Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning control”

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 1,297 records · Page 72

Bugs, Microbes, Biofuels, and Coffee

​​Berkeley Lab scientist Javier A. Ceja-Navarro discusses how his team is learning to utilize microbes that live inside the digestive tracts of insects for pest control, improved agriculture, and energy production.

59 BASIC BIOLOGICAL SCIENCES↗

DeepPhenoMem V1.0: deep learning modelling of canopy greenness dynamics accounting for multi-variate meteorological memory effects on vegetation phenology

Abstract. Vegetation phenology plays a key role in controlling the seasonality of ecosystem processes that modulate carbon, water and energy fluxes between the biosphere and atmosphere. Accurate modelling of vegetation phenology in the interplay of Earth's surface and the atmosphere is thus crucial to understand how the coupled system will respond to and shape climatic changes. Phenology is controlled by meteorological conditions at different timescales: on the one hand, changes in key meteorological variables (temperature, water, radiation) can have immediate effects on the vegetation development; on the other hand, phenological changes can be driven by past environmental conditions, known as memory effects. However, the processes governing meteorological memory effects on phenology are not completely understood, resulting in their limited performance of vegetation phenology represented in land surface models. A deep learning model, specifically a long short-term memory network (LSTM), has the potential to capture and model the meteorological memory effects on vegetation phenology. Here, we apply the LSTM to model the vegetation phenology using meteorological drivers and high-temporal-resolution canopy greenness observations through digital repeat photography by the PhenoCam network. We compare a multiple linear regression model, a no-memory-effect LSTM model and a full-memory-effect LSTM model to predict the whole seasonal greenness trajectory and the corresponding phenological transition dates across 50 sites and 317 site years during 2009–2018, covering deciduous broadleaf forests, evergreen needleleaf forests and grasslands. Results show that the deep learning model outperforms the multiple linear regression model, and the full-memory-effect LSTM model performs better than the no-memory-effect model for all three plant function types (median R2 of 0.878, 0.957 and 0.955 for broadleaf forests, evergreen needleleaf forests and grasslands). We also find that the full-memory-effect LSTM model is capable of predicting the seasonal dynamic variations of canopy greenness and reproducing trends in shifting phenological transition dates. We also performed a sensitivity analysis of the full-memory-effect LSTM model to assess its plausibility, revealing its coherence with established knowledge of vegetation phenology sensitivity to meteorological conditions, particularly changes in temperature. Our study highlights that (1) multi-variate meteorological memory effects play a crucial role in vegetation phenology, and (2) deep learning opens up new avenues for improving the representation of vegetation phenological processes in land surface models via a hybrid modelling approach.

Geology↗

Anomalous electroweak physics unraveled via evidential deep learning

The ever-growing ecosystem of beyond standard model (BSM) calculations and parametrizations has motivated the development of systematic methods for making quantitative cross-comparisons over the wide range of possible models, especially with controllable uncertainties. In this setting, the language of uncertainty quantification (UQ) furnishes useful metrics for assessing statistical overlaps and discrepancies among BSM and related models. In this study, we leverage recent machine learning (ML) developments in evidential deep learning (EDL) for UQ to separate data (aleatoric) and knowledge (epistemic) uncertainties in a model-discrimination setting. We construct several potentially BSM-motivated scenarios for the anomalous electroweak interaction (AEWI) of neutrinos with nucleons in deep inelastic scattering ( v DIS). These scenarios are then quantitatively mapped, as a demonstration, alongside Monte Carlo replicas of the CT18 PDFs used to calculate the $\varDelta \chi ^{2}$ statistic for a typical multi-GeV v DIS experiment, CDHSW. Our framework effectively highlights areas of model agreement and provides a classification of out-of-distribution (OOD) samples. By offering the opportunity to quantitatively understand model overlaps, the approach presented in this work can help facilitate efficient BSM model exploration and exclusion for future New Physics searches.

AI↗

Comparative Studies of the Structural and Transport Properties of Molten Salt FLiNaK Using the Machine-Learned Neural Network and Reparametrized Classical Forcefields

Despite surging interest in molten salt reactors and thermal storage systems, knowledge of the physicochemical properties of molten salts are still inadequate due to demanding experiments that require high temperature, impurity control, and corrosion mitigation. Therefore, the ability to predict these properties for molten salts from first-principles computations is urgently needed. Herein, we developed and compared a machine-learned neural network force field (NNFF) and a reparametrized rigid ion model (RIM) for a prototypical molten salt LiF–NaF–KF (FLiNaK). We found that NNFF was able to reproduce both the structural and transport properties of the molten salt with first-principles accuracy and classical-MD computational efficiency. Furthermore, the correlation between the local atomic structures and the dynamics was identified by comparing with RIMs, suggesting the significance of polarization of anions implicitly embedded in the NNFF. Furthermore, this work demonstrated a computational framework that can facilitate the screening of molten salts with different chemical compositions, impurities, and additives, and at different thermodynamic conditions suitable for the next-generation nuclear reactors and thermal energy storage facilities.

