Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Performance Modeling”

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 685 records · Page 38
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Product consistency test results for the LAW Phase 4 gases

In this report, the Savannah River National Laboratory provides chemical analysis of Product Consistency Test (PCT) leachates from a series of simulated nuclear waste glasses fabricated at the Pacific Northwest National Laboratory (PNNL). The series included quenched and canister-centerline cooled (CCC) versions of the glasses. The resulting data will be used in the development of enhanced property/composition models for waste vitrification at Hanford. For some of the glass leachates, minor scatter among the triplicate values of some analytes were observed. For other leachates, there were more significant differences among the triplicate values. A review of the PCT data noted that there was little difference between the normalized values based on targeted or measured glass composition. Several of the study glasses have normalized concentration of element “i” (NCi) values that are greater than the Hanford Tank Waste Treatment and Immobilization Plant immobilized low-activity waste constraint of 4 g/L for boron (B), sodium (Na), and silicon (Si). The results of these glasses will help ensure the ability of advanced glass performance models to appropriately predict acceptable compositions. For the study glasses with NCi values exceeding 4 g/L, the CCC heat treatment samples had generally lower NCi values than quenched samples. The samples of the Environmental Assessment (EA) reference glass included with each PCT set had generally consistent NCi values. The release rates for boron (B), potassium (K), lithium (Li), sodium (Na), and silicon (Si) were highly correlated for the study glasses.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2021

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

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

artificial intelligence, deep learning, neural lan↗
DOE OSTI2025

Continued Testing and Modeling of the AirSquared All-Metal Tritium Scroll Pump

The implementation of fusion energy requires the processing of the deuterium-tritium mixture used to fuel the reaction. Many gas processing operations require either a gas-motive force or a pressure gradient across a system; both are achieved using vacuum pumps. However, because of the material challenges of working with tritium, specialized pumps are required that use only metal on wetted surfaces. This prevents tritium retention and degradation of materials such as oils and polymers and reduces the generation of tritiated waste. Typical gas handling systems for tritium operations involve metal bellows pumps, all-metal scroll pumps, and metal turbomolecular pumps, depending on the pressure requirements. With the industry standard Normetex Type 15 m 3 /h (typically referred to as the Normetex 15) pump no longer available, the fusion market requires viable alternatives. In this study, we test an American-made pump, the AirSquared V16H034A-C01, and compare its performance to the Normetex. A performance model of the AirSquared pump is also produced, which can be applied to general process models to generate an accurate description of pressures and flows through various unit operations.

08 HYDROGEN↗
DOE OSTI2021

Technical note: Uncertainties in eddy covariance CO 2 fluxes in a semiarid sagebrush ecosystem caused by gap-filling approaches

Abstract. Gap-filling eddy covariance CO2 fluxes is challenging at dryland sites due to small CO2 fluxes. Here, four machine learning (ML) algorithms including artificial neural network (ANN), k-nearest neighbors (KNNs), random forest (RF), and support vector machine (SVM) are employed and evaluated for gap-filling CO2 fluxes over a semiarid sagebrush ecosystem with different lengths of artificial gaps. The ANN and RF algorithms outperform the KNN and SVM in filling gaps ranging from hours to days, with the RF being more time efficient than the ANN. Performances of the ANN and RF are largely degraded for extremely long gaps of 2 months. In addition, our results suggest that there is no need to fill the daytime and nighttime net ecosystem exchange (NEE) gaps separately when using the ANN and RF. With the ANN and RF, the gap-filling-induced uncertainties in the annual NEE at this site are estimated to be within 16 g C m−2, whereas the uncertainties by the KNN and SVM can be as large as 27 g C m−2. To better fill extremely long gaps of a few months, we test a two-layer gap-filling framework based on the RF. With this framework, the model performance is improved significantly, especially for the nighttime data. Therefore, this approach provides an alternative in filling extremely long gaps to characterize annual carbon budgets and interannual variability in dryland ecosystems.

