Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning efficiency”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,315 records · Page 73

Holistic Approach to Data Center Energy Efficiency

This presentation discusses NREL's Energy System Integrations Facility and NREL's holistic design approach to sustainable data centers that led to the world's most energy-efficient data center. It describes Peregrine, a warm water liquid cooled supercomputer, waste heat reuse in the data center, demonstrated PUE and ERE, and lessons learned during four years of operation.

97 MATHEMATICS AND COMPUTING↗

A deep learning-based direct forecasting of CO 2 plume migration

Accurate and timely forecasts of CO 2 plume evolution in geological reservoirs are crucial for CO 2 migration detection, leakage risk assessment, and operation decision support. Conventional forecasting usually adopts a two-step strategy, first calibrating reservoir model parameters against observations using iterative inverse modeling (or history matching) and then applying the calibrated model for predictions. This method impedes real-time forecasts due to the heavy computational demand in inverse modeling and may suffer from poor prediction accuracy because of the limited observation data. In this work, we propose a deep learning-based latent space mapping framework to forecast CO 2 plume migration directly by avoiding the inverse modeling. We first use the convolutional autoencoder to map the high-dimensional complex plume extents onto low-dimensional latent space. Next, we use neural networks to learn the relationship between the observation variables and the prediction latent variables. And then for given observation data, we infer the prediction values directly. This one-step direct forecasting is computationally efficient which requires a few number of parallelizable reservoir simulations and it can provide accurate predictions with limited observations by learning the observation-prediction relationship in the reduced dimension. Therefore, our proposed method enables an in-time forecast of dynamic CO 2 plume distributions. In this work, we demonstrate the effectiveness and accuracy of our method in predicting the CO 2 plume migration using four metrics such as plume area, centroid movement distance, and plume spreading in the primary and secondary directions. And the spatio-temporal evolution patterns of plume migration under diverse geological complexities are also accurately quantified.

15 GEOTHERMAL ENERGY↗

Enabling deeper learning on big data for materials informatics applications

Abstract The application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.

36 MATERIALS SCIENCE↗

3D_MolGNN_RL

3D-MolGNNRL, couples reinforcement learning (RL) to a deep generative model based on 3D-Scaffold to generate target candidates specific to a protein pocket building up atom by atom from the core scaffold. 3D-MolGNNRL provides an efficient way to optimize key features within a protein pocket using a parallel graph neural network model. The agent learns to build molecules in 3D space while optimizing the binding affinity, potency, and synthetic accessibility of the candidates generated for the SARS-CoV-2 Main protease

Kumar, Neeraj↗

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]↗

Characterization and Quantification of Radiation-Induced Clusters/Precipitates in RPV Steels Using STEM-EDS and Machine Learning

Over the operational lifespan of a nuclear reactor, reactor pressure vessel (RPV) steels are subjected to significant neutron irradiation, resulting in complex microstructural changes and the consequent degradation of mechanical properties. Various physically motivated correlation models have been developed to predict neutron irradiation-induced embrittlement of RPVs under different irradiation conditions. However, the efficient and accurate characterizations and quantification of radiation-induced clusters in RPVs are still challenging, which will affect the precision of the predictive models for embrittlement of RPV components. In the DOE Visiting Faculty Program (VFP) research work at Oak Ridge National Lab (ORNL), I integrate machine learning to aid Scanning Transmission Electron Microscopy – Energy Dispersive X-ray Spectroscopy (STEM-EDS) analyses, which improve the characterization and quantification of radiation-induced clusters in RPV steels, thereby enabling more accurate predictions of material behavior under irradiation. The surveillance base- and welded- RPV steels were annealed at various temperatures of 340 °C, 450 °C and 500 °C for up to 168 hours, respectively. Afterwards, I have characterized radiation-induced clusters using advanced STEM-EDS techniques and subsequently applying machine learning algorithms to analyze and refine STEM-EDS datasets, enhancing the quantification of clusters compositions and distributions. In the end, an efficient workflow for integrating STEM-EDS data analysis with machine learning to address challenges including noise reduction has been developed. The completion of this VFP work will support bridge critical gaps in the accurate quantification of radiation-induced clusters in RPV steels using STEM-EDS and support the development of more precise models for predicting RPV embrittlement in the Light Water Reactor Sustainability program supported by Department of Energy and enhancing the collaboration between ORNL and Alred University. The outcome of the VFP project will leverage a few research papers submission to peer-reviewed journals in the relevant scientific field and a few oral presentations at national and international conferences.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

A Flexible-blocking Based Approach for Performance Tuning of Matrix Multiplication Routines for Large Matrices with Edge Cases

