SEARCH · Engineering Papers

Results for “learning rate”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 865 records · Page 48

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Exploring PV Circularity by Modeling Socio-Technical Dynamics of Modules’ End-of-Life Management

The circular economy (CE) tackles environmental and resource scarcity issues by maximizing value retention in the economy. The concept implies design strategies such as reducing the use of materials or improving products’ durability and end-of-life (EOL) strategies, for example, reusing products and components and recycling materials. With an estimated 80 million tons of global cumulative EOL photovoltaic (PV) modules, applying CE principles to the PV industry could alleviate resource scarcity issues while also providing economic benefits. However, transitioning to a CE may imply changes in organizations and consumer behaviors. In this context, assessment of CE strategies may require accounting for behavioral change, a requirement that methods from complex system science such as agent-based modeling meet. Thus, this paper uses an agent-based modeling (ABM) approach to study circularity in the photovoltaics supply chain. Four types of agents are represented in the ABM: PV owners, installers, recyclers, and manufacturers. Moreover, five possible EOL options – including three CE strategies – are modeled. Departing from traditional techno-economic analysis, the model includes techno-economic factors as well as social factors to model EOL management decisions. Results show that each dollar decrease in the recycling fees improves the recycling rate by roughly 1.1%. However, excluding social factors underestimates the effect that lower recycling prices have on material circularity.

agent-based modeling↗

DOE OSTI2025

“When I talk about it, my eyes light up!” Impacts of a national laboratory internship on community college student success

Participation in technical/research internships may improve undergraduate graduation rates and persistence in science, technology, engineering, and mathematics (STEM), yet little is known about the benefits of these activities a) for community college students, b) when hosted by national laboratories, and c) beyond the first few years after the internship. We applied Social Cognitive Career Theory (SCCT) to investigate alumni perspectives about how CCI at Lawrence Berkeley National Laboratory (LBNL) impacted their academic/career activities. We learned that alumni had low confidence and expectations of success in STEM as community college students. Participation in CCI increased their professional networks, expectations of success, and STEM skills, identity, and self-efficacy/confidence. Hispanic/Latinx alumni recalled the positive impact of mentors who prioritized personal connections, and women valued "warm" social environments. We propose several additions to the SCCT model, to better reflect the supports and barriers to STEM persistence for community college students.

careers↗

DOE OSTI2022

Enhanced Oblique Decision Tree Enabled Policy Extraction for Deep Reinforcement Learning in Power System Emergency Control

Deep reinforcement learning (DRL) algorithms have successfully solved many challenging problems in various power system control scenarios. However, their decision-making process is usually regarded as black-boxes. Furthermore, how DRL models interact with human intelligence remains an open problem. Thus, this paper proposes a policy extraction framework to extract a complex DRL model into an explainable policy. This framework includes three parts: 1) DRL training and data generation. We train an agent for a specific control task and generate data, which contains the control policy of the agent. 2) Policy extraction. We propose an information gain rate based weighted oblique decision tree (IGR-WODT) for DRL policy extraction. 3) Policy evaluation. We define three metrics to evaluate the performance of the proposed approach. A case study for the under-voltage load shedding problem shows that the IGR-WODT presents a performance enhancement compared with DRL, weighted oblique decision tree, and univariate decision tree. The proposed policy extraction method could provide an intuitive explanation of the neural network decision-making process to the dispatchers when making final decisions on power grid operation. Also, the resulted rule-based controller could replace the deep neural network-based controller in many field edge devices with limited computing resources, providing comparable performance.

deep reinforcement learning↗

DOE OSTI2024

Generic and ML Workloads in an HPC Datacenter: Node Energy, Job Failures, and Node-Job Analysis

