Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “recurrence”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Assessment of Clonal Expansion Using CarcSeq Measurement of Lung Cancer Driver Mutations and Correlation With Mouse Strain- and Sex-Related Incidence of Spontaneous Lung Neoplasia

Quantification of variation in levels of spontaneously occurring cancer driver mutations (CDMs) was developed to assess clonal expansion and predict future risk of neoplasm development. Specifically, an error-corrected next-generation sequencing method, CarcSeq, and a mouse CarcSeq panel (analogous to human and rat panels) were developed and used to quantify low-frequency mutations in a panel of amplicons enriched in hotspot CDMs. Mutations in a subset of panel amplicons, Braf, Egfr, Kras, Stk11, and Tp53, were related to incidence of lung neoplasms at 2 years. This was achieved by correlating median absolute deviation (MAD) from the overall median mutant fraction (MF) measured in the lung DNA of 16-week-old male and female, B6C3F1 and CD-1 mice (10 mice/sex/strain) with percentages of spontaneous alveolar/bronchioloalveolar adenomas and carcinomas reported in bioassay control groups. A total of 1586 mouse lung mutants with MFs > x 10-4 were recovered. The ratio of nonsynonymous to synonymous mutations was used to assess the proportion of recovered mutations conferring a positive selective advantage. The greatest ratio was observed in what is considered the most lung tumor-sensitive model examined, male B6C3F1 mice. Of the recurrent, nonsynonymous mouse mutations recovered, 55.5% have been reported in human tumors, with many located in or around the mouse equivalent of human cancer hotspot codons. MAD for the same subset of amplicons measured in normal human lung DNA samples showed a correlation of moderate strength and borderline significance with age (a cancer risk factor), as well as age-related cumulative lung cancer risk, suggesting MAD may inform species extrapolation.

Toxicology↗
DOE OSTI2023

Locoregional Treatment of Glioblastoma With Targeted α Therapy: [213Bi]Bi-DOTA–Substance P Versus [225Ac]Ac-DOTA–Substance P—Analysis of Influence Parameters

Background Glioblastoma (GB) is the most malignant primary brain tumor. Therefore, introduction of new treatment options is critically important. The aim of this study was to assess local treatment with α emitters [ 213 Bi]Bi-DOTA–substance P (SP) and [ 225 Ac]Ac-DOTA-SP. Methods Treatment was performed as salvage therapy in patients with recurrent primary and secondary GB. [ 213 Bi]Bi-DOTA-SP with injected activity 1.85 GBq per cycle was used in 20 primary (48.2 ± 11.8 years old) and in 9 secondary (38.8 ± 10.8 years old) GB patients and [ 225 Ac]Ac-DOTA-SP in 15 primary (45.1 ± 9.9 years old) and in 6 secondary (37.8 ± 6.4 years old) GB patients with a dose escalation scheme (10, 20, and 30 MBq). Results Local treatment with [ 213 Bi]Bi-DOTA-SP and [ 225 Ac]Ac-DOTA-SP was well tolerated with only few adverse effects. There was no statistically significant difference between [ 213 Bi]Bi-DOTA-SP and [ 225 Ac]Ac-DOTA-SP groups in survival parameters. For primary GB, survival parameters of patients treated with [ 213 Bi]Bi-DOTA-SP and [ 225 Ac]Ac-DOTA-SP were as follows(in months): progression-free survival time, 2.7 versus 2.4; OS-d (overall survival from time of diagnosis to death from any cause), 23.6 versus 21.0; OS-t (overall survival from the start of treatment to death from any cause), 7.5 versus 5.0; and OS-r (overall survival from recurrence in primary tumors to death from any cause), 10.9 versus 12.0. Survival parameters of secondary GB patients treated with [ 213 Bi]Bi-DOTA-SP and [ 225 Ac]Ac-DOTA-SP were as follows (in months): progression-free survival time, 5.8 versus 2.4; OS-d, 52.3 versus 65.0; OS-t, 16.4 versus 16.0; and OS-c (overall survival from conversion into secondary GB multiforme to death from any cause), 18.4 versus 36.0. Conclusions The similarity results of 213 Bi or 225 Ac may suggest that the local treatment of brain tumors can be greatly simplified. The experience to date shows that local radioisotope treatment of brain tumors requires further dosimetry studies, taking into account the complexity of biological processes.

