Search NASA⌕ Search

SEARCH · Search NASA

Results for “training 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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Language in Comparative Perspective

The twentieth century will be noted for a wide variety of scientific and technological advancements, including powered flight, antibiotics, space travel, and the breaking of the genetic code. It also should be noted as the century in which major psychological, as well as biological, continuities between animal and human have been defined. Charles Darwin (1859) was quite right when he anticipated continuity in mental processes, some of which provide for language. Though none will argue that any animal has the full capacity of humans for language, none should deny that at least some animals have quite impressive competencies for language skills, including speech comprehension. The finding that the language skills in the bonobo and the chimpanzee are likely more fully and efficiently developed as a result of early rearing than by formal training at a later age declares a continuity even stronger than that defined by the language acquisition potential of the ape. To clarify, because early rearing facilitates the emergence of language in ape as well as in child, a naturalness to the familiar course of language acquisition, whereby comprehension precedes production, is also corroborated. In turn, the continuity and the shared naturalness of language acquisition serve jointly to define an advanced and critical point of linkage between the genera Pan and Homo - and, as concluded by Domjan (1993), one worthy of contributing to the series of reconceptions of ourselves as anticipated by Ploog and Melnechuk (1971).

Rumbaugh, Duane M.↗
NASA NTRS2011

Integrated Modeling, Mapping, and Simulation (IMMS) Framework for Exercise and Response Planning

EmergenCy management personnel at federal, stale, and local levels can benefit from the increased situational awareness and operational efficiency afforded by simulation and modeling for emergency preparedness, including planning, training and exercises. To support this goal, the Department of Homeland Security's Science & Technology Directorate is funding the Integrated Modeling, Mapping, and Simulation (IMMS) program to create an integrating framework that brings together diverse models for use by the emergency response community. SUMMIT, one piece of the IMMS program, is the initial software framework that connects users such as emergency planners and exercise developers with modeling resources, bridging the gap in expertise and technical skills between these two communities. SUMMIT was recently deployed to support exercise planning for National Level Exercise 2010. Threat, casualty. infrastructure, and medical surge models were combined within SUMMIT to estimate health care resource requirements for the exercise ground truth.

Mapar, Jalal↗
NASA NTRS2017

Flow and Noise From Septa Nozzles

This investigation pertains to distributed propulsion system. Basically, the jet exhaust is divided and channeled through multiple compartments or septa. In one version of the concept each septum is to be driven by an electric fan, the power being supplied by engines suitably mounted on the airframe. In the latter hybrid case the need for heavy power trains is eliminated and system studies indicate a net benefit in efficiency. From aeroacoustics point of view, however, there are concerns. An immediate question is whether the noise from the multiple jets would be equal to or greater than that from an equivalent single jet. When multiple jets are placed side by side sometimes they resonate and produce more noise. In order to address these issues a fundamental model-scale experiment is being carried out at NASA Glenn Research Center (GRC). Preliminary results from this study have been presented recently. One of the key findings is that the noise from the septa nozzle can actually be less than that from the equivalent single nozzle. Continued studies make it clear that the flow from the septa nozzle may be quite sensitive to upstream passage geometry in each septum. This can have a profound impact on the evolution of the flow downstream as well as noise. These issues are currently being researched. The proposed paper is to summarize the results from the mainly experimental study that is to be aided by limited numerical simulation.

nozzle flow↗
NASA NTRSDate not supplied

10-kHz PLIF Thermometry for a Turbulent Jet Flame using Single Burst-mode OPO

Two-color Planar laser-induced fluorescence (TC-PLIF) thermometry techniques that employ two laser systems and two cameras face challenges when implemented in practical combustion facilities because of experimental complexity and multiple laser and camera requirements, particularly for high-speed TC-PLIF. To circumvent those problems, we developed a fast, dual-wavelength switching, burst-mode OPO technology to significantly reduce the experimental complexity of high-speed TC-PLIF thermometry and simplify its implementation in harsh combustion and flow test facilities. A fast, dual-wavelength switched seed laser enabled a high-energy, high-repetition-rate burst-mode laser to generate two 10-kHz pulse trains at wavelengths of ~354.8 nm. The injection-seeded OPO efficiently converts the burst-mode laser output to285.62 nm and 285.67 nm to excite the Q2(12) and P1(8) OH transitions. PLIF images were collected from each of the two excitation transitions with a single camera and an UV intensifier, and intensity ratios from the images were used to determine local temperatures. Ten kHz hydroxyl radical (OH) TC-PLIF for premixedCH4/Air/H2 jet flame was demonstrated.