36 MATERIALS SCIENCE↗

Accelerating Discovery of Solid‐State Thin‐Film Metal Dealloying for 3D Nanoarchitecture Materials Design through Laser Thermal Gradient Treatment

Thin‐film solid‐state metal dealloying (thin‐film SSMD) is a promising method for fabricating nanostructures with controlled morphology and efficiency, offering advantages over conventional bulk materials processing methods for integration into practical applications. Although machine learning (ML) has facilitated the design of dealloying systems, the selection of key thermal treatment parameters for nanostructure formation remains largely unknown and dependent on experimental trial and error. To overcome this challenge, a workflow enabling high‐throughput characterization of thermal treatment parameters is demonstrated using a laser‐based thermal treatment to create temperature gradients on single thin‐film samples of Nb‐Al/Sc and Nb‐Al/Cu. This continuous thermal space enables observation of dealloying transitions and the resulting nanostructures of interest. Through synchrotron X‐ray multimodal and high‐throughput characterization, critical transitions and nanostructures can be rapidly captured and subsequently verified using electron microscopy. The key temperatures driving chemical reactions and morphological evolutions are clearly identified. While the oxidation may influence nanostructure formation during thin‐film treatment, the dealloying process at the dealloying front involves interactions solely between the dealloying elements, highlighting the availability and viability of the selected systems. Further, this approach enables efficient exploration of the dealloying process and validation of ML predictions, thereby accelerating the discovery of thin‐film SSMD systems with targeted nanostructures.

36 MATERIALS SCIENCE↗

Modifications to the JET Shattered Pellet Injector to Optimize Disruption Mitigation Experiments for Supporting ITER’s DMS Design

Shattered pellet injection (SPI) experiments on Joint European Torus (JET) are an important element in determining the physics basis for mitigating disruptions in ITER. Here, the initial design of the JET SPI system included three barrels to produce pellets with diameters of 4.5, 8.1, and 12.5 mm. The variability of the pellet speed by operating with and without a mechanical punch was limited and led to poor pellet integrity, so the mechanical punch was removed. Fragment size distribution is a function of pellet speed and the desire to change the resulting fragment size distribution was not originally a requirement. After the first set of SPI experiments on JET, different pellet sizes were considered to enable dual injection experiments with identical pellet diameters. It was also determined that speed control is necessary to improve experimental repeatability and to determine how the fragment size distribution impacts mitigation performance. Two barrels were fabricated to form pellets of 10 mm diameter and a third to form an 8.1 mm diameter pellet. New propellant valves were also fabricated and characterized to improve repeatability and overall performance. To have fine control of pellet speed, inserts to reduce the breech volume were fabricated and installed. Laboratory testing was conducted to ensure pellet release and provide a comparison of propellant gas delivered versus pellet speeds for a range of pellet types and mixtures. This article will also discuss how lessons learned from the JET SPI modifications can be applied to other SPI systems, such as the ITER SPI system, as controlling pellet release with the least amount of propellant gas is essential for optimal SPI effectiveness.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Transforming Aeration Energy in Water Resource Recovery Facilities (WRRFs) through Suboxic Nitrogen Removal (Final Report)

The objective of this project was to advance two key technological components—aeration control strategies and process design methodologies—to support the development and broader adoption of suboxic biological nitrogen removal (SBNR). The project focused on achieving the following three goals: • Enhance Model Predictive Control (MPC) Technology: Advance the DO/Nmaster MPC platform from its initial 2018 pilot deployment at the Chico Water Resource Recovery Facility in California to full-scale integration. This included partnering with a blower technology commercialization partner and incorporating machine learning (ML) capabilities to enable nationwide deployment. • Bridge Knowledge Gaps in SBNR Process Design: Address fundamental gaps in SBNR process understanding through controlled pilot-scale testing at a dedicated pilot facility. These efforts supported the development of robust kinetic models to inform reliable SBNR control, operational strategies, and design frameworks. • Demonstrate Full-Scale Implementation of Low DO/SBNR with ML: Transition low dissolved oxygen (DO)/SBNR coupled with ML from pilot-scale trials to full-scale demonstration in flow-through biological nutrient removal (BNR) systems, with the goal of enabling scalable, nationwide adoption in activated sludge treatment processes. The project included demonstration of SBNR at the pilot scale as performed by Hampton Roads Sanitation District (HRSD) and at the full-scale as performed by the Los Angeles County Sanitation Districts' (LACSD) Pomona Water Reclamation Plant (POWRP).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Releasing chemical energy in spatiallyprogrammed ferroelectrics