Radiology, Nuclear Medicine & Medical Imaging↗
DOE OSTI2025

Echo state network for coarsening dynamics of charge density waves

An echo state network (ESN) is a type of reservoir computer that uses a recurrent neural network with a sparsely connected hidden layer. Compared with other recurrent neural networks, one great advantage of ESN is the simplicity of its training process. Yet, despite the seemingly restricted learnable parameters, ESN has been shown to successfully capture the spatial-temporal dynamics of complex patterns. Here we build an ESN to model the coarsening dynamics of charge-density waves (CDWs) in a semiclassical Holstein model, which exhibits a checkerboard electron density modulation at half-filling stabilized by a commensurate lattice distortion. The inputs to the ESN are local CDW order parameters in a finite neighborhood centered around a given site, while the output is the predicted CDW order of the center site at the next time step. Special care is taken in the design of couplings between hidden layer and input nodes to ensure lattice symmetries are properly incorporated into the ESN model. Since the model predictions depend only on CDW configurations of a finite domain, the ESN is scalable and transferrable in the sense that a model trained on dataset from a small system can be directly applied to dynamical simulations on larger lattices. Furthermore, our work opens avenues for efficient dynamical modeling of pattern formations in functional electron materials.

2-dimensional systems↗
DOE OSTI2025

GRUMDN: A Multi-Task Model for Predicting Human Patterns-of-Life from Stay Transition Data

Understanding human patterns-of-life (PoL) is essential towards ensuring safe and secure indoor facility environment as well as outdoor urban environment. Prediction of human movement in between places of interest is vital in understanding human PoL. Movement between spaces maybe represented and detected in one of the two forms: 1) trajectories: locations measured at regular time intervals by mobile sensors, bluetooth or GPS sensors; or 2) stay transitions: semantic PoI (points of interest) and stay duration data measurable by eventbased sensors that collect data when a check-in or check-out event is detected. Stay transition data provides a more compressed data format compared to trajectories data, especially in situations with longer stay durations, while preserving the information necessary for PoL analysis. Now as introduced briefly in the paper, our deployed end application (Digital Twin of a facility with non-player characters, besides the interactive user in virtual reality) needed a well-performing and validated AI/ML model for simulating high quality stay transitions behavior. In this study we thus primarily present our findings with developing and validating that model, which is a multi-task neural network for stay transition prediction. The neural network consists of two heads, for corresponding two tasks of stay category prediction and stay duration prediction. We evaluated gated recurrent units and multi-layer perceptrons of varying network sizes for stay category prediction; while mixture density networks, noisy generator-only networks, and generative adversarial networks of varying network sizes for stay duration prediction. We have then evaluated four multi-task models, constructed by combining these specialized models, on their ability to predict stay transition data. We tested our models on datasets from two different cases: 1) a simulation-generated dataset of indoor movement within the HFIR (high flux isotope reactor) nuclear reactor facility at Oak Ridge National Laboratory (ORNL); and 2) the GeoLife human mobility dataset of outdoor urban movement available in literature. Our results indicate that GRUMDN, which combines gated recurrent units (GRU) for stay category prediction task, and mixture density networks (MDN) for stay duration prediction task, did overall outperform other multitask models and the current state-of-the-art.

Gunaratne, Chathika [ORNL] (ORCID:0000000225088745↗
DOE OSTI2026

NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning

Spiking Neural Networks (SNNs) are computational models inspired by the event-driven communication and connectivity patterns of biological neural circuits. They enable high energy efficiency and natural support for diverse architectures ranging from layered networks to small-world and graphstructured topologies. In this work, we introduce NeuroCoreX, an open-source, FPGA-based spiking neural network emulator that provides real-time, on-chip learning and flexible network organization. NeuroCoreX supports both feedforward sensory inputs streamed directly from sensors or PCs via UART and recurrent on-chip connectivity, enabling simultaneous processing and learning from external stimuli and internal network dynamics-capabilities rarely available in existing FPGA SNN platforms. The system implements a Leaky Integrate-and-Fire (LIF) neuron model with current-based synapses and supports pair-based STDP learning on both feedforward and recurrent synapses. A lightweight Python interface enables interactive configuration, live monitoring, weight read-back, and experiment control. Importantly, NeuroCoreX is tightly integrated with the SuperNeuroMAT simulator, allowing SNN models to be transferred seamlessly from software to hardware for hardware-in-the-loop development. By combining real-time plasticity, flexible connectivity, and an open-source VHDL implementation, NeuroCoreX provides an extensible and accessible platform for neuromorphic research, algorithm-hardware co-design, and energy-efficient edge intelligence.