thermometry↗
NASA NTRSDate not supplied

10-kHz PLIF Thermometry for Turbulent Jet Flame using Single Burst-mode OPO

Two-color Planar Laser-Induced Fluorescence (TC-PLIF) thermometry techniques that employ two laser systems and two cameras face challenges when implemented in practical combustion facilities because of experimental complexity and multiple laser and camera requirements, particularly for high-speed TC-PLIF. To circumvent those problems, we developed a fast, dual-wavelength switching, burst-mode OPO technology to significantly reduce the experimental complexity of high-speed TC-PLIF thermometry and simplify its implementation in harsh combustion and flow test facilities. A fast, dual-wavelength switched seed laser enabled a high-energy, high-repetition-rate burst-mode laser to generate two 10-kHz pulse trains at wavelengths of ~354.8 nm. The injection-seeded OPO efficiently converts the burst-mode laser output to 285.62 nm and 285.67 nm to excite the Q2(12) andP1(8) OH transitions. PLIF images were collected from each of the two excitation transitions with a single camera and an UV intensifier, and intensity ratios from the images were used to determine local temperatures. Ten kHz hydroxyl radical (OH) TC-PLIF for premixedCH4/Air/H2 jet flame was demonstrated.

thermometry↗
DOE OSTI2022

Model-Free Building Temperature Control and Power Allocation Under Measurement Time Delays

Taking a step towards a greener planet has created an increased need for a higher integration of renewable energy resources into the electric grid. Nonetheless, the intermittency and uncertainty associated with renewable generation have slowed down this integration. Demand response (DR) has been recently adopted to address this challenge by utilizing demand side flexibility and enabling the participation of many grid-interactive efficient buildings (GEBs). However, existing DR methods require significant modeling and/or training efforts and are computationally expensive. To address the aforementioned issues, we propose a model-free control (MFC)-based strategy that is robust to the time delays in the temperature measurements of the thermostatically controlled loads (TCLs). It assigns to each GEB a local controller to maintain the TCLs’ temperatures within desired comfort levels, while the load aggregator (LA) allocates the assigned reference power provided by the distribution system operator (DSO) to support a specific grid service, such as demand peak reduction, load shifting, balancing supply and demand, and consuming the solar photovoltaic power locally. We investigate the effects of such loss of information on the local control action as well as on meeting the power allocation constraint. We conclude that, for an appropriate choice of design parameters, the proposed MFC controller is satisfactorily robust to measurement time delays.

Telsang, Bhagyashri↗
DOE OSTI2020

Automated Cloud Based Long Short-Term Memory Neural Network Based SWE Prediction

Snow derived water is a critical component of the US water supply. Measurements of the Snow Water Equivalent (SWE) and associated predictions of peak SWE and snowmelt onset are essential inputs for water management efforts. This paper aims to develop an integrated framework for real-time data ingestion, estimation, prediction and visualization of SWE based on daily snow datasets. In particular, we develop a data-driven approach for estimating and predicting SWE dynamics using the Long Short-Term Memory neural network (LSTM) method. Our approach uses historical datasets (precipitation, air temperature, SWE, and snow thickness) collected at NRCS Snow Telemetry (SNOTEL) stations to train the LSTM network and current year data to predict SWE behavior. The performance of our prediction was compared for different prediction dates and prediction training datasets. Our results suggest that the proposed LSTM network can be an efficient tool for forecasting the SWE timeseries, as well as Peak SWE and snowmelt timing. Results showed that the window size impacts the model performance (where the Nash Sutcliffe efficiency (NSE) ranged from 0.96 to 0.85 and the Rooted Mean Square Error (RMSE) ranged from 0.038 to 0.07) with an optimum number that should be calibrated for different stations and climate conditions. In addition, by implementing the LSTM prediction capability in a cloud based site-monitoring platform, we automate model-data integration. By making the data accessible through a graphical web interface and an underlying API which exposes both training and prediction capabilities. The associated results can be made easily accessible to a broad range of stakeholders.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Quasi-Classical Trajectory Calculation of Rate Constants Using an Ab Initio Trained Machine Learning Model (aML-MD) with Multifidelity Data