Chemical energy ferroelectrics are generally solid macromolecules showing spontaneous polarization and chemical bonding energy. These materials still suffer drawbacks, including the limited control of energy release rate, and thermal decomposition energy well below total chemical energy. To overcome these drawbacks, we report the integrated molecular ferroelectric and energetic material from machine learning-directed additive manufacturing coupled with the ice-templating assembly. The resultant aligned porous architecture shows a low density of 0.35 g cm -3 , polarization-controlled energy release, and an anisotropic thermal conductivity ratio of 15. Thermal analysis suggests that the chlorine radicals react with macromolecules enabling a large exothermic enthalpy of reaction (6180 kJ kg -1 ). In addition, the estimated detonation velocity of molecular ferroelectrics can be tuned from 6.69 ± 0.21 to 7.79 ± 0.25 km s -1 by switching the polarization state. These results provide a pathway toward spatially programmed energetic ferroelectrics for controlled energy release rates.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Deep Reinforcement Learning for Distribution System Cyber Attack Defense with DERs

The use of smart inverter capabilities of distributed energy resources (DERs) enhances the grid reliability but in the meanwhile exhibits more vulnerabilities to cyber-attacks. This paper proposes a deep reinforcement learning (DRL)-based defense approach. The defense problem is reformulated as a Markov decision making process to control DERs and minimizing load shedding to address the voltage violations caused by cyber-attacks. The original soft actor-critic (SAC) method for continuous actions has been extended to handle discrete and continuous actions for controlling DERs' setpoints and loadshedding scenarios. Numerical comparison results with other control approaches, such as Volt-VAR and Volt-Watt on the modified IEEE 33-node, show that the proposed method can achieve better voltage regulation and have less power losses in the presence of cyber-attacks.

active distribution systems↗

Towards Secure Autonomous Vehicles: An Integrated Edge and Multi-Modal Machine Learning Framework for Intrusion Detection

Autonomous vehicles (AVs) are vulnerable to cyberattacks targeting both internal communication networks and external perception sensors. While edge-based intrusion de- tection for Controller Area Network (CAN) buses offers real-time protection, it cannot detect cross-modal threats. Conversely, multi-modal fusion approaches improve coverage but often lack efficiency for in-vehicle deployment. This thesis integrates two complemen- tary solutions: (1) a lightweight, edge-deployable machine learning framework for CAN bus intrusion detection, and (2) a late-fusion system combining CAN FD and LiDAR data. Together, they form a hierarchical defense capable of handling single-modality and coordi- nated attacks. Simulations show that CAN-only models reach 93% accuracy on simulated DoS, spoofing, replay, and fuzzy attacks, while the fusion system achieves 0.87 AUC and 0.82 F1-score at 2 ms latency. This unified framework establishes a scalable, explainable, and field-ready strategy for AV cybersecurity.

97 MATHEMATICS AND COMPUTING↗

Prevention of a wrong-location misadministration through the use of an intradepartmental incident learning system

Purpose: A series of examples are presented in which potential errors in the delivery of radiation therapy were prevented through use of incident learning. These examples underscore the value of reporting near miss incidents. Methods: Using a departmental incident learning system, eight incidents were noted over a two-year period in which fields were treated 'out-of-sequence,' that is, fields from a boost phase were treated, while the patient was still in the initial phase of treatment. As a result, an error-prevention policy was instituted in which radiation treatment fields are 'hidden' within the oncology information system (OIS) when they are not in current use. In this way, fields are only available to be treated in the intended sequence and, importantly, old fields cannot be activated at the linear accelerator control console. Results: No out-of-sequence treatments have been reported in more than two years since the policy change. Furthermore, at least three near-miss incidents were detected and corrected as a result of the policy change. In the first two, the policy operated as intended to directly prevent an error in field scheduling. In the third near-miss, the policy operated 'off target' to prevent a type of error scenario that it was not directly intended to prevent. In this incident, an incorrect digitally reconstructed radiograph (DRR) was scheduled in the OIS for a patient receiving lung cancer treatment. The incorrect DRR had an isocenter which was misplaced by approximately two centimeters. The error was a result of a field from an old plan being scheduled instead of the intended new plan. As a result of the policy described above, the DRR field could not be activated for treatment however and the error was discovered and corrected. Other quality control barriers in place would have been unlikely to have detected this error. Conclusions: In these examples, a policy was adopted based on incident learning, which prevented several errors, at least one of which was potentially severe. These examples underscore the need for a rigorous, systematic incident learning process within each clinic. The experiences reported in this technical note demonstrate the value of near-miss incident reporting to improve patient safety.

