Search NASA⌕ Search

SEARCH · Search NASA

Results for “ADVANCED NETWORKING”

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 883 records · Page 49

Digital Modeling on Large Kernel Metamaterial Neural Network

Deep neural networks (DNNs) utilized recently are physically deployed with computational units (e.g., CPUs and GPUs). Such a design might lead to a heavy computational burden, significant latency, and intensive power consumption, which are critical limitations in applications such as Internet of Things (IoT), edge computing, and usage of drones. Recent advances in optical computational units (e.g., metamaterial) have shed light on energy-free and light-speed neural networks. However, the digital design of the metamaterial neural network (MNN) is fundamentally limited by its physical limitations, such as precision, noise, and bandwidth during fabrication. Moreover, the unique advantages of MNN’s (e.g., light-speed computation) are not fully explored via standard 3×3 convolution kernels. In this paper, we propose a novel large kernel metamaterial neural network (LMNN) that maximizes the digital capacity of the state-of-the-art (SOTA) MNN with model re-parametrization and network compression, while also considering the optical limitation explicitly. The new digital learning scheme can maximize the learning capacity of MNN while modeling the physical restrictions of meta-optics. With the proposed LMNN, the computation cost of the convolutional front-end can be offloaded to fabricated optical hardware. The experimental results on two publicly available datasets demonstrate that the optimized hybrid design improved classification accuracy while reducing computational latency. In conclusion, the development of the proposed LMNN is a promising step towards the ultimate goal of energy-free and light-speed AI.

97 MATHEMATICS AND COMPUTING↗

Advances in High-Power Wireless Charging Systems: Overview and Design Considerations

Wireless charging systems are foreseen as an effective solution to improve the convenience and safety of conventional conductive chargers. As this technology has matured, recent broad applications of wireless chargers to electrified transportation have indicated a trend toward higher power, power density, modularity, and scalability of designs. In this article, commercial systems and laboratory prototypes are reviewed, focusing mostly on the advances in high-power wireless charging systems. The recent endeavors in magnetic pad designs, compensation networks, power electronics converters, control strategies, and communication protocols are illustrated. Both stationary and dynamic (in-motion) wireless charging systems are discussed, and critical differences in their designs and applications are emphasized. On that basis, the comparisons among different solutions and design considerations are summarized to present the essential elements and technology roadmap that will be necessary to support large-scale deployment of high-power wireless charging systems. The review is concluded with the discussion of several fundamental challenges and prospects of high-power wireless power transfer (WPT) systems. Foreseen challenges include utilization of advanced materials, electric and electromagnetic field measurement and mitigation, customization, communications, power metering, and cybersecurity.

25 ENERGY STORAGE↗

Baseflow Identification via Explainable AI With Kolmogorov‐Arnold Networks

Abstract Hydrological models often involve constitutive laws that may not be optimal in every application. We propose to replace such laws with the Kolmogorov‐Arnold networks (KANs), a class of neural networks designed to identify symbolic expressions. We demonstrate KAN's potential on the problem of baseflow identification, a notoriously challenging task plagued by significant uncertainty. KAN‐derived functional dependencies of the baseflow components on the aridity index outperform their original counterparts; they demonstrate that water availability, rather than potential evapotranspiration, drives baseflow by constraining actual evapotranspiration under arid conditions. On a test set, they increase the Nash‐Sutcliffe efficiency (NSE) by 65%, decrease the root mean squared error by 29%, and increase the Kling‐Gupta efficiency by 34%. This superior performance is achieved while reducing the number of fitting parameters from three to two. Next, we use data from 378 catchments across the continental United States to refine the water‐balance equation at the mean‐annual scale. The KAN‐derived equations based on the refined water balance outperform both the current aridity index model, with up to a 105% increase in NSE, and the KAN‐derived equations based on the original water balance. While the performance of our model and tree‐based machine learning methods is similar, KANs offer the advantage of simplicity and transparency and require no specific software or computational tools. This case study focuses on the aridity index formulation, but the approach is flexible and transferable to other hydrological processes. Plain Language Summary Equations used in hydrologic model are often suboptimal, resulting in reduced prediction accuracy and efficiency. We implemented Kolmogorov‐Arnold networks (KAN), a machine learning algorithm for deriving symbolic formulations, to estimate groundwater recharge and showed that it outperforms an existing state‐of‐the‐art semi‐empirical formulation. In hydrology, Nash‐Sutcliffe efficiency (NSE), root mean squared error (RMSE), and Kling‐Gupta efficiency (KGE) are commonly used to evaluate model performance. Higher NSE and KGE values indicate better performance, while lower RMSE values are preferable. Our results show that NSE increased by 71%, RMSE decreased by 32%, and KGE improved by 25%. In addition, KAN identifies an optimal functional form and can be used to derive new analytical formulas using the prior knowledge. The KAN‐inspired equation outperformed the original formulation and reduced the fitting parameters. Furthermore, we refined the water‐balance equation at the mean‐annual scale and showed that, based on the new water‐balance equation, KAN can derive new formulations that are superior to the original aridity index formulations (up to 105% increase in NSE) and KAN‐derived equations based on the original water balance. These findings highlight the significant potential of KAN to advance the scientific understanding of a wide range of hydrologic processes. Key Points Kolmogorov‐Arnold networks (KANs) enhance interpretability of machine‐learned hydrological models KAN‐derived symbolic formulations outperform state‐of‐the‐art semi‐empirical aridity indices KAN‐identified functional form yields an analytical index with fewer fitting parameters and improved performance