HPC datacenters offer a backbone to the modern digital society. Increasingly, they run Machine Learning (ML) jobs next to generic, compute-intensive workloads, supporting science, business, and other decision-making processes. However, understanding how ML jobs impact the operation of HPC datacenters, relative to generic jobs, remains desirable but understudied. In this work, we leverage long-term operational data, collected from a national-scale production HPC datacenter, and statistically compare how ML and generic jobs can impact the performance, failures, resource utilization, and energy consumption of HPC datacenters. Our study provides key insights, e.g., ML-related power usage causes GPU nodes to run into temperature limitations, median/mean runtime and failure rates are higher for ML jobs than for generic jobs, both ML and generic jobs exhibit highly variable arrival processes and resource demands, significant amounts of energy are spent on unsuccessfully terminating jobs, and concurrent jobs tend to terminate in the same state. We open-source our cleaned-up data traces on Zenodo (https://doi. org/10.5281/zenodo.13685426), and provide our analysis toolkit as software hosted on GitHub (https://github.com/atlarge-research/2024-icpads-hpc-workload-characterization). This study offers multiple benefits for data center administrators, who can improve operational efficiency, and for researchers, who can further improve system designs, scheduling techniques, etc.

crossanalysis↗

DOE OSTI2024

A Deep Learning-Driven Sampling Technique to Explore the Phase Space of an RNA Stem-Loop

The folding and unfolding of RNA stem-loops are critical biological processes; however, their computational studies are often hampered by the ruggedness of their folding landscape, necessitating long simulation times at the atomistic scale. Here, we adapted DeepDriveMD (DDMD), an advanced deep learning-driven sampling technique originally developed for protein folding, to address the challenges of RNA stem-loop folding. Although tempering- and order parameter-based techniques are commonly used for similar rare-event problems, the computational costs or the need for a priori knowledge about the system often present a challenge in their effective use. DDMD overcomes these challenges by adaptively learning from an ensemble of running MD simulations using generic contact maps as the raw input. DeepDriveMD enables on-the-fly learning of a low-dimensional latent representation and guides the simulation toward the undersampled regions while optimizing the resources to explore the relevant parts of the phase space. We showed that DDMD estimates the free energy landscape of the RNA stem-loop reasonably well at room temperature. Our simulation framework runs at a constant temperature without external biasing potential, hence preserving the information on transition rates, with a computational cost much lower than that of the simulations performed with external biasing potentials. Here, we also introduced a reweighting strategy for obtaining unbiased free energy surfaces and presented a qualitative analysis of the latent space. This analysis showed that the latent space captures the relevant slow degrees of freedom for the RNA folding problem of interest. Finally, throughout the manuscript, we outlined how different parameters are selected and optimized to adapt DDMD for this system. We believe this compendium of decision-making processes will help new users adapt this technique for the rare-event sampling problems of their interest.

Gupta, Ayush↗

DOE OSTI2021

Atomistic Mechanism Underlying the Si ( 111 ) - ( 7 × 7 ) Surface Reconstruction Revealed by Artificial Neural-Network Potential

The 7×7 reconstruction of the Si(111) surface represents arguably the most fascinating surface reconstruction so far observed in nature. Yet, the atomistic mechanism underpinning its formation remains unclear after it was discovered sixty years ago. Experimentally, it is observed post priori so that analysis of its formation mechanism can only be carried out in analogy with archaeology. Theoretically, density-functional theory (DFT) correctly predicts the Si(111)-(7×7) ground state but is impractical to simulate its formation process; while empirical potentials failed to produce it as the ground state. Developing an artificial neural-network potential of DFT quality, we carried out accurate large-scale simulations to unravel the formation of the Si(111)-(7×7) surface. We reveal a possible step-mediated atom-pop rate-limiting process that triggers massive nonconserved atomic rearrangements, most remarkably, a critical process of collective vacancy diffusion that mediates a sequence of selective dimer, corner-hole, stacking-fault, and dimer-line pattern formation, to fulfill the 7×7 reconstruction. Our findings may not only solve the long-standing mystery of this famous surface reconstruction but they also illustrate the power of machine learning in studying complex structures.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Understanding the Impact of Data Staging for Coupled Scientific Workflows

We report the rate of data generated by cutting-edge experimental science facilities and large-scale simulations enabled by current high-performance computing (HPC) systems has continued to grow at a far greater pace than the development of the network and storage capabilities on which these systems rely. To cope with this challenge, scientist are moving toward the creation of autonomous experiments and HPC simulations using machine learning. However, efficiently moving, storing, and processing large amounts of data away from the point of origin presents an incredible challenge. In-memory computing, in situ analysis, data staging, and data streaming are recognized viable alternatives to traditional file-based methods for transferring data between coupled workflows. However, the performance trade-offs and limitations for these methods are not fully understood when used in HPC applications. This article presents a comprehensive performance assessment of the current solutions for data staging when applied to applications that are not necessary I/O intensive which makes them not ideal candidates for these methods. Our study is based on experiments running at scale on Oak Ridge National Laboratory's Summit supercomputer using applications and simulations that cover typical computational motifs and patterns. We investigated the usability and cost/benefit trade-offs of staging algorithms for HPC applications under different scenarios and highlight opportunities for optimizing the dataflow between coupled simulation workflows.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Finding MIDDLE Ground: Scalable and Secure Distributed Learning