60 APPLIED LIFE SCIENCES↗

GATEWAY Report Brief: Evaluating Tunable LED Lighting in the Swedish Medical Behavioral Health Unit

Summary of a GATEWAY report evaluation of a tunable LED lighting system installed in the new Swedish Medical Behavioral Health Unit in Seattle that incorporates color-tunable luminaires in common areas, and uses advanced controls for dimming and color tuning, with the goal of providing a better environment for staff and patients. The report reviews the design of the tunable lighting system, summarizes two sets of measurements, and discusses the circadian, energy, and commissioning implications as well as lessons learned from the project.

59 BASIC BIOLOGICAL SCIENCES↗

High-fidelity retrieval from instantaneous line-of-sight returns of nacelle-mounted lidar including supervised machine learning

Abstract. Wind turbine applications that leverage nacelle-mounted Doppler lidar are hampered by several sources of uncertainty in the lidar measurement, affecting both bias and random errors. Two problems encountered especially for nacelle-mounted lidar are solid interference due to intersection of the line of sight with solid objects behind, within, or in front of the measurement volume and spectral noise due primarily to limited photon capture. These two uncertainties, especially that due to solid interference, can be reduced with high-fidelity retrieval techniques (i.e., including both quality assurance/quality control and subsequent parameter estimation). Our work compares three such techniques, including conventional thresholding, advanced filtering, and a novel application of supervised machine learning with ensemble neural networks, based on their ability to reduce uncertainty introduced by the two observed nonideal spectral features while keeping data availability high. The approach leverages data from a field experiment involving a continuous-wave (CW) SpinnerLidar from the Technical University of Denmark (DTU) that provided scans of a wide range of flows both unwaked and waked by a field turbine. Independent measurements from an adjacent meteorological tower within the sampling volume permit experimental validation of the instantaneous velocity uncertainty remaining after retrieval that stems from solid interference and strong spectral noise, which is a validation that has not been performed previously. All three methods perform similarly for non-interfered returns, but the advanced filtering and machine learning techniques perform better when solid interference is present, which allows them to produce overall standard deviations of error between 0.2 and 0.3 m s−1, or a 1 %–22 % improvement versus the conventional thresholding technique, over the rotor height for the unwaked cases. Between the two improved techniques, the advanced filtering produces 3.5 % higher overall data availability, while the machine learning offers a faster runtime (i.e., ∼ 1 s to evaluate) that is therefore more commensurate with the requirements of real-time turbine control. The retrieval techniques are described in terms of application to CW lidar, though they are also relevant to pulsed lidar. Previous work by the authors (Brown and Herges, 2020) explored a novel attempt to quantify uncertainty in the output of a high-fidelity lidar retrieval technique using simulated lidar returns; this article provides true uncertainty quantification versus independent measurement and does so for three techniques rather than one.

47 OTHER INSTRUMENTATION↗

A HPC Theory-Guided Machine Learning Cyberinfrastructure for Communicating Hydrometeorological Data Across Scales

High-resolution predictions of hydrometeorological variables are critical for supporting hydropower generation decisions and flood control at hydroelectric power plants. Traditional climate and hydrologic models rely on the numerical simulation of detailed physical processes. Therefore, running these simulations is time-, labor-, and computation-intensive. Improving the spatial and temporal resolution in these modeling outputs could lead to cubic increases in both the simulation time and computational demands, rendering high-resolution hydrometeorological predictions expensive and impractical. Many past studies apply the super resolution (SR) technique to downscale climate models using deep learners. However, deep learners are deemed “black-boxes,” as their derivation processes from low-resolution outputs to high-resolution outputs are often hidden. Their results are difficult for domain scientists to interpret and validate. Thus, there is a need for an exploratory machine learning approach that can partially integrate domain-specific theory and knowledge into the data-driven mapping process between simulation outputs of different spatial scales. The domain-specific theory and knowledge can be incorporated into the data model through an inductive approach in which process-related environmental variables are used and analyzed as key drivers (i.e., environmental surrogates) to reflect the complex physical processes. Many of these variables, such as land use land cover, soil types, topography, digital elevation, air temperature, and various watershed characteristics, can be directly measured through sensors or remote sensing techniques. Additionally, SR applications that can downscale hydrological and hydrodynamics models to efficiently produce high-resolution (1 m) flood depth grids are still rare. Since the flood depth grid can be used to support critical decisions for flood control operation at hydroelectric power plants, it is crucial to enable an SR-based capability for interpolating high-resolution flood inundation maps.