baseflow↗

National Solar Jobs Accelerator (Final Technical Report (FTR))

The aptitudes and experiences gained through military service—such as dynamic leadership, teamwork and critical thinking skills, technical specialization, and a mission-completion work ethic—make veterans exceptional candidates for a wide range of solar energy careers. The solar industry offers a highly collaborative and purpose-driven work environment that resonates with service members and veterans looking to rise to their next challenge, and solar employers are eager to tap into this valuable talent pool. From October 2019 - February 2023, The National Solar Jobs Accelerator (publicly the Solar Ready Vets Network TM (SRV Network; SRVN)) enhanced and streamlined options for military service members and veterans to pursue solar training, certification, and employment, while advancing solar employers’ efforts and capacity to invest in military talent as part of a long-term workforce development strategy. The SRVN was led by the Interstate Renewable Energy Council (IREC) in partnership with the Solar Energy Industries Association (SEIA), the US Chamber of Commerce Foundation’s Hiring Our Heroes program (HOH) and the North American Board of Certified Energy Practitioners (NABCEP). Through several direct-impact and indirect, high-impact capacity building initiatives aligned with six key objectives, the SRV Network strengthened solar career pathways, and promoted increased representation of military talent across all levels and sectors of the solar workforce. A work-based learning Corporate Fellowship model connected transitioning service members with on-the-job experience in leadership roles with solar employers nationwide. The project advanced broader veteran recruitment and talent development by expanding GI Bill eligibility and streamlining veterans’ pathways for solar training and credentialing, supported direct connections to jobs with top solar employers, and led coordination among key education and industry partners to advance registered apprenticeships aligned with solar career pathways. To ensure that the project best served the needs of all stakeholders, an Advisory Committee of military-connected solar professionals, solar employers, and training providers met biannually to guide project activities and sustainability plans. The project team engaged the broader “SRV Network” (comprised of over 2,000 veterans, employers and training organizations) through regular newsletters and targeted outreach to share resources, hiring fairs, webinars, and other opportunities for engagement. The work done under this award builds on the previous iterations of the Department of Energy’s Solar Ready Vets ® program. As the solar industry continues to grow rapidly over the next decade, the military community will continue to be a highly valuable source of talent. The relationships established and work accomplished through this project will have an enduring positive impact well beyond the funding period.

14 SOLAR ENERGY↗

Advanced Reconfiguration and Protection of Distribution Systems: Four Areas of Supporting Research

Historically, distribution systems have been very susceptible to transmission- and distribution-level events, such as line trips and faults within substations, because local sources of energy, if available at all, were only designed to operate in the context of a fully functional grid. However, the increasing deployment of advanced measuring devices, distributed energy resources (DERs), and energy storage provide the opportunity to improve reliability at the distribution level using advanced measurement-based reconfiguration and protection methods. This report discusses research regarding 1) a transmission equivalent model, 2) an algorithm for distinguishing between transmission- and distribution-level events, 3) a spreadsheet to help site new measurement devices, and 4) network theory to enable smart reconfiguration of distribution systems. Each of these areas of research support the development and study of advanced reconfiguration and protection methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Final Technical Report: Commercial Advanced Lighting Control (ALC) Demonstration and Deployment