Gautam, Ashish [ORNL]↗
DOE OSTI2023

Transcatheter Arterial Chemoembolization for Treatment-Naive Hepatocellular Carcinoma Has Different Treatment Effects Depending on Central or Peripheral Tumor Location

Introduction: The purpose of this study was to evaluate the treatment efficacy of transcatheter arterial chemoembolization (TACE) for treatment-naive hepatocellular carcinoma (HCC) according to tumor location and burden. Methods: Between 2010 and 2019, consecutive patients who underwent TACE as the first treatment were enrolled. Tumors were classified into two categories based on their location, as central or peripheral tumors. Tumors in the central zone, which is within 1 cm of the main trunk or the first branch of the portal vein, were classified as central tumors, while those located in the peripheral zone were classified as peripheral tumors. Patients were grouped according to the HCC location and up-to-7 criteria. Patients with central tumors were classified into the central arm and those with only peripheral tumors were classified into the peripheral arm. Patients within and beyond the up-to-7 criteria were classified into the up-to-7 in and up-to-7 out-groups, respectively. Local recurrence-free survival (LRFS) and progression-free survival (PFS) were compared per nodule (central tumor vs. peripheral tumor) and per patient (central arm vs. peripheral arm), respectively. The prognostic factors of LRFS and PFS were analyzed by univariate and multivariate analyses. Results: A total of 174 treatment-naive patients with 352 HCCs were retrospectively enrolled. Ninety-six patients and 130 lesions were selected by propensity score matching. Median LRFS was longer for peripheral tumors than central tumors (not reached vs. 3.3 months, p < 0.001). Median PFS was 17.1 months (8.3–24.9) in the peripheral arm and up-to-7 in, 7.0 months (3.3–12.7) in the peripheral arm and up-to-7 out, 8.4 months (4.0–12.6) in the central arm and up-to-7 in, and 3.0 months (1.2–4.9) in the central arm and up-to-7 out-groups. The peripheral arm and up-to-7 in-groups had significantly longer PFS than the other three groups (p = 0.013, p = 0.015, p < 0.001, respectively). Multivariate analysis confirmed that the central zone and central arm were associated with high adjusted hazard ratios for tumor recurrence or death (2.87, p < 0.001; 2.89, p < 0.001, respectively). Conclusion: Treatment-naive HCCs in the peripheral zone had a longer LRFS and PFS following TACE compared to those in the central zone.

Gastroenterology & Hepatology↗
DOE OSTI2021

Fully Convolutional Spatio-Temporal Models for Representation Learning in Plasma Science

We have trained a fully convolutional spatio-temporal model for fast and accurate representation learning in the challenging exemplar application area of fusion energy plasma science. The onset of major disruptions is a critically important fusion energy science issue that must be resolved for advanced tokamak plasmas such as the $25B burning plasma international thermonuclear experimental reactor (ITER) experiment. While a variety of statistical methods have been used to address the problem of tokamak disruption prediction and control, recent approaches based on deep learning have proven particularly compelling. In the present paper, we introduce further improvements to the fusion recurrent neural network (FRNN) software suite, which delivered cross-machine disruption predictions with unprecedented accuracy using a large database of experimental signals from two major tokamaks. Up to now, FRNN was based on the long short-term memory (LSTM) variant of recurrent neural networks to leverage the temporal information in the data. Here, we implement and apply the "temporal convolutional neural network (TCN)" architecture to the time-dependent input signals. Furthermore, this allows highly optimized convolution operations to carry the majority of the computational load of training, thus enabling a reduction in training time, and the effective use of high-performance computing resources for hyperparameter tuning. At the same time, the TCN-based architecture achieves better predictive performance when compared with the LSTM architecture for various tasks for a representative fusion database.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Deployment of Dynamic Neural Network Optimization to Minimize Heat Rate During Ramping for Coal Power Plants (Final Technical Report)