Machine learning (ML) provides a great opportunity for the construction of models with improved accuracy in classical molecular dynamics (MD). However, the accuracy of a ML trained model is limited by the quality and quantity of the training data. Generating large sets of accurate ab initio training data can require significant computational resources. Furthermore, inconsistent or incompatible data with different accuracies obtained using different methods may lead to biased or unreliable ML models that do not accurately represent the underlying physics. Recently, transfer learning showed its potential for avoiding these problems as well as for improving the accuracy, efficiency, and generalization of ML models using multifidelity data. In this work, ab initio trained ML-based MD (aML-MD) models are developed through transfer learning using DFT and multireference data from multiple sources with varying accuracy within the Deep Potential MD framework. Further, the accuracy of the force field is demonstrated by calculating rate constants for the H + HO 2 → H 2 + 3 O 2 reaction using quasi-classical trajectories. We show that the aML-MD model with transfer learning can accurately predict the rate constants while reducing the computational cost by more than five times compared to the use of more expensive quantum chemistry training data sets. Hence, the aML-MD model with transfer learning shows great potential in using multifidelity data to reduce the computational cost involved in generating the training set for these potentials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Coefficient-to-Basis Network: a fine-tunable operator learning framework for inverse problems with adaptive discretizations and theoretical guarantees

We propose a Coefficient-to-Basis Network (C2BNet), a novel framework for solving inverse problems within the operator learning paradigm. C2BNet efficiently adapts to different discretizations through fine-tuning, using a pre-trained model to significantly reduce computational cost while maintaining high accuracy. Unlike traditional approaches that require retraining from scratch for new discretizations, our method enables seamless adaptation without sacrificing predictive performance. Furthermore, we establish theoretical approximation and generalization error bounds for C2BNet by exploiting low-dimensional structures in the underlying datasets. Our analysis demonstrates that C2BNet adapts to low-dimensional structures without relying on explicit encoding mechanisms, highlighting its robustness and efficiency. To validate our theoretical findings, we conducted extensive numerical experiments that showcase the superior performance of C2BNet on several inverse problems. The results confirm that C2BNet effectively balances computational efficiency and accuracy, making it a promising tool to solve inverse problems in scientific computing and engineering applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Exponential concentration in quantum kernel methods

Kernel methods in Quantum Machine Learning (QML) have recently gained significant attention as a potential candidate for achieving a quantum advantage in data analysis. Among other attractive properties, when training a kernel-based model one is guaranteed to find the optimal model’s parameters due to the convexity of the training landscape. However, this is based on the assumption that the quantum kernel can be efficiently obtained from quantum hardware. In this work we study the performance of quantum kernel models from the perspective of the resources needed to accurately estimate kernel values. We show that, under certain conditions, values of quantum kernels over different input data can be exponentially concentrated (in the number of qubits) towards some fixed value. Thus on training with a polynomial number of measurements, one ends up with a trivial model where the predictions on unseen inputs are independent of the input data. We identify four sources that can lead to concentration including expressivity of data embedding, global measurements, entanglement and noise. For each source, an associated concentration bound of quantum kernels is analytically derived. Lastly, we show that when dealing with classical data, training a parametrized data embedding with a kernel alignment method is also susceptible to exponential concentration. Our results are verified through numerical simulations for several QML tasks. Altogether, we provide guidelines indicating that certain features should be avoided to ensure the efficient evaluation of quantum kernels and so the performance of quantum kernel methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

The Rise of Neural Networks for Materials and Chemical Dynamics

Machine learning (ML) is quickly becoming a premier tool for modeling chemical processes and materials. ML-based force fields, trained on large data sets of high-quality electron structure calculations, are particularly attractive due their unique combination of computational efficiency and physical accuracy. This Perspective summarizes some recent advances in the development of neural network-based interatomic potentials. Designing high-quality training data sets is crucial to overall model accuracy. One strategy is active learning, in which new data are automatically collected for atomic configurations that produce large ML uncertainties. Another strategy is to use the highest levels of quantum theory possible. Transfer learning allows training to a data set of mixed fidelity. A model initially trained to a large data set of density functional theory calculations can be significantly improved by retraining to a relatively small data set of expensive coupled cluster theory calculations. These advances are exemplified by applications to molecules and materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