This three-year demonstration and deployment project sought to address market barriers to accelerating the adoption of Advanced Lighting Controls (ALCs), an underutilized technology with low market penetration. ALCs are defined as networked, addressable lighting control systems that utilize software or intelligent controllers to combine multiple energy-saving lighting control strategies in a single space (e.g., smart-time scheduling, daylight harvesting, task tuning, occupancy control, personal control, variable load-shedding, and plug-load control). The networked intelligent aspect of these systems allows applicable lighting control strategies to be combined in a single space, layered over one another, maximizing overall energy-savings. The project included five real building demonstrations of ALCs across the Northeast US region. The demonstrations provided valuable data and experience to support deployment tasks that are necessary to overcome market barriers. These deployment tasks included development of training resources for building designers, installers, and trades, as well as development of new energy efficiency rebates for the technology from Efficiency Forward’s utility partners. Educating designers, installers, and trades on ALCs is a critical task for reducing the cost of the technology that is currently inflated due to perceived complexity and unfamiliarity with how to design and install the systems. Further, utility and non-utility energy efficiency programs continue to relegate the technology to custom or ill-suited prescriptive program designs that do not effectively deploy the technology at scale. This project developed new, scalable rebate approaches for the technology. Efficiency Forward utilized their DesignLights Consortium® (DLC) brand and network of 81 DLC member utilities to develop and deploy the results of the project. The outputs of the project have included five published case studies, a six-hour ALC technology training curriculum that has already been deployed in five US states, and new rebates offered for the technology that have been deployed by a dozen utilities across the US. Widespread adoption of ALC technology in commercial buildings would provide tremendous benefits. The current market penetration of ALC systems is estimated at <0.1% in commercial buildings. If ALC systems were installed in all commercial buildings, approximately 1,051 TBtu of energy could be saved. This would translate into customer cost savings of approximately $10.7 billion annually.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Soft network composite materials with deterministic and bio-inspired designs

Hard and soft structural composites found in biology provide inspiration for the design of advanced synthetic materials. Many examples of bio-inspired hard materials can be found in the literature; far less attention has been devoted to soft systems. Here we introduce deterministic routes to low-modulus thin film materials with stress/strain responses that can be tailored precisely to match the non-linear properties of biological tissues, with application opportunities that range from soft biomedical devices to constructs for tissue engineering. The approach combines a low-modulus matrix with an open, stretchable network as a structural reinforcement that can yield classes of composites with a wide range of desired mechanical responses, including anisotropic, spatially heterogeneous, hierarchical and self-similar designs. Demonstrative application examples in thin, skin-mounted electrophysiological sensors with mechanics precisely matched to the human epidermis and in soft, hydrogel-based vehicles for triggered drug release suggest their broad potential uses in biomedical devices.

36 MATERIALS SCIENCE↗

Deep learning with mixup augmentation for improved pore detection during additive manufacturing

In additive manufacturing (AM), process defects such as keyhole pores are difficult to anticipate, affecting the quality and integrity of the AM-produced materials. Hence, considerable efforts have aimed to predict these process defects by training machine learning (ML) models using passive measurements such as acoustic emissions. This work considered a dataset in which keyhole pores of a laser powder bed fusion (LPBF) experiment were identified using X-ray radiography and then registered both in space and time to acoustic measurements recorded during the LPBF experiment. Due to AM’s intrinsic process controls, where a pore-forming event is relatively rare, the acoustic datasets collected during monitoring include more non-pores than pores. In other words, the dataset for ML model development is imbalanced. Moreover, this imbalanced and sparse data phenomenon remains ubiquitous across many AM monitoring schemes since training data is nontrivial to collect. Hence, we propose a machine learning approach to improve this dataset imbalance and enhance the prediction accuracy of pore-labeled data. Specifically, we investigate how data augmentation helps predict pores and non-pores better. This imbalance is improved using recent advances in data augmentation called Mixup, a weak-supervised learning method. Convolutional neural networks (CNNs) are trained on original and augmented datasets, and an appreciable increase in performance is reported when testing on five different experimental trials. When ML models are trained on original and augmented datasets, they achieve an accuracy of 95% and 99% on test datasets, respectively. We also provide information on how dataset size affects model performance. Lastly, we investigate the optimal Mixup parameters for augmentation in the context of CNN performance.

36 MATERIALS SCIENCE↗

A three-dimensional self-assembled SnS 2 -nano-dots@graphene hybrid aerogel as an efficient polysulfide reservoir for high-performance lithium–sulfur batteries

Reliable sulfur cathodes hold the key to realizing high-performance lithium–sulfur (Li–S) batteries, yet the electrochemical inefficiency and instability arising from the poor conductivity of sulfur and lithium sulfide together with polysulfide diffusion present challenges. We present here a new three-dimensional graphene aerogel embedded with in situ grown SnS 2 nano-dots (SnS 2 -ND@G) as an efficient sulfur host. First, benefiting from a highly conductive, hierarchically porous, and mechanically self-supported architecture, the SnS 2 -ND@G aerogel enables the cathode to hold high sulfur content (75 wt%) and loading (up to 10 mg cm –2 ). Both values exceed most of the reported metal-compound-related cathode work (<60 wt% sulfur content and <3 mg cm –2 sulfur loading) in the literature. Second, this work takes advantage of a facile one-pot self-assembly fabrication, effectively guaranteeing a homogeneous deposition of SnS 2 nano-dots in the graphene aerogel with a small amount of SnS 2 (16 wt%). It greatly overcomes the shortcomings of physical incorporation methods to make metal-compound/carbon substrates reported in previous studies. More importantly, by rationally combining the physical entrapment from graphene and chemical adsorptivity from SnS 2 nano-dots towards polysulfides, the SnS 2 -ND@G aerogel demonstrates remarkably improved polysulfide-trapping capability and electrochemical stability. As a result, a high peak capacity of 1234 mA h g –1 , a high reversible capacity of 1016 mA h g –1 after 300 cycles, exceptional rate capability (C/10 – 3C rates), and impressive areal capacity (up to 11 mA h cm –2 ) are achieved. Furthermore, this work provides a viable path to integrate a conductive graphene network and nano-sized SnS 2 as a promising cathode substrate for developing advanced Li–S batteries.