Yao, Jingyu↗
DOE OSTI2023

DeepAstroUDA: semi-supervised universal domain adaptation for cross-survey galaxy morphology classification and anomaly detection

Abstract Artificial intelligence methods show great promise in increasing the quality and speed of work with large astronomical datasets, but the high complexity of these methods leads to the extraction of dataset-specific, non-robust features. Therefore, such methods do not generalize well across multiple datasets. We present a universal domain adaptation method, DeepAstroUDA , as an approach to overcome this challenge. This algorithm performs semi-supervised domain adaptation (DA) and can be applied to datasets with different data distributions and class overlaps. Non-overlapping classes can be present in any of the two datasets (the labeled source domain, or the unlabeled target domain), and the method can even be used in the presence of unknown classes. We apply our method to three examples of galaxy morphology classification tasks of different complexities (three-class and ten-class problems), with anomaly detection: (1) datasets created after different numbers of observing years from a single survey (Legacy Survey of Space and Time mock data of one and ten years of observations); (2) data from different surveys (Sloan Digital Sky Survey (SDSS) and DECaLS); and (3) data from observing fields with different depths within one survey (wide field and Stripe 82 deep field of SDSS). For the first time, we demonstrate the successful use of DA between very discrepant observational datasets. DeepAstroUDA is capable of bridging the gap between two astronomical surveys, increasing classification accuracy in both domains (up to 40 % on the unlabeled data), and making model performance consistent across datasets. Furthermore, our method also performs well as an anomaly detection algorithm and successfully clusters unknown class samples even in the unlabeled target dataset.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

A Multiphysics Evaluation of Annular Uranium-Zirconium Metallic Fuels [Poster]

This study examines the performance of U-10Zr annular metallic fuel rodlets which were experimentally evaluated as part of the Advanced Fuels Campaign (AFC). The AFC mission is to develop novel fuel technologies and facilitate the implementation of those technologies by industry partners. A key objective is to improve steady-state and transient performance over current fuel types. The experiments of interest in this study included annular metallic U-Zr fuel rodlets within HT-9 cladding which were placed in SS-316 capsules and inserted in the Advanced Test Reactor (ATR). Certain mechanical and thermal conditions cannot be directly evaluated through experiments and fuel performance modeling is used to shed light on this evolution over time. In this study, BISON Multiphysics simulations are leveraged to investigate the state of the fuel system throughout and after the experimental conditions.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2023

Enhancing the representation of water management in global hydrological models

Abstract. This study enhances an existing global hydrological model (GHM), Xanthos, by adding a new water management module that distinguishes between the operational characteristics of irrigation, hydropower, and flood control reservoirs. We remapped reservoirs in the Global Reservoir and Dam (GRanD) database to the 0.5∘ spatial resolution in Xanthos so that a single lumped reservoir exists per grid cell, which yielded 3790 large reservoirs. We implemented unique operation rules for each reservoir type, based on their primary purposes. In particular, hydropower reservoirs have been treated as flood control reservoirs in previous GHM studies, while here, we determined the operation rules for hydropower reservoirs via optimization that maximizes long-term hydropower production. We conducted global simulations using the enhanced Xanthos and validated monthly streamflow for 91 large river basins, where high-quality observed streamflow data were available. A total of 1878 (296 hydropower, 486 irrigation, and 1096 flood control and others) out of the 3790 reservoirs are located in the 91 basins and are part of our reported results. The Kling–Gupta efficiency (KGE) value (after adding the new water management) is ≥ 0.5 and ≥ 0.0 in 39 and 81 basins, respectively. After adding the new water management module, model performance improved for 75 out of 91 basins and worsened for only 7. To measure the relative difference between explicitly representing hydropower reservoirs and representing hydropower reservoirs as flood control reservoirs (as is commonly done in other GHMs), we use the normalized root mean square error (NRMSE) and the coefficient of determination (R2). Out of the 296 hydropower reservoirs, the NRMSE is > 0.25 (i.e., considering 0.25 to represent a moderate difference) for over 44 % of the 296 reservoirs when comparing both the simulated reservoir releases and storage time series between the two simulations. We suggest that correctly representing hydropower reservoirs in GHMs could have important implications for our understanding and management of freshwater resource challenges at regional-to-global scales. This enhanced global water management modeling framework will allow the analysis of future global reservoir development and management from a coupled human–earth system perspective.