Edge computing methods allow devices to efficiently train a high-performing, robust, and personalized model for predictive tasks. However, these methods succumb to privacy and scalability concerns such as adversarial data recovery and expensive model communication. Furthermore, edge computing methods unrealistically assume that all devices train an identical model. In practice, edge devices have varying computational and memory constraints which may not allow certain devices to have the space or speed to train a specific model. To overcome these issues, we propose MIDDLE: a model independent distributed learning algorithm which allows heterogeneous edge devices to assist each other’s training while communicating only non-sensitive information. MIDDLE unlocks the ability for edge devices, regardless of computational or memory constraints, to assist each other even with completely different model architectures. Furthermore, MIDDLE does not require model or gradient communication which greatly reduces communication size and time. We prove that MIDDLE attains the optimal convergence rate O(1/sqrt(TM)) of stochastic gradient descent for convex and non-convex smooth optimization (for total iterations T and batch size M). Finally, our experimental results demonstrate that MIDDLE (even in non-IID data settings) attains robust and high-performing models without model or gradient communication.

Bornstein, Marc I.↗

DOE OSTI2026

Real-Time Anomaly Detection for Beyond Standard Model Searches in ProtoDUNE Horizontal Drift

This paper summarizes work conducted throughout a SULI internship at Fermi National Accelerator Laboratory focused on building an unsupervised machine learning model for real-time anomaly detection in ProtoDUNE Horizontal Drift. Using simulated data, we trained an autoencoder model on a pure cosmic dataset, and evaluated it on both cosmic and neutrino events---making the model an anomaly detector. The goal was to make a model which matches or exceeds the current ADC Simple Window trigger algorithm so that our model can perform at the same rate but provide sensitivity to potential beyond-the-Standard-Model (BSM) signatures. In the end, we were able to construct a model which slightly exceeds the capabilities of the ADC Simple Window while remaining completely unsupervised, achieving $31.9 \pm 0.2$\% ($26.6 \pm 0.2$\%) $\nu$ efficiency at 5 Hz (2 Hz), a 3.6 (3.2) percentage point increase. Additionally, $17.5 \pm 0.3$\% ($18.3 \pm 0.3$\%) of the events that passed the autoencoder at 5 Hz (2 Hz) were missed by the current trigger algorithm. Future work will investigate alternative normalization methods, including quantile transformation, and evaluate the model on ProtoDUNE-HD detector-glitch data if that data becomes available.

Wilson, Cameron C. [Cincinnati U., RWC]↗

DOE OSTI2026

Real-Time Anomaly Detection for Beyond Standard Model Searches in ProtoDUNE Horizontal Drift

Wilson, Cameron C. [Cincinnati U., RWC]↗

DOE OSTI2026

Real-Time Anomaly Detection for Searches Beyond the Standard Model in the ProtoDUNE Horizontal Drift Detector

This paper summarizes work conducted throughout a SULI internship at Fermi National Accelerator Laboratory focused on building an unsupervised machine learning model for real-time anomaly detection in ProtoDUNE Horizontal Drift. Using simulated data, we trained an autoencoder model on a pure cosmic dataset, and evaluated it on both cosmic and neutrino events—making the model an anomaly detector. The goal was to make a model which matches or exceeds the current ADC Simple Window trigger algorithm so that our model can perform at the same rate but provide sensitivity to potential beyond-the-Standard-Model (BSM) signatures. In the end, we were able to construct a model which slightly exceeds the capabilities of the ADC Simple Window while remaining completely unsupervised, achieving 31.9 ± 0.2% (26.6 ± 0.2%) ν efficiency at 5 Hz (2 Hz), a 3.6 (3.2) percentage point increase. Additionally, 17.5 ± 0.3% (18.3 ± 0.3%) of the events that passed the autoencoder at 5 Hz (2 Hz) were missed by the current trigger algorithm. Future work will investigate alternative normalization methods, including quantile transformation, and evaluate the model on ProtoDUNE-HD detector-glitch data if that data becomes available.

