augment their internship experience, students participate in the Space Life Sciences Summer Institute (SLSSI). The purpose of the Institute is to offer a unique learning environment that focuses on the current biomedical issues associated with human spaceflight; providing an introduction of the paradigms, problems, and technologies of modern spaceflight cast within the framework of life sciences. The Institute faculty includes NASA scientists, physicians, flight controllers, engineers, managers, and astronauts; and fosters a multi-disciplinary science approach to learning with a particular emphasis on stimulating experimental creativity and innovation within an operational environment. This program brings together scientists and students to discuss cutting-edge solutions to problems in space physiology, environmental health, and medicine; and provides a familiarization of the various aspects of space physiology and environments. In addition to the lecture series, behind-the-scenes tours are offered that include the Neutral Buoyancy Laboratory, Mission Control Center, space vehicle training mockups, and a hands-on demonstration of the Space Shuttle Advanced Crew Escape Suit. While the SLSSI is managed and operated at the Johnson Space Center in Texas, student interns from the other NASA centers (Glenn and Ames Research Centers, in Ohio and California) also participate through webcast distance learning capabilities.

Hayes, Judith↗

DOE OSTI2019

Quantifying Climate and Catchment Control on Hydrological Drought in the Continental United States

The evolution of hydrological drought events is a result of complex (nonlinear) interactions between climate and catchment processes. To investigate such nonlinear relationship, we integrated a machine learning modeling framework based on the random forest (RF) algorithms with an interpretation framework to quantify the role of climate and catchment controls on hydrological drought. More particularly, our framework interprets a built RF machine-learning model to identify dominant variables and visualize their functional dependence and interaction effects on hydrological drought characteristics utilizing concepts of minimal depth, interactive depth, and partial dependence. We test our proposed modeling framework based on a set of 652 continental United States catchments with minimal human interference for a period of 1979–2010. Application of this framework indicated presence of three distinct drought regimes, which includes, Regime 1: droughts with longer duration, less frequent and lesser intensity; Regime 2: droughts with moderate duration, moderate frequency, and moderate intensity; and Regime 3: droughts with shorter duration, more frequent, and more intense. RF algorithm was able to accurately model the drought characteristics (intensity, duration, and number of events) for all the three drought regimes as a function of selected variables. It was observed that the type of dominant variables as well as their nonlinear functional relationship with hydrological droughts characteristics can vary between three selected regimes. Finally, our interpretation framework indicated that catchment characteristics have a significant role in controlling the hydrologic drought for catchments (regime 1), whereas both climate and catchment characteristics control hydrological drought in regimes 2 and 3.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRSDate not supplied

Transient Optimization of a Gas Turbine Engine

Gas turbine engines are the primary power plants for modern commercial aircraft. Transients prompted by significant changes in thrust or power demand are common and unavoidable. Extreme transient scenarios such as those associated with a go-around during a landing attempt are possible and must be accounted for in the design of the engine and its controller. Engine transients tend to cause a reduction in compressor operability margin, which must be addressed by the engine control system and accounted for in the engine design to prevent events such as compressor stall/surge and combustor blow out. Transient operability concerns typically lead to compromises in the engine design that sacrifice efficiency and/or limit responsiveness. Transient operability is typically managed by logic that limits the fuel flow command. If this logic is not optimized, then the potential for valuable performance could be lost. This study presents a strategy for optimizing the transient limit logic and proposes a strategy for updating the control logic over the lifespan of the engine. The results demonstrate significant improvements in transient operability. For example, of the results at sea level static conditions demonstrated a 31% reduction in the usage of the high pressure compressor operability stack during a snap acceleration transient. Furthermore, a reinforcement learning algorithm is demonstrated to modify the transient logic as the engine degrades to minimize response time while respecting a prescribed compressor operability margin limit. A simple demonstration of the reinforcement learning algorithm resulted in a thrust response time reduction of ~11.8%.

transient↗

NASA NTRSDate not supplied

Transient Optimization of a Gas Turbine Engine

Gas turbine engines are the primary power plants for modern commercial aircraft. Transients prompted by significant changes in thrust or power demand are common and unavoidable. Extreme transient scenarios such as those associated with a go-around during a landing attempt are possible and must be accounted for in the design of the engine and its controller. Engine transients tend to cause a reduction in compressor operability margin, which must be addressed by the engine control system and accounted for in the engine design to prevent events such as compressor stall/surge and combustor blow out. Transient operability concerns typically lead to compromises in the engine design that sacrifice efficiency and/or limit responsiveness. Transient operability is typically managed by logic that limits the fuel flow command. If this logic is not optimized, then the potential for valuable performance could be lost. This study presents a strategy for optimizing the transient limit logic and proposes a strategy for updating the control logic over the lifespan of the engine. The results demonstrate significant improvements in transient operability. For example, of the results at sea level static conditions demonstrated a 31% reduction in the usage of the high pressure compressor operability stack during a snap acceleration transient. Furthermore, a reinforcement learning algorithm is demonstrated to modify the transient logic as the engine degrades to minimize response time while respecting a prescribed compressor operability margin limit. A simple demonstration of the reinforcement learning algorithm resulted in a thrust response time reduction of ~11.8%.

transient↗

NASA NTRSDate not supplied

Transient Optimization of a Gas Turbine Engine

Gas turbine engines are the primary power plants for modern commercial aircraft. Transients prompted by significant changes in thrust or power demand are common and unavoidable. Extreme transient scenarios such as those associated with a go-around during a landing attempt are possible and must be accounted for in the design of the engine and its controller. Engine transients tend to cause a reduction in compressor operability margin, which must be addressed by the engine control system and accounted for in the engine design to prevent events such as compressor stall/surge and combustor blow out. Transient operability concerns typically lead to compromises in the engine design that sacrifice efficiency and/or limit responsiveness. Transient operability is typically managed by logic that limits the fuel flow command. If this logic is not optimized, then the potential for valuable performance could be lost. This study presents a strategy for optimizing the transient limit logic and proposes a strategy for updating the control logic over the lifespan of the engine. The results demonstrate significant improvements in transient operability. For example, of the results at sea level static conditions demonstrated a 31% reduction in the usage of the high pressure compressor operability stack during a snap acceleration transient. Furthermore, a reinforcement learning algorithm is demonstrated to modify the transient logic as the engine degrades to minimize response time while respecting a prescribed compressor operability margin limit. A simple demonstration of the reinforcement learning algorithm resulted in a thrust response time reduction of ~11.8%.

transient↗