Efficient and scalable matrix operations are being highly demanding in the recent era of Machine Learning, Deep Learning, and Big Data Analytics. The two commonly used matrix-matrix operations in the Basic Linear Algebra Subprograms (BLAS) specification are General Matrix-Matrix multiplication (GEMM) and Symmetric Rank-k update (SYRK). The SYRK routine is a specialization of the GEMM routine, where half of the multiplications are skipped as the resultant matrix is known to be symmetric. Fortunately, several linear algebra libraries implement these BLAS routines quite efficiently. The libraries usually partition the input matrices into blocks and place them in processor caches, thus improving performance by leveraging the caches. However, the contemporary libraries are highly optimized for squarish matrices, but the performance degrades significantly for the matrices with edge case (strictly thin or strictly fat shapes) in the multicore machine. The primary reason is that the current state-of-the-art libraries make fixed block shapes based on a processor architecture, and do not consider the shape of the input matrices. In this paper, we propose a new blocking approach, we name it Flexible-blocking, to mitigate the scalability issues. In contrast to the contemporary libraries, our approach formulates the blocks of the input matrices based on the shapes of the matrices as well as the number of threads used in the implementation. Our proposed technique shows noticeable performance improvement on multicore shared-memory machines for the edge case matrices.

Hossain, Md Mosharaf↗

Co-design of Advanced Architectures for Graph Analytics using Machine Learning

A graph is an excellent way of representing relationships among entities. We can use graph analytics to synthesize and analyze such relational data, and extract relevant features that are useful for various tasks such as machine learning. Considering the crucial role of graph analytics in various domains, it is important and timely to investigate the right hardware configurations that can achieve optimal performance for graph workloads on future high-performance computing systems. Design space exploration studies facilitate the selection of appropriate configurations (e.g. memory) to achieve a desired system performance. Recently, the approach of accelerating graph analytics using persistent non-volatile memory has gained a lot of attention. Traditional system simulators such as Gem5 and NVMain can be used to explore the design space of these advanced memory architectures for graph workloads. However, these simulators are slow in execution thus limiting the efficiency of design space exploration studies. To overcome this challenge, we proposed a machine learning based approach to co-design advanced memory architectures for graph workloads. We tested our approach with DRAM, non-volatile memory, and hybrid memory (DRAM+NVM) using a breadth first search benchmark algorithm. Our results showed the applicability of the proposed machine learning based approach to the co-design of the advanced memory architectures. In this paper, we provide recommendations on selecting advanced memory architectures to achieve desired performance for graph workloads. We also discuss the performances of different machine learning models that were considered in this study.

Kurte, Kuldeep↗

Adaptive learning-driven high-throughput synthesis of oxygen reduction reaction Fe–N–C electrocatalysts

Reducing human reliance on inefficient energy systems and fossil fuels has become more urgent due to the consequences of global climate change. However, traditional trial-and-error approaches have hampered our ability to accelerate the discovery and implementation of functional materials for efficient energy conversion devices, such as polymer electrolyte fuel cells (PEFCs). To address this, we develop an adaptive learning framework that integrates machine learning and state-of-the-art capabilities in high-throughput synthesis to achieve expedited optimization of iron-nitrogen-carbon PEFC oxygen reduction reaction (ORR) electrocatalysts. We use statistical inference, uncertainty quantification, and global optimization to build a computational design-of-experiment tool that identifies the optimum compositions to be investigated next to reduce the demands placed on experimental materials discovery. We benchmark the ability of the proposed strategy to discover optimum catalyst synthesis conditions in a six-dimensional search space when starting with a thirty-six-sample database. By following the adaptive learning strategy, we synthesize fourteen new catalysts from approximately ten billion unique compositions and discover four catalysts that outperform all original samples. The best machine learning-optimized catalyst is 33% more active than the highest-performing one in the initial database, showing an ORR activity seven times larger than those typically reported for the same class of materials.