Wilson, C. [Cincinnati U., RWC]↗

DOE OSTI2022

Preface to special topic: The High Repetition Rate Frontier in High-Energy-Density Physics

High-repetition-rate (HRR) experiments can collect large datasets with high temporal, spatial, and/or parametric resolution or large numbers of repeat measurements for statistics. HRR experiments also enable new experimental designs, including active feedback control loops and novel diagnostics, that can improve the reproducibility as well as the quantity of measurements. Together, these attributes make HRR experiments ideal for performing high-quality repeatable science. Until recently, these techniques have not been applied to high-energy-density–physics (HEDP) experiments, which are typically restricted to repetition rates of a few per day. However, recent advancements in lasers, pulsed-power drivers, target fabrication, and diagnostics are starting to change this fact, opening an exciting new frontier of HRR HEDP experiments. A mini-conference on this subject at the 2021 meeting of the American Physical Society Division of Plasma Physics brought together members of this growing community. As a result, the “High Repetition Rate Frontier in High-Energy-Density Physics” special topic in Physics of Plasmas highlights current progress in this exciting area.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2023

Accelerating gradient descent and Adam via fractional gradients

Here we propose a class of novel fractional-order optimization algorithms. We define a fractional-order gradient via the Caputo fractional derivatives that generalizes integer-order gradient. We refer it to as the Caputo fractional-based gradient, and develop an efficient implementation to compute it. A general class of fractional-order optimization methods is then obtained by replacing integer-order gradients with the Caputo fractional-based gradients. To give concrete algorithms, we consider gradient descent (GD) and Adam, and extend them to the Caputo fractional GD (CfGD) and the Caputo fractional Adam (CfAdam). We demonstrate the superiority of CfGD and CfAdam on several large scale optimization problems that arise from scientific machine learning applications, such as ill-conditioned least squares problem on real-world data and the training of neural networks involving non-convex objective functions. Numerical examples show that both CfGD and CfAdam result in acceleration over GD and Adam, respectively. We also derive error bounds of CfGD for quadratic functions, which further indicate that CfGD could mitigate the dependence on the condition number in the rate of convergence and results in significant acceleration over GD.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Reinterpreting fundamental plane correlations with machine learning

ABSTRACT This work explores the relationships between galaxy sizes and related observable galaxy properties in a large volume cosmological hydrodynamical simulation. The objectives of this work are to develop a better understanding of both the correlations between galaxy properties and the influence of environment on galaxy physics in order to build an improved model for the galaxy sizes, building off of the fundamental plane. With an accurate intrinsic galaxy size predictor, the residuals in the observed galaxy sizes can potentially be used for multiple cosmological applications, including making measurements of galaxy velocities in spectroscopic samples, estimating the rate of cosmic expansion, and constraining the uncertainties in the photometric redshifts of galaxies. Using projection pursuit regression, the model accurately predicts intrinsic galaxy sizes and have residuals which have limited correlation with galaxy properties. The model decreases the spatial correlation of galaxy size residuals by a factor of ∼5 at small scales compared to the baseline correlation when the mean size is used as a predictor.

Astronomy & Astrophysics↗

DOE OSTI2025

Machine Learning‐Augmented Molecular Dynamics Simulations (MD) Reveal Insights Into the Disconnect Between Affinity and Activation of ZTP Riboswitch Ligands

Abstract The challenge of targeting RNA with small molecules necessitates a better understanding of RNA–ligand interaction mechanisms. However, the dynamic nature of nucleic acids, their ligand‐induced stabilization, and how conformational changes influence gene expression pose significant difficulties for experimental investigation. This work employs a combination of computational and experimental methods to address these challenges. By integrating structure‐informed design, crystallography, and machine learning‐augmented all‐atom molecular dynamics simulations (MD), we synthesized, biophysically and biochemically characterized, and studied the dissociation of a library of small molecule activators of the 5‐aminoimidazole–4–carboxamide ribonucleotide triphosphate (ZTP) riboswitch, a ligand‐binding RNA motif that regulates bacterial gene expression. We uncovered key interaction mechanisms, revealing valuable insights into the role of ligand binding kinetics on riboswitch activation. Further, we established that ligand on‐rates determine activation potency as opposed to binding affinity and elucidated RNA structural differences, which provide mechanistic insights into the interplay of RNA structure on riboswitch activation.