13 HYDRO ENERGY↗
DOE OSTI2020

Effects of surface runoff and infiltration partition methods on hydrological modeling: A comparison of four schemes in two watersheds in the Northeastern US

The ratio according to which the precipitation/snowmelt is divided into surface and subsurface water is of primary importance to watershed scale hydrological modeling. The present study compared four different surface runoff and infiltration partition methods in the Richards-equation-based SWAT model (RSWAT), i.e., daily curve number method (DC-RSWAT), hourly curve number method (HC-RSWAT), Green-Ampt method (GA-RSWAT), and effective infiltration capacity method (EIC-RSWAT). These four versions of RSWAT and a daily-curve-number-based SWAT (DC-SWAT) were used to simulate daily flow rate (from 2001 to 2015) at the outlets of the Tuckahoe Creek Watershed (TCW) and Greensboro Watershed (GW) of the Chesapeake Bay in Maryland. Parameter sensitivity analysis, calibration, and prediction uncertainty analysis were conducted. The results indicate that surface runoff and infiltration partition methods have pronounced impacts on model performance. Comparative analysis showed that DC-RSWAT outperformed other versions of RSWAT for both calibration (from 2001 to2007) and validation (from 2008 to 2015) periods in the two test watersheds. In general, DC-RSWAT achieved more accurate deterministic flow simulation and reliable uncertainty estimation than other versions. As such, daily-curve-number method is recommended for surface runoff and infiltration partition in RSWAT for simulating stream flow.

hydrology, modeling, streamflow↗
DOE OSTI2023

Connecting Large‐Scale Meteorological Patterns to Extratropical Cyclones in CMIP6 Climate Models Using Self‐Organizing Maps

Abstract Extratropical cyclones (ETCs) are responsible for the majority of cool‐season extreme events in the northeastern United States (NEUS), often leading to high‐impact weather conditions that can have wide‐ranging socioeconomic impacts. Evaluating the ability of climate models to adequately simulate ETC dynamics is essential for improving model performance and increasing confidence in future projections used by stakeholders and policymakers. ETCs are traditionally studied using techniques such as case studies and synoptic typing, however, these approaches can be time‐consuming, require subjective analysis, and do not necessarily identify the coincident large‐scale meteorological patterns (LSMPs). Here, we apply self‐organizing maps (SOMs) as an automated machine‐learning approach to characterize the LSMPs and associated frequency and intensity of discrete ETC events over NEUS. The dominant patterns of geopotential height variability are identified through SOM analysis of five reanalysis products during the last four decades. ETC events are tracked using TempestExtremes and are integrated with SOMs to classify the accumulated cyclone activity (ACA) associated with each pattern. We then evaluate the skill of CMIP6 historical experiments in simulating the LSMPs and ETC events identified in the SOM. Our results identify a robust bias toward more zonal patterns, with models struggling to reproduce the more amplified patterns typically associated with the highest cyclone activity. While model resolution has some impact on simulation credibility, model configuration appears to be more important in LSMP representation. The vast majority of CMIP6 models produce too few ETCs, although model errors are distributed around historical reanalyses when ACA is normalized by storm frequency.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Improved Prediction of Cold-Air Pools in the Weather Research and Forecasting Model Using a Truly Horizontal Diffusion Scheme for Potential Temperature

The terrain-following vertical coordinate system used by many atmospheric models, including the Weather Research and Forecasting (WRF) Model, is prone to errors in regions of complex terrain. These errors stem, in part, from the calculation of horizontal gradients within the diffusion term of the momentum or scalar evolution equations. In WRF, such gradients can be calculated along coordinate surfaces, or using metric terms that help account for grid skewness. However, neither of these options ensures a truly horizontal gradient calculation, especially if a grid cell is skewed enough that the heights of the neighboring grid points used in the calculation fall outside the vertical range of the cell. In this work, an improved scheme that uses Taylor series approximations to vertically interpolate variables to the level necessary for a truly horizontal gradient calculation is implemented in WRF for the diffusion of potential temperature. The scheme is validated using an atmosphere-at-rest configuration, in which spurious flows develop only as a result of numerical errors and can thus be used as a proxy for model performance. Following validation, the method is applied to the simulation of cold-air pools (CAPs), which occur in regions of complex terrain and are characterized by strong near-surface temperature gradients. Using the truly horizontal scheme, idealized simulations demonstrate reduced numerical mixing in a quiescent CAP, and a realistic case study in the Columbia River basin shows a reduction in positive wind speed bias by up to roughly 20% compared to observations from the Second Wind Forecast Improvement Project.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Investigating the Role of Accident Tolerant Cladding on Source Term Reduction for High-Burnup PWRs Using MELCOR