Much success was achieved throughout the course of this project. A successful implementation of Dynamic Neural Network Optimization (D-NNO) was coupled with Adaptive Predictive Controls (APC) and a novel hardware installation comprised of an advanced sensor network (ASN) measuring mass-weighted averages of flue gas constituents above the horizontal superheater of a coal-fired utility boiler. From 2019 through 2023 (including an extension due to COVID delays), the team was able to prototype, evaluate, deploy, iterate, and ultimately finalize an advanced closed-loop control D-NNO system which demonstrated the ability to: •improve unit efficiency ~2.0% relative to unoptimized operation (represented as total fuel fired per MWh generated) •improve unit NOx emission rates 10%+ beyond static optimization baselines •improve unit temperature stability as much as 58% and on average 12% •improve operating load stability as much as 35% The culmination of this project has generated an advanced methodology of deploying specially designed recurrent neural networks (long short-term memory, gated recurrent unit, encoder-decoder networks, transformers, etc.), customized trajectory planning and closed-loop optimization modules capable of adapting to live electric grid responses and demands, self-tuning and adaptive expert controls constantly adjusting prediction parameters to real-time unit behavior, and a hardware/software package able to reliably calculate net unit heat rate (NUHR) in real-time using flue gas constituents, machine learning, and known combustion relationships. Through this real-time NUHR value, immediate feedback on system adjustments relative to operating efficiency was available, allowing for rapid improvements to system performance. In addition to development and deployment of the advanced D-NNO system, the approach methodology has been readily commercialized through the project platform Griffin Open Systems, LLC, the D-NNO software platform host. Similar methodologies to those developed by this project have already been deployed at 5 other units across the United States, with another 6 implementations scheduled, and more expected. Over the course of the project, multiple academic papers were submitted and accepted for publication within esteemed academic journals, and PhD students were trained and graduated, as well as undergraduate students becoming involved and participating to project objectives.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2024

Improved Subseasonal Forecasting of Extreme Polar Vortices Using Machine Learning

Our research was focused on forecasting the position and shape of the winter stratospheric polar vortex at a subseasonal timescale of 15 days in advance. To achieve this, we employed both statistical and neural network machine learning techniques. The analysis was performed on 42 winter seasons of reanalysis data provided by NASA giving us a total of 6,342 days of data. The state of the polar vortex for determined by using geometric moments to calculate the centroid latitude and the aspect ratio of an ellipse fit onto the vortex. Timeseries for thirty additional precursors were calculated to help improve the predictive capabilities of the algorithm. Feature importance of these precursors was performed using random forest to measure the predictive importance and the ideal number of precursors. Then, using the precursors identified as important, various statistical methods were tested for predictive accuracy with random forest and nearest neighbor performing the best. An echo state network, a type of recurrent neural network that features sparsely connected hidden layer and a reduced number of trainable parameters that allows for rapid training and testing, was also implemented for the forecasting problem. Hyperparameter tuning was performed for each methods using a subset of the training data. The algorithms were trained and tuned on the first 41 years of data, then tested for accuracy on the final year. In general, the centroid latitude of the polar vortex proved easier to predict than the aspect ratio across all algorithms. Random forest outperformed other statistical forecasting algorithms overall but struggled to predict extreme values. Forecasting from echo state network suggested a strong predictive capability past 15 days, but further work is required to fully realize the potential of recurrent neural network approaches.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Performance Comparison of Machine Learning Models for Ultrasonic Nondestructive Evaluation of Alkali-Silica Reaction in Concrete