Chemistry↗

DOE OSTI2023

Deep Reinforcement Learning Based Smart Water Heater Control for Reducing Electricity Consumption and Carbon Emission

Water heating is the third largest electricity consumer in U.S. households, after space heating and cooling. Thus, water heaters represent a significant potential for reducing electricity consumption and associated CO2 emissions of residential buildings. To this end, this study proposes a model-free deep reinforcement learning (RL) approach that aims to minimize the electricity consumption and the CO2 emissions of a heat pump water heater without affecting user comfort. In this approach, a set of RL agents focusing on either electricity saving or emission reduction, with different look ahead periods, were trained using the deep Q-networks (DQN) algorithm and their performance was tested on different hot water usage and Marginal Operating Emissions Rate (MOER) profiles. The testing results showed that the RL agents that focus on electricity saving can save electricity in the range of 12–22% by operating the water heater with maximum heat pump efficiency and minimum electric element utilization. On the other hand, the RL agents that focus on emission reduction reduced emissions in the range of 18–37% by making use of the variable MOER values. These RL agents used the heat pump and/or an element when the MOER values are low due to the availability of renewable energy sources (e.g., solar and wind) and mostly avoided the periods of carbon-intensive periods. Overall, these results showed that the proposed RL approach can help minimize the electricity consumption and the CO2 emissions of a heat pump water heater without having any prior knowledge about the device.

Amasyali, Kadir↗

DOE OSTI2025

Metastability and Ostwald step rule in the crystallisation of diamond and graphite from molten carbon

Abstract Experimental challenges in determining the phase diagram of carbon at temperatures and pressures near the graphite-diamond-liquid triple point are often related to the persistence of metastable crystalline or glassy phases, superheated crystals, or supercooled liquids. A deeper understanding of the crystallisation kinetics of diamond and graphite is crucial for effectively interpreting the outcomes of these experiments. Here, we reveal the microscopic mechanisms of diamond and graphite nucleation from liquid carbon through molecular simulations with first-principles machine learning potentials. Our simulations accurately reproduce the experimental phase diagram of carbon near the triple point and show that liquid carbon crystallises spontaneously upon cooling. Metastable graphite crystallises in the domain of diamond thermodynamic stability at pressures above the triple point. Furthermore, whereas diamond crystallises through a classical nucleation pathway, graphite follows a two-step process in which low-density fluctuations forego ordering. Calculations of the nucleation rates of the two competing phases confirm this result and reveal a manifestation of Ostwald’s step rule, where the strong metastability of graphite hinders the transformation to the stable diamond phase. Our results provide a key to interpreting melting and recrystallisation experiments and shed light on nucleation kinetics in polymorphic materials with deep metastable states.

Science & Technology - Other Topics↗

DOE OSTI2023

MArVD2: a machine learning enhanced tool to discriminate between archaeal and bacterial viruses in viral datasets

Abstract Our knowledge of viral sequence space has exploded with advancing sequencing technologies and large-scale sampling and analytical efforts. Though archaea are important and abundant prokaryotes in many systems, our knowledge of archaeal viruses outside of extreme environments is limited. This largely stems from the lack of a robust, high-throughput, and systematic way to distinguish between bacterial and archaeal viruses in datasets of curated viruses. Here we upgrade our prior text-based tool (MArVD) via training and testing a random forest machine learning algorithm against a newly curated dataset of archaeal viruses. After optimization, MArVD2 presented a significant improvement over its predecessor in terms of scalability, usability, and flexibility, and will allow user-defined custom training datasets as archaeal virus discovery progresses. Benchmarking showed that a model trained with viral sequences from the hypersaline, marine, and hot spring environments correctly classified 85% of the archaeal viruses with a false detection rate below 2% using a random forest prediction threshold of 80% in a separate benchmarking dataset from the same habitats.

Vik, Dean (ORCID:000000027546899X)↗