36 MATERIALS SCIENCE↗

Multi-fidelity Bayesian neural networks: Algorithms and applications

Here we propose a new class of Bayesian neural networks (BNNs) that can be trained using noisy data of variable fidelity, and we apply them to learn function approximations as well as to solve inverse problems based on partial differential equations (PDEs). These multi-fidelity BNNs consist of three neural networks: The first is a fully connected neural network, which is trained following the maximum a posteriori probability (MAP) method to fit the low-fidelity data; the second is a Bayesian neural network employed to capture the cross-correlation with uncertainty quantification between the low- and high-fidelity data; and the last one is the physics-informed neural network, which encodes the physical laws described by PDEs. For the training of the last two neural networks, we first employ the mean-field variational inference (VI) to maximize the evidence lower bound (ELBO) to obtain informative prior distributions for the hyperparameters in the BNNs, and subsequently we use the Hamiltonian Monte Carlo (HMC) method to estimate accurately the posterior distributions for the corresponding hyperparameters. We demonstrate the accuracy of the present method using synthetic data as well as real measurements. Specifically, we first approximate a one- and four-dimensional function, and then infer the reaction rates in one- and two-dimensional diffusion-reaction systems. Moreover, we infer the sea surface temperature (SST) in the Massachusetts and Cape Cod Bays using satellite images and in-situ measurements. Taken together, our results demonstrate that the present method can capture both linear and nonlinear correlation between the low- and high-fidelity data adaptively, identify unknown parameters in PDEs, and quantify uncertainties in predictions, given a few scattered noisy high-fidelity data. Finally, we demonstrate that we can effectively and efficiently reduce the uncertainties and hence enhance the prediction accuracy with an active learning approach, using as examples a specific one-dimensional function approximation and an inverse PDE problem.

97 MATHEMATICS AND COMPUTING↗

Energy Impact Illinois (Final Technical Report)

Energy Impact Illinois (EI2) is an alliance of government organizations, nonprofits, and regional utility companies led by the Chicago Metropolitan Agency for Planning (CMAP) that is dedicated to helping communities in the Chicago metropolitan area become more energy efficient. Originally organized as the Chicago Region Retrofit Ramp-Up (CR3), EI2 became part of the nationwide Better Buildings Neighborhood Program (BBNP) in May 2010 after receiving a $25 million award from the U.S. Department of Energy (DOE) authorized through the American Recovery and Reinvestment Act of 2009 (ARRA). The program’s primary goal was to fund initiatives that mitigate barriers to energy efficiency retrofitting activities across residential, multifamily, and commercial building sectors in the seven-county CMAP region and to help to build a sustainable energy efficiency marketplace. The EI2 Final Technical Report provides a detailed review of the strategies, implementation methods, challenges, lessons learned, and final results of the EI2 program during the initial grant period from 2010-2013. During the program period, EI2 successfully increased direct retrofit activity in the region and was able to make a broader impact on the energy efficiency market in the Chicago region. As the period of performance for the initial grant comes to an end, EI2’s legacy raises the bar for the region in terms of helping homeowners and building owners to take action on the continually complex issue of energy efficiency.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Joint Chance Constraints Reduction Through Learning in Active Distribution Networks

Due to an increase in distributed generation and controllable loads, distribution networks are frequently operating under high levels of uncertainty. Joint chance constraints, which seek to satisfy multiple constraints simultaneously with a prescribed probability, are one way to incorporate uncertainty across sets of constraints for optimization and control of these networks. Due to the complexity of evaluating these constraints directly, sampling approaches or approximations can be used to transform the joint chance constraint into deterministic constraints. However, sampling techniques may be extremely computationally expensive and not suitable for physical networks operating on fast timescales, and conservative approximations may needlessly result in a much higher cost of system operation. The proposed framework aims to provide a scalable, data-driven approach which learns operational trends in a power network, eliminates zero-probability events (e.g., inactive constraints), and uses this additional information to accurately and efficiently approximate the joint chance constraint directly.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Using Reinforcement Learning to Optimize Quantum Circuits in the Presence of Noise

As we move towards devices which utilize more qubits, it becomes increasing more important to map quantum circuits in a way that uses resources efficiently as well as maximizes the reliability of the results of that circuit. To this end, we will need to rely on heuristic algorithms, specifically reinforcement learning (RL) as a method of building quantum circuits based on observations of the noise characteristics in its environment.

Guy, Khalil↗

Building a DFT+U machine learning interatomic potential for uranium dioxide

Despite uranium dioxide (UO 2 ) being a widely used nuclear fuel, fuel performance models rely extensively on empirical correlations of material behavior, leveraging the historical operating experience of UO 2 . Mechanistic models that consider an atomistic understanding of the processes governing fuel performance (such as fission gas release and creep) will enable a better description of fuel behavior under non-prototypical conditions such as in new reactor concepts or for modified UO 2 fuel compositions. To this end, molecular dynamics simulation is a powerful tool for rapidly predicting physical properties of proposed fuel candidates. However, the reliability of these simulations depends largely on the accuracy of the atomic forces. Traditionally, these forces are computed using either a classical force field (FF) or density functional theory (DFT). While DFT is relatively accurate, the computational cost is burdensome, especially for f-electron elements, such as actinides. By contrast, classical FFs are computationally efficient but are less accurate. For these reasons, we report a new accurate machine learning interatomic potential (MLIP) for UO 2 that provides high-fidelity reproduction of DFT forces at a similar low cost to classical FFs. We employ an active learning approach that autonomously augments the DFT training data set to iteratively refine the MLIP. To further improve the quality of our predictions, we utilize transfer learning to retrain our MLIP to higher-accuracy DFT+U data. We validate our MLIPs by comparing predicted physical properties (e.g., thermal expansion and elastic properties) with those from existing classical FFs and DFT/DFT+U calculations, as well as with experimental data when available.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