FINETUNA: fine-tuning accelerated molecular simulations

Abstract Progress towards the energy breakthroughs needed to combat climate change can be significantly accelerated through the efficient simulation of atomistic systems. However, simulation techniques based on first principles, such as density functional theory (DFT), are limited in their practical use due to their high computational expense. Machine learning approaches have the potential to approximate DFT in a computationally efficient manner, which could dramatically increase the impact of computational simulations on real-world problems. However, they are limited by their accuracy and the cost of generating labeled data. Here, we present an online active learning framework for accelerating the simulation of atomic systems efficiently and accurately by incorporating prior physical information learned by large-scale pre-trained graph neural network models from the Open Catalyst Project. Accelerating these simulations enables useful data to be generated more cheaply, allowing better models to be trained and more atomistic systems to be screened. We also present a method of comparing local optimization techniques on the basis of both their speed and accuracy. Experiments on 30 benchmark adsorbate-catalyst systems show that our method of transfer learning to incorporate prior information from pre-trained models accelerates simulations by reducing the number of DFT calculations by 91%, while meeting an accuracy threshold of 0.02 eV 93% of the time. Finally, we demonstrate a technique for leveraging the interactive functionality built in to Vienna ab initio Simulation Package (VASP) to efficiently compute single point calculations within our online active learning framework without the significant startup costs. This allows VASP to work in tandem with our framework while requiring 75% fewer self-consistent cycles than conventional single point calculations. The online active learning implementation, and examples using the VASP interactive code, are available in the open source FINETUNA package on Github.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Search for HH → bbτ⁺τ⁻ Using Run 3 Scouting Data Analyze b-tagging and tau-tagging Performance with Unified Particle Transformer

B-tagging and tau-tagging performances play an important role in the search for the rare event HH → bbτ⁺τ⁻. A transformer-based neural network, Unified Particle Transformer, is applied for both tagging tasks, and Run 3 proton–proton collision scouting data at center-of-mass energy of 13.6 TeV is used. The scouting data stream accepts events at a much higher rate compared to traditional triggers, but stores only the objects reconstructed in the trigger, no low-level detector information. Therefore, existing taggers trained for the offline event reconstruction cannot be used. Analysis of the SoftMax plots, ROC/AUC curves, confusion matrix, accuracy and losses are used to evaluate model performance. Specifically, the tagging efficiency of the signal and misidentification probability across multiple background processes are compared for varying working points. Different training samples with distinct distributions of jet flavors are utilized and related model performances are analyzed. Interpretability methods, such as Integrated Gradients, may further be applied to study the input features’ influence on the model’s decisions, providing insights into potential improvements.

Chen, Blair [Purdue U., West Lafayette; Fermilab]↗
DOE OSTI2022

Fed-DeepONet: Stochastic Gradient-Based Federated Training of Deep Operator Networks

The Deep Operator Network (DeepONet) framework is a different class of neural network architecture that one trains to learn nonlinear operators, i.e., mappings between infinite-dimensional spaces. Traditionally, DeepONets are trained using a centralized strategy that requires transferring the training data to a centralized location. Such a strategy, however, limits our ability to secure data privacy or use high-performance distributed/parallel computing platforms. To alleviate such limitations, in this paper, we study the federated training of DeepONets for the first time. That is, we develop a framework, which we refer to as Fed-DeepONet, that allows multiple clients to train DeepONets collaboratively under the coordination of a centralized server. To achieve Fed-DeepONets, we propose an efficient stochastic gradient-based algorithm that enables the distributed optimization of the DeepONet parameters by averaging first-order estimates of the DeepONet loss gradient. Then, to accelerate the training convergence of Fed-DeepONets, we propose a moment-enhanced (i.e., adaptive) stochastic gradient-based strategy. Finally, we verify the performance of Fed-DeepONet by learning, for different configurations of the number of clients and fractions of available clients, (i) the solution operator of a gravity pendulum and (ii) the dynamic response of a parametric library of pendulums.