The use of accident tolerant fuel (ATF) cladding can increase coping times during and beyond design basis accidents. While such gains may be incremental, they provide a margin that can potentially be recovered to enable high-burnup (HBU) operation. Realizing such a margin requires demonstrating that the combination of HBU and ATF has not led to an overall increase in source term. This study investigates the influence of cladding technology (Zr-based, Cr-coated Zr, and FeCrAl) and fuel cycle length (18 and 24 months) on radiological dose at the boundary of the exclusion zone for a four-loop pressurized water reactor to investigate whether ATF claddings can provide such benefits. We analyze a recovered large break loss-of-coolant accident scenario to investigate the impact of transient timescale on the benefits of such coping time increases. The simulations have been performed using the MELCOR and MELCOR Accident Consequence Code System codes. For the cases analyzed, increased fuel cycle length did not necessarily increase radionuclide release and hydrogen generation, as these were found to be sensitive to the core power distribution. Similarly, off-site dose consequence is dominated by short-lived radionuclides that tend to saturate earlier in the burnup, so higher burnup operation did not necessarily increase the source term for the phenomena and transients analyzed here. Delays in recovery of the lowpressure safety injection system increase hydrogen production and radionuclide release, especially between 780 s and 1620 s, due to the nonlinear oxidation and core degradation behavior. Results show that Cr-coated Zr enhances safety by delaying heatup and gap release. Here, when uncertainty propagation on oxidation properties is considered, FeCrAl exhibits the lowest overall radionuclide release and off-site dose throughout the spectrum. However, while the considered “base model” performance is superior under delayed injection scenarios, upper-bound cases display hydrogen generation risk comparable to the Zr-based cladding.

Accident Tolerant Fuel↗
DOE OSTI2022

Combined TREAT-LOC and SATS LOCA Experiment Plan: Integral LOCA Experiments on High-Burnup Fuels

The Transient Reactor Test Facility (TREAT) loss-of-coolant (LOC) and high-burnup (HBu) experiment series, along with the Severe Accident Test Station (SATS) HBu experiment series, are integral LOC accident (LOCA) experiments planned under the DOE AFC program, which aim to support burnup extension needs by addressing identified R&D priorities in order to achieve an improved understanding of fuel fragmentation, relocation, and dispersal (FFRD) of HBu fuel during LOCA events. The data produced under this plan will be used to further validate and confirm existing models and inform future R&D and model development. The experimental program has been specifically designed to address knowledge gaps and opportunities identified through a detailed review of existing public knowledge on LOCA FFRD. The test program employs a unique combination of in- and out-of-pile experimental approaches and state-of-the-art facilities to provide a clear connection to the existing integral and semi-integral LOCA experiment database. The primary goal of the program is to investigate the impact of prototypic HBu fuel/cladding thermomechanical behaviors under postulated LWR LOCA conditions that have not yet been fully studied. These conditions correspond with prototypic decay-energy heatup (DEH) and stored-energy heatup (SEH) conditions. Importantly, TREAT’s unique capability will enable the first evaluation of the impact of SEH conditions on HBu fuels. The test program will emphasize the development of an improved mechanistic understanding of key experimental phenomena through independent experimental systems, development of a database to support fuel performance modeling tools and employing world-leading advanced materials characterization and in-situ diagnostics to evaluate FFRD. The results of the program will provide novel data to support modeling development and validation and will represent a significant advancement in evaluating prototypic conditions, as well as to inform the technical basis for LOCA-induced FFRD.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Growing grasses in unprofitable areas of US Midwest croplands could increase species richness