Alkali-silica reaction (ASR) causes concrete degradation, leading to cracking, rebar corrosion, and reduced structural integrity, which raises safety concerns. Ultrasonic nondestructive evaluation (NDE) effectively assesses concrete properties and monitors ASR progression. However, its deployment and analysis require specialized expertise and subjective interpretation. As computational power increases, artificial intelligence (AI) and machine learning (ML) algorithms are increasingly being used to automate NDE data analysis across various industries for AI-assisted automation. Regulatory agencies are adapting to this technological shift, prompting a need to evaluate current ML technologies’ capabilities and limitations in assessing concrete material properties and damage. This report presents a comparative analysis of four ML regression models for predicting concrete material damage induced by ASR expansion using long-term ultrasonic data monitoring. The models investigated include linear regression (LR), support vector regression (SVR), shallow neural networks (NN), and deep neural networks (DNN). LR, SVR, and shallow NN models use features extracted from ultrasonic signals, whereas the DNN model processes time-domain ultrasonic signals and frequency spectra directly. The study systematically compared the models’ performance from various perspectives, including model input, prediction performance, and generalization ability. The findings indicate significant variability in model performance, with some ML algorithms achieving very high or very low prediction accuracy depending on the preprocessing and feature engineering (extraction and selection) applied. Key insights include the observation that shallow ML models (LR, SVR, and shallow NNs) require meticulous preprocessing and feature extraction to achieve high accuracy. In contrast, the DNN model, although it bypasses the need for feature engineering, necessitates extensive preprocessing to mitigate noise and computational demands. The SVR model emerged as the top performer among the shallow models, and the DNN model exhibited superior performance on specific datasets but struggled with generalization across specimens from different batches. Additionally, the SVR model is sensitive to temperature variations, whereas the DNN model is robust in this regard. Using recurrent neural networks is recommended for future ASR expansion prediction studies. Recurrent neural networks’ inherent ability to capture temporal dependencies and long-term patterns makes them well suited for analyzing sequential ultrasonic monitoring data. Overall, the results and conclusions of this study could provide insights into the capabilities and effectiveness of ML when applied to ultrasonic NDE data and help identify best practices for using ML for ultrasonic NDE of concrete material properties.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Transformer Neural Networks with Spatiotemporal Attention for Predictive Control and Optimization of Industrial Processes

In the context of real-time optimization and model predictive control of industrial systems, machine learning, and neural networks represent cutting-edge tools that hold promise for enhancing dynamic modeling. This work presents a novel transformer neural network architecture for real-time optimization and model predictive control. This network design includes a modified attention mechanism inspired by positional embedding attention from vision transformers and task-specific modifications to the input-output structure of the transformer’s decoder stack. Experiments were conducted using data from a 450 MW coal-fired power plant to evaluate this approach's effectiveness. The transformer neural network was compared with conventional recurrent models, including GRU and LSTM. The transformer exhibited a 6% increase in the R-squared (R2) value of predictions and an 83% reduction in mean squared error (MSE). Computation time was also reduced by 84% compared to conventional recurrent models.

Gallup, Ethan R.↗
DOE OSTI2026

Hyaloscypha finlandica Metabolome Repository

This repository provides the curated data tables, manuscript figure and table exports, dependency records, and workflow scripts supporting an integrated comparative genomics and untargeted LC-MS/MS metabolomics analysis of Hyaloscypha finlandica strain PMI 746, a root-associated dark septate endophyte of poplar. The repository includes genome-mining summaries from antiSMASH, FunBGCeX, BGC-Prophet, and BiG-SCAPE; processed metabolomics inputs; metabolite annotation evidence; statistical outputs; and publication-facing figures and tables. Raw LC-MS/MS spectra, full genome/protein downloads, and large generated tool outputs are referenced through public archive/accession records and are not stored in Git.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Deep Learning Predicts Stress–Strain Relations of Granular Materials Based on Triaxial Testing Data

This study presents an AI-based constitutive modelling framework wherein the prediction model directly learns from triaxial testing data by combining discrete element modelling (DEM) and deep learning. A constitutive learning strategy is proposed based on the generally accepted frame-indifference assumption in constructing material constitutive models. The low-dimensional principal stress-strain sequence pairs, measured from discrete element modelling of triaxial testing, are used to train recurrent neural networks, and then the predicted principal stress sequence is augmented to other high-dimensional or general stress tensor via coordinate transformation. Through detailed hyperparameter investigations, it is found that long short-term memory (LSTM) and gated recurrent unit (GRU) networks have similar prediction performance in constitutive modelling problems, and both satisfactorily predict the stress responses of granular materials subjected to a given unseen strain path. Furthermore, the unique merits and ongoing challenges of data-driven constitutive models for granular materials are discussed.