State of the art astronomical simulations have provided datasets which enabled the training of novel deep learning techniques for constraining cosmological parameters. However, differences in subgrid physics implementation and numerical approximations among simulation suites lead to differences in simulated datasets, which pose a hard challenge when trying to generalize across diverse data domains and ultimately when applying models to observational data. Recent work reveals deep learning algorithms are able to extract more information from complex cosmological simulations than summary statistics like power spectra. We introduce Domain Adaptive Graph Neural Networks (DA-GNNs), trained on CAMELS data, inspired by CosmoGraphNet (Villanueva-Domingo et al 2023). By utilizing GNNs, we can capitalize on their capacity to capture both astrophysical and topological features of galaxy distributions. Mixing these capabilities with domain adaptation techniques such as Maximum Mean Discrepancy (MMD), which enable extraction of domain-invariant features, our framework demonstrates enhanced accuracy and robustness. We present experimental results, including the alignment of distributions across domains through data visualization. These findings suggest that DA-GNNs are an efficient way of extracting domain independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗

Virtual Neuron: A Neuromorphic Approach for Encoding Numbers

Neuromorphic computers perform computations by emulating the human brain and are expected to be indispensable for energy-efficient computing in the future. They are primarily used in spiking neural network-based machine learning applications. However, neuromorphic computers are unable to preprocess data for these applications. Currently, data is preprocessed on a CPU or a GPU-this incurs a significant cost of transferring data from the CPU/GPU to the neuromorphic processor and vice versa. This cost can be avoided if preprocessing is done on the neuromorphic processor. To efficiently preprocess data on a neuromorphic processor, we first need an efficient mechanism for encoding data that can lend itself to all general-purpose preprocessing operations. Current encoding approaches have limited applicability and may not be suitable for all preprocessing operations. In this paper, we present the virtual neuron as a mechanism for encoding integers and rational numbers on neuromorphic processors. We evaluate the performance of the virtual neuron on physical and simulated neuromorphic hardware and show that it can perform an addition operation using 23 nJ of energy on average using a mixed-signal, memristor-based neuromorphic processor. The virtual neuron encoding approach is the first step in preprocessing data on a neuromorphic processor.

Date, Prasanna↗

Scalable FPGA Accelerator for Deep Convolutional Neural Networks with Stochastic Streaming

Here, FPGA-based heterogeneous computing platform, due to its extreme logic reconfigurability, emerges to be a strong contender as computing fabric in modern AI. As a result, various FPGA-based accelerators for deep CNN—the key driver of modern AI—have been proposed due to their advantages of high performance, reconfigurability, and fast development round, etc. In general, the consensus among researchers is that, although FPGA-based accelerator can achieve much higher energy efficiency, its raw computing performance lags behind when compared with GPUs with similar logic density. In this paper, we develop an alternative methodology to efficiently implement CNNs with FPGAs that outperform GPUs in terms of both power consumption and performance. Our key idea is to design a scalable hardware architecture and circuit design for large-scale CNNs that leverages a stochastic-based computing principle. Specifically, there are three major performance advantages. First, all key components of our deep learning CNN are designed and implemented to compute stochastically, thus achieving excellent computing performance and energy efficiency. Second, because our proposed CNN architecture enables a stream-mode computing, all of its stages can process even the partial results from preceding stages, therefore not incurring unnecessary latency due to data dependency. Finally, our FPGA-based deep CNN also provides a superior hardware scalability when compared with conventional FPGA implementations by reducing the bandwidth requirement between layers. The results show that our proposed CNN architecture significantly outperforms all previous FPGA-based deep CNN implementation approaches. It achieves 1.58x more GOPS, 6.42x more GOPS/Slice, and 10.92x more GOPS/W when compared with state-of-the-art CNN architecture. The top-5 accuracy of stochastic VGG-16 CNN is 86.77 percent with 18.91 fps frame rate.

97 MATHEMATICS AND COMPUTING↗