The US has large potential to grow perennial energy crops, but because these crops are rarely grown in current agricultural landscapes, it is unclear how biodiversity may be affected. Over time, as agriculture has increased, many grassland species have declined. In addition, not all agricultural land is profitable for growing annual crops. Unprofitable areas were responsible for a loss of approximately $110 million USD per year from 2013 to 2016. Based on this, we want to know how converting less-profitable portions of agricultural fields to switchgrass, a native prairie grass, would influence species occurrence. To address this question, we developed an alternative landscape in which clustered corn/soy acres with a low return on investment (ROI) were replaced with grassland. We also developed and validated species distribution models to predict changes in species occurrence for 28 avian species in Iowa in response to landscape management. Furthermore, we compared results for three different models: Random forest (RF), Stochastic gradient boosting (GBM), and Neural network (Nnet) and found that all models performed well and predicted similar species distribution. Predicted species richness increased by 3.66% (RF), 2.79% (GBM), and 7.51% (Nnet) when we simulated a change in management for ~3% of Iowa's low ROI corn/soybean areas to grassland. If harvested, these areas could generate approximately 7.6 million dry tons/year of switchgrass for bioenergy, thereby increasing farmers earnings. Unprofitable areas tended to occur along streams, which suggest that incorporating partially harvested riparian buffers can benefit avian biodiversity, while improving water quality and reducing unnecessary costs for farmers.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

RLScheduler: An Automated HPC Batch Job Scheduler Using Reinforcement Learning

Today’s high-performance computing (HPC) platforms are still dominated by batch jobs. Accordingly, effective batch job scheduling is crucial to obtain high system efficiency. Existing HPC batch job schedulers typically leverage heuristic priority functions to prioritize and schedule jobs. But, once configured and deployed by the experts, such priority functions can hardly adapt to the changes of job loads, optimization goals, or system settings, potentially leading to degraded system efficiency when changes occur. To address this fundamental issue, we present RLScheduler, an automated HPC batch job scheduler built on reinforcement learning. RLScheduler relies on minimal manual interventions or expert knowledge, but can learn high-quality scheduling policies via its own continuous ‘trial and error’. We introduce a new kernel-based neural network structure and trajectory filtering mechanism in RLScheduler to improve and stabilize the learning process. Through extensive evaluations, we confirm that RLScheduler can learn high-quality scheduling policies towards various workloads and various optimization goals with relatively low computation cost. Moreover, we show that the learned models perform stably even when applied to unseen workloads, making them practical for production use.

Zhang, Di↗
DOE OSTI2024

Utilizing digitized occurrence records of Midwestern feral Cannabis sativa to develop ecological niche models

Hemp (Cannabis sativa L.) has historically played a vital role in agriculture across the globe. Feral and wild populations have served as genetic resources for breeding, conservation, and adaptation to changing environmental conditions. However, feral populations of Cannabis, specifically in the Midwestern United States, remain poorly understood. This study aims to characterize the abiotic tolerances of these populations, estimate suitable areas, identify regions at risk of abiotic suitability change, and highlight the utility of ecological niche models (ENMs) in germplasm conservation. The Maxent algorithm was used to construct a series of ENMs. Validation metrics and MOP (Mobility-oriented Parity) analysis were used to assess extrapolation risk and model performance. We also projected the final projected under current and future climate scenarios (2021–2040 and 2061–2080) to assess how abiotic suitability changes with time. Climate change scenarios indicated an expansion of suitable habitat, with priority areas for germplasm collection in Indiana, Illinois, Kansas, Missouri, and Nebraska. This study demonstrates the application of ENMs for characterizing feral Cannabis populations and highlights their value in germplasm conservation and breeding efforts. Populations of feral C. sativa in the Midwest are of high interest, and future research should focus on utilizing tools to aid the collection of materials for the characterization of genetic diversity and adaptation to a changing climate.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Evaluation of interactive and prescribed agricultural ammonia emissions for simulating atmospheric composition in CAM-chem