42 ENGINEERING↗
DOE OSTI2020

Transcriptome Dynamics of the Inflorescence in Reciprocally Formed Allopolyploid Tragopogon miscellus (Asteraceae)

Polyploidy is an important evolutionary mechanism and is prevalent among land plants. Most polyploid species examined have multiple origins, which provide genetic diversity and may enhance the success of polyploids. In some polyploids, recurrent origins can result from reciprocal crosses between the same diploid progenitors. Although great progress has been made in understanding the genetic consequences of polyploidy, the genetic implications of reciprocal polyploidization remain poorly understood, especially in natural polyploids. Tragopogon (Asteraceae) has become an evolutionary model system for studies of recent and recurrent polyploidy. Allotetraploid T. miscellus has formed reciprocally in nature with resultant distinctive floral and inflorescence morphologies (i.e., short- vs. long-liguled forms). In this study, we performed comparative inflorescence transcriptome analyses of reciprocally formed T. miscellus and its diploid parents, T. dubius and T. pratensis. In both forms of T. miscellus, homeolog expression of ~70% of the loci showed vertical transmission of the parental expression patterns (i.e., parental legacy), and ~20% of the loci showed biased homeolog expression, which was unbalanced toward T. pratensis. However, 17.9% of orthologous pairs showed different homeolog expression patterns between the two forms of T. miscellus. No clear effect of cytonuclear interaction on biased expression of the maternal homeolog was found. In terms of the total expression level of the homeologs studied, 22.6% and 16.2% of the loci displayed non-additive expression in short- and long-liguled T. miscellus, respectively. Unbalanced expression level dominance toward T. pratensis was observed in both forms of T. miscellus. Significantly, genes annotated as being involved in pectin catabolic processes were highly expressed in long-liguled T. miscellus relative to the short-liguled form, and the majority of these differentially expressed genes were transgressively down-regulated in short-liguled T. miscellus. Given the known role of these genes in cell expansion, they may play a role in the differing floral and inflorescence morphologies of the two forms. In summary, the overall inflorescence transcriptome profiles are highly similar between reciprocal origins of T. miscellus. However, the dynamic homeolog-specific expression and non-additive expression patterns observed in T. miscellus emphasize the importance of reciprocal origins in promoting the genetic diversity of polyploids.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Physics-Informed Deep Learning for Reconstruction of Spatial Missing Climate Information in the Antarctic

Understanding the influence of the Antarctic on the global climate is crucial for the prediction of global warming. However, due to very few observation sites, it is difficult to reconstruct the rational spatial pattern by filling in the missing values from the limited site observations. To tackle this challenge, regional spatial gap-filling methods, such as Kriging and inverse distance weighted (IDW), are regularly used in geoscience. Nevertheless, the reconstructing credibility of these methods is undesirable when the spatial structure has massive missing pieces. Inspired by image inpainting, we propose a novel deep learning method that demonstrates a good effect by embedding the physics-aware initialization of deep learning methods for rapid learning and capturing the spatial dependence for the high-fidelity imputation of missing areas. We create the benchmark dataset that artificially masks the Antarctic region with ratios of 30%, 50% and 70%. The reconstructing monthly mean surface temperature using the deep learning image inpainting method RFR (Recurrent Feature Reasoning) exhibits an average of 63% and 71% improvement of accuracy over Kriging and IDW under different missing rates. With regard to wind speed, there are still 36% and 50% improvements. In particular, the achieved improvement is even better for the larger missing ratio, such as under the 70% missing rate, where the accuracy of RFR is 68% and 74% higher than Kriging and IDW for temperature and also 38% and 46% higher for wind speed. In addition, the PI-RFR (Physics-Informed Recurrent Feature Reasoning) method we proposed is initialized using the spatial pattern data simulated by the numerical climate model instead of the unified average. Compared with RFR, PI-RFR has an average accuracy improvement of 10% for temperature and 9% for wind speed. When applied to reconstruct the spatial pattern based on the Antarctic site observations, where the missing rate is over 90%, the proposed method exhibits more spatial characteristics than Kriging and IDW.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars

Despite the utility of neural networks (NNs) for astronomical time-series classification, the proliferation of learning architectures applied to diverse data sets has thus far hampered a direct intercomparison of different approaches. Here we perform the first comprehensive study of variants of NN-based learning and inference for astronomical time series, aiming to provide the community with an overview on relative performance and, hopefully, a set of best-in-class choices for practical implementations. In both supervised and self-supervised contexts, we study the effects of different time-series-compatible layer choices, namely the dilated temporal convolutional neural network (dTCNs), long-short term memory NNs, gated recurrent units and temporal convolutional NNs (tCNNs). Additionally, we also study the efficacy and performance of encoder-decoder (i.e., autoencoder) networks compared to direct classification networks, different pathways to include auxiliary (non-time-series) metadata, and different approaches to incorporate multi-passband data (i.e., multiple time series per source). Performance—applied to a sample of 17,604 variable stars (VSs) from the MAssive Compact Halo Objects (MACHO) survey across 10 imbalanced classes—is measured in training convergence time, classification accuracy, reconstruction error, and generated latent variables. We find that networks with recurrent NNs generally outperform dTCNs and, in many scenarios, yield to similar accuracy as tCNNs. In learning time and memory requirements, convolution-based layers perform better. We conclude by discussing the advantages and limitations of deep architectures for VS classification, with a particular eye toward next-generation surveys such as the Legacy Survey of Space and Time, the Roman Space Telescope, and Zwicky Transient Facility.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Third-integer Resonant Extraction Regulation System for Mu2e

A third-integer resonant slow extraction system is being developed for Fermilab's Delivery Ring to deliver protons to the upcoming Mu2e experiment. The timescale of the extraction (or spill) duration is 43 milliseconds, which is extremely short and unprecedented. Additionally, the experiment's strict and challenging requirements on the quality of the spill at this time scale has led to the development of a new Spill Regulation System (SRS) design. The SRS primarily consists of three components - slow regulation, fast regulation, and harmonic content suppressor. Contributions to the first two components of the SRS, i.e., Slow Regulation and Fast Regulation subsystems, will be presented in which new adaptive learning algorithm schemes for the slow regulation of the spill -- validated using particle tracking simulations -- shall be described. In addition to these novel methods for the enhancement of the spill regulation system, results of employing Machine Learning in enhancing the performance of the resonant extraction are also presented. At the forefront of applying ML techniques to solve non-linear accelerator control problems, this work includes optimizing the PID gains as well as the replacement of the traditional PID controller using Recurrent Neural Networks and Gated Recurrent Unit (GRU) ML models to achieve efficiencies greater than a PID controller. Cutting-edge on-going Reinforcement Learning efforts, including an actor-critic family of learning algorithms, to regulate the spill rate will be reviewed, as well as present analytical calculations pertaining the transit time of particles in a third-integer resonant extraction. Detailed numerical investigations and validations of such calculations, the model of which could be exported and reliably used in future analytical modeling of any resonant extraction, are discussed.

43 PARTICLE ACCELERATORS↗
DOE OSTI2023

Machine Learning-Based Model Predictive Control of Two-Time-Scale Systems

In this study, we present a general form of nonlinear two-time-scale systems, where singular perturbation analysis is used to separate the dynamics of the slow and fast subsystems. Machine learning techniques are utilized to approximate the dynamics of both subsystems. Specifically, a recurrent neural network (RNN) and a feedforward neural network (FNN) are used to predict the slow and fast state vectors, respectively. Moreover, we investigate the generalization error bounds for these machine learning models approximating the dynamics of two-time-scale systems. Next, under the assumption that the fast states are asymptotically stable, our focus shifts toward designing a Lyapunov-based model predictive control (LMPC) scheme that exclusively employs the RNN to predict the dynamics of the slow states. Additionally, we derive sufficient conditions to guarantee the closed-loop stability of the system under the sample-and-hold implementation of the controller. A nonlinear chemical process example is used to demonstrate the theory. In particular, two RNN models are constructed: one to model the full two-time-scale system and the other to predict solely the slow state vector. Both models are integrated within the LMPC scheme, and we compare their closed-loop performance while assessing the computational time required to execute the LMPC optimization problem.

97 MATHEMATICS AND COMPUTING↗