Moya, Christian↗
DOE OSTI2022

Public – Private Partnership to Promote Efficient Manufacturing and Workforce Development (IAC Final Technical Report)

Through delivering ninety (90) energy assessments to small- and medium-sized manufacturing facilities in and around Tennessee, significant understandings were gained through providing detailed energy assessment reports to manufacturers and training seventy-seven (77) engineering students in which thirty-five (35) certified IAC students were recognized by DOE. The robust involvement of Tennessee Valley Authority (TVA), local utility and Tennessee Tech’s Cybersecurity Education, Research, and Outreach Center (CEROC) in majority of assessments made the technical operation very effective where leaded to 40.5% implementation rate of energy recommendations. Other benefits of the award to the public are a dynamic modeling tool capable of analyzing existing cooling towers for energy use optimization was developed and presented to DOE IAC, providing technical assistance to non-participating manufacturers in the form of workshop and training, publishing fifteen (15) peer-reviewed conference and journal papers as well as a book chapter in the area of industrial energy efficiency field, assisting the TVA Magnolia Combined Cycle Power Plant to become the First 50001 Ready Certified Power Plant in the U.S. through briefing them on ISO 50001 and 50001 Ready as well as providing an energy assessment to the plant, assisted the new IAC center at Clemson University with on-site and remote support, and provided assessment and training in unique areas of water, waste water, cyber security and smart manufacturing to our clients, students and community.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Automatic identification and quantification of dense microcracks in high-performance fiber-reinforced cementitious composites through deep learning-based computer vision

Highlights: • A method is presented to detect, locate, quantify, and visualize dense microcracks in HPFRCC. • Quantification of dense microcracks is realized using deep learning method for the first time. • The presented method uses deep learning models that are trained using a realistic dataset size. • The presented method has a high computation efficiency for identifying and quantifying cracks. • The presented method provides crack width with errors up to 50 μm and a R{sup 2} value of 0.984. High-performance fiber-reinforced cementitious composites (HPFRCCs) feature high mechanical strengths, crack resistance, and durability. Under excessive loading, HPFRCCs demonstrate dense microcracks that are difficult to identify using existing methods. This study presents a computer vision method for identification, quantification, and visualization of microcracks in HPFRCCs based on deep learning. The presented method integrates multiple deep learning models and computer vision techniques in a hierarchical architecture. The crack pattern (e.g., number, width, and spacing of cracks) are automatically determined from pictures without human intervention. This study shows that the presented method achieves an accuracy of 0.992 for crack detection and an accuracy finer than 50 μm (R{sup 2} > 0.984) for quantification of crack width when deep learning models are trained using only 200 pictures of HPFRCCs and 200 pictures of conventional concrete with incorporation of data augmentation. The presented method is expected to be also applicable to other materials featuring complex cracks.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Joint physics-based and data-driven time-lapse seismic inversion: Mitigating data scarcity

In carbon capture and sequestration (CCS), developing rapid and effective imaging techniques is crucial for real-time monitoring of the spatial and temporal dynamics of CO 2 propagation during/after injection. With continuing improvements in computational power and data storage, data-driven techniques based on machine learning (ML) have been effectively applied to seismic inverse problems. In particular, ML helps alleviate the ill-posedness and high computational cost of full-waveform inversion (FWI). However, such data-driven inversion techniques require massive high-quality training data sets to ensure prediction accuracy, which hinders their application to time-lapse monitoring of CO 2 sequestration. We propose an efficient “hybrid” time-lapse workflow that combines physics-based FWI and data-driven ML inversion. The scarcity of the available training data is addressed by developing a new data-generation technique with physics constraints. The method is vali dated on a synthetic CO 2 -sequestration model based on the Kimberlina storage reservoir in California. The proposed approach is shown to synthesize a large volume of high-quality, physically realistic training data, which is critically important in accurately characterizing the CO 2 movement in the reservoir. In conclusion, the developed hybrid methodology can also simultaneously predict the variations in velocity and saturation and achieve high spatial resolution in the presence of realistic noise in the data.

58 GEOSCIENCES↗
DOE OSTI2024

Seed classification with random forest models

Premise: To improve forest conservation monitoring, we developed a protocol to automatically count and identify the seeds of plant species with minimal resource requirements, making the process more efficient and less dependent on human operators. Methods and Results: Seeds from six North American conifer tree species were separated from leaf litter and imaged on a flatbed scanner. In the most successful species-classification approach, an ImageJ macro automatically extracted measurements for random forest classification in the software R. The method allows for good classification accuracy, and the same process can be used to train the model on other species. Conclusions: This protocol is an adaptable tool for efficient and consistent identification of seed species or potentially other objects. Automated seed classification is efficient and inexpensive, making it a practical solution that enhances the feasibility of large-scale monitoring projects in conservation biology.

59 BASIC BIOLOGICAL SCIENCES↗