Abstract. Ammonia (NH3) plays a central role in the chemistry of inorganic secondary aerosols in the atmosphere. The largest emission sector for NH3 is agriculture, where NH3 is volatilized from livestock wastes and fertilized soils. Although the NH3 volatilization from soils is driven by the soil temperature and moisture, many atmospheric chemistry models prescribe the emission using yearly emission inventories and climatological seasonal variations. Here we evaluate an alternative approach where the NH3 emissions from agriculture are simulated interactively using the process model FANv2 (Flow of Agricultural Nitrogen, version 2) coupled to the Community Atmospheric Model with Chemistry (CAM-chem). We run a set of 6-year global simulations using the NH3 emission from FANv2 and three global emission inventories (EDGAR, CEDS and HTAP) and evaluate the model performance using a global set of multi-component (atmospheric NH3 and NH4+, and NH4+ wet deposition) in situ observations. Over East Asia, Europe and North America, the simulations with different emissions perform similarly when compared with the observed geographical patterns. The seasonal distributions of NH3 emissions differ between the inventories, and the comparison to observations suggests that both FANv2 and the inventories would benefit from more realistic timing of fertilizer applications. The largest differences between the simulations occur over data-scarce regions. In Africa, the emissions simulated by FANv2 are 200 %–300 % higher than in the inventories, and the available in situ observations from western and central Africa, as well as NH3 retrievals from the Infrared Atmospheric Sounding Interferometer (IASI) instrument, are consistent with the higher NH3 emissions as simulated by FANv2. Overall, in simulating ammonia and ammonium concentrations over regions with detailed regional emission inventories, the inventories based on these details (HTAP, CEDS) capture the atmospheric concentrations and their seasonal variability the best. However these inventories cannot capture the impact of meteorological variability on the emissions, nor can these inventories couple the emissions to the biogeochemical cycles and their changes with climate drivers. Finally, we show with sensitivity experiments that the simulated time-averaged nitrate concentration in air is sensitive to the temporal resolution of the NH3 emissions. Over the CASTNET monitoring network covering the US, resolving the NH3 emissions hourly instead monthly reduced the positive model bias from approximately 80 % to 60 % of the observed yearly mean nitrate concentration. This suggests that some of the commonly reported overestimation of aerosol nitrate over the US may be related to unresolved temporal variability in the NH3 emissions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Informative and non-informative decomposition of turbulent flow fields

Not all the information in a turbulent field is relevant for understanding particular regions or variables in the flow. Here, we present a method for decomposing a source field into its informative Φ I (x, t) and residual Φ R (x, t) components relative to another target field. The method is referred to as informative and non-informative decomposition (IND). All the necessary information for physical understanding, reduced-order modelling and control of the target variable is contained in Φ I (x, t), whereas Φ R (x, t) offers no substantial utility in these contexts. The decomposition is formulated as an optimisation problem that seeks to maximise the time-lagged mutual information of the informative component with the target variable while minimising the mutual information with the residual component. The method is applied to extract the informative and residual components of the velocity field in a turbulent channel flow, using the wall shear stress as the target variable. We demonstrate the utility of IND in three scenarios: (i) physical insight into the effect of the velocity fluctuations on the wall shear stress; (ii) prediction of the wall shear stress using velocities far from the wall; and (iii) development of control strategies for drag reduction in a turbulent channel flow using opposition control. In case (i), IND reveals that the informative velocity related to wall shear stress consists of wall-attached high- and low-velocity streaks, collocated with regions of vertical motions and weak spanwise velocity. This informative structure is embedded within a larger-scale streak–roll structure of residual velocity, which bears no information about the wall shear stress. In case (ii), the best-performing model for predicting wall shear stress is a convolutional neural network that uses the informative component of the velocity as input, while the residual velocity component provides no predictive capabilities. Finally, in case (iii), we demonstrate that the informative component of the wall-normal velocity is closely linked to the observability of the target variable and holds the essential information needed to develop successful control strategies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Outlook towards deployable continual learning for particle accelerators

Particle accelerators are high power complex machines. To ensure uninterrupted operation of these machines, thousands of pieces of equipment need to be synchronized, which requires addressing many challenges including design, optimization and control, anomaly detection and machine protection. With recent advancements, machine learning (ML) holds promise to assist in more advance prognostics, optimization, and control. While ML based solutions have been developed for several applications in particle accelerators, only few have reached deployment and even fewer to long term usage, due to particle accelerator data distribution drifts caused by changes in both measurable and non-measurable parameters. In this paper, we identify some of the key areas within particle accelerators where continual learning can allow maintenance of ML model performance with distribution drifts. Particularly, we first discuss existing applications of ML in particle accelerators, and their limitations due to distribution drift. Next, we review existing continual learning techniques and investigate their potential applications to address data distribution drifts in accelerators. By identifying the opportunities and challenges in applying continual learning, this paper seeks to open up the new field and inspire more research efforts towards deployable continual learning for particle accelerators.

43 PARTICLE ACCELERATORS↗