13 HYDRO ENERGY↗

International Linear Collider Accelerator Physics R&D

ILC work at Illinois has concentrated primarily on technical issues relating to the design of the accelerator. Because many of the problems to be resolved require a working knowledge of classical mechanics and electrodynamics, most of our research projects lend themselves well to the participation of undergraduate research assistants. The undergraduates in the group are scientists, not technicians, and find solutions to problems that, for example, have stumped PhD-level staff elsewhere. The ILC Reference Design Report calls for 6.7 km circumference damping rings (which prepare the beams for focusing) using “conventional” stripline kickers driven by fast HV pulsers. Our primary goal was to determine the suitability of the 16 MeV electron beam in the AØ region at Fermilab for precision kicker studies.We found that the low beam energy and lack of redundancy in the beam position monitor system complicated the analysis of our data. In spite of these issues we concluded that the precision we could obtain was adequate to measure the performance and stability of a production module of an ILC kicker, namely 0.5%. We concluded that the kicker was stable to an accuracy of ~2.0% and that we could measure this precision to an accuracy of ~0.5%. As a result, a low energy beam like that at AØ could be used as a rapid-turnaround facility for testing ILC production kicker modules. The ILC timing precision for arrival of bunches at the collision point is required to be 0.1 picosecond or better. We studied the bunch-to-bunch timing accuracy of a “phase detector” installed in AØ in order to determine its suitability as an ILC bunch timing device. A phase detector is an RF structure excited by the passage of a bunch. Its signal is fed through a 1240 MHz high-Q resonant circuit and then down-mixed with the AØ 1300 MHz accelerator RF. We used a kind of autocorrelation technique to compare the phase detector signal with a reference signal obtained from the phase detector’s response to an event at the beginning of the run. We determined that the device installed in our beam, which was instrumented with an 8-bit 500 MHz ADC, could measure the beam timing to an accuracy of 0.4 picoseconds. Simulations of the device showed that an increase in ADC clock rate to 2 GHz would improve measurement precision by the required factor of four. As a result, we felt that a device of this sort, assuming matters concerning dynamic range and long-term stability can be addressed successfully, would work at the ILC. Cost effective operation of the ILC will demand highly reliable, fault tolerant and adaptive solutions for both hardware and software. The large numbers of subsystems and large multipliers associated with the modules in those subsystems will cause even a strong level of unit reliability to become an unacceptable level of system availability. An evaluation effort is underway to evaluate standards associated with high availability, and to guide ILC development with standard practices and well-supported commercial solutions. One area of evaluation involves the Advanced Telecom Computing Architecture (ATCA) hardware and software. We worked with an ATCA crate, processor monitors, and a small amount of ATCA circuit boards in order to develop a backplane “spy” board that would let us watch the ATCA backplane communications and pursue development of an inexpensive processor monitor that could be used as a physics-driven component of the crate-level controls system. We made good progress, and felt that we had determined a productive direction to extend this work. We felt that we had learned enough to begin designing a workable processor monitor chip if there were to be sufficient interest in ATCA shown by the ILC community. Fault recognition is a challenging issue in the crafting a high reliability controls system. With tens of thousands of independent processors running hundreds of thousands of critical processes, how can the system identify that a problem has arisen and determine the appropriate steps to take to correct, or compensate, for the failure? One possible solution might come through the use of the OpenClovis supervisory system, which runs on Linux processors and allows a select set of processors to monitor the behavior of individual processes and processors in a large, distributed controls network. We found that OpenClovis exhibited an irritating amount of sensitivity to the exact version of the Linux kernel running on the processors, and that it was poorly equipped to help us sort through problems that arose through conflicts so deep in the operating systems of the processors. But once this issue was addressed, we found that it performed as expected, recognizing crashes and process (and processor) failures.

43 PARTICLE ACCELERATORS↗

Deep Learning without Global Optimization by Random Fourier Neural Networks

Here we introduce a new training algorithm for deep neural networks that utilize random complex exponential activation functions. Our approach employs a Markov chain Monte Carlo sampling procedure to iteratively train network layers, avoiding global and gradient-based optimization while maintaining error control. It consistently attains the theoretical approximation rate for residual networks with complex exponential activation functions, determined by network complexity. Additionally, it enables efficient learning of multiscale and high-frequency features, producing interpretable parameter distributions. Despite using sinusoidal basis functions, we do not observe Gibbs phenomena in approximating discontinuous target functions.

97 MATHEMATICS AND COMPUTING↗