25 ENERGY STORAGE↗

DCTRGAN: improving the precision of generative models with reweighting

Significant advances in deep learning have led to more widely used and precise neural network-based generative models such as Generative Adversarial Networks (Gans). We introduce a post-hoc correction to deep generative models to further improve their fidelity, based on the Deep neural networks using the Classification for Tuning and Reweighting (Dctr) protocol. The correction takes the form of a reweighting function that can be applied to generated examples when making predictions from the simulation. We illustrate this approach using Gans trained on standard multimodal probability densities as well as calorimeter simulations from high energy physics. We show that the weighted Gan examples significantly improve the accuracy of the generated samples without a large loss in statistical power. This approach could be applied to any generative model and is a promising refinement method for high energy physics applications and beyond.

47 OTHER INSTRUMENTATION↗

Distributed Small-Signal Stability Conditions for Inverter-Based Unbalanced Microgrids

The proliferation of inverter-based generation and advanced sensing, controls, and communication infrastructure have facilitated accelerated deployment of microgrids. A coordinated network of microgrids can maintain reliable power delivery to critical facilities during extreme events. Low-inertia offered by the power-electronics–interfaced energy resources, however, can present significant challenges to ensuring stable operation of the microgrids. In this work, distributed small-signal stability conditions for inverter-based microgrids are developed that involve the droop-controller parameters and the network parameters (e.g. line impedances, loads). The distributed closed-form parametric stability conditions derived in this paper can be verified in a computationally efficient manner, facilitating reliable design and operations of networks of microgrids. Dynamic phasor models have been used to capture the effects of electromagnetic transients. Furthermore, numerical results are presented, along with PSCAD simulations, to validate the analytical stability conditions. Effects of design choices, such as the conductor types, and inverter sizes, on the small-signal stability of inverter-based microgrids are investigated to derive useful engineering insights.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Uncertainty-Informed Volume Visualization using Implicit Neural Representation

The increasing adoption of Deep Neural Networks (DNNs) has led to their application in many challenging scientific visualization tasks. While advanced DNNs offer impressive generalization capabilities, understanding factors such as model prediction quality, robustness, and uncertainty is crucial. These insights can enable domain scientists to make informed decisions about their data. However, DNNs inherently lack ability to estimate prediction uncertainty, necessitating new research to construct robust uncertainty-aware visualization techniques tailored for various visualization tasks. In this work, we propose uncertainty-aware implicit neural representations to model scalar field data sets effectively and comprehensively study the efficacy and benefits of estimated uncertainty information for volume visualization tasks. We evaluate the effectiveness of two principled deep uncertainty estimation techniques: (1) Deep Ensemble and (2) Monte Carlo Dropout (MC-Dropout). These techniques enable uncertainty-informed volume visualization in scalar field data sets. Our extensive exploration across multiple data sets demonstrates that uncertainty-aware models produce informative volume visualization results. Moreover, integrating prediction uncertainty enhances the trustworthiness of our DNN model, making it suitable for robustly analyzing and visualizing real-world scientific volumetric data sets.

Saklani, Shanu↗

Redox transistors for neuromorphic computing

Efficiency bottlenecks inherent to conventional computing in executing neural algorithms have spurred the development of novel devices capable of “in-memory” computing. Commonly known as “memristors,” a variety of device concepts including conducting bridge, vacancy filament, phase change, and other types have been proposed as promising elements in artificial neural networks for executing inference and learning algorithms. In this article, we review the recent advances in memristor technology for neuromorphic computing and discuss strategies for addressing the most significant performance challenges, including nonlinearity, high read/write currents, and endurance. As an alternative to two-terminal memristors, we introduce the three-terminal electrochemical memory based on the redox transistor (RT), which uses a gate to tune the redox state of the channel. Decoupling the “read” and “write” operations using a third terminal and storage of information as a charge-compensated redox reaction in the bulk of the transistor enables high-density information storage. These properties enable low-energy operation without compromising analog performance and nonvolatility. Finally, we discuss the RT operating mechanisms using organic and inorganic materials, approaches for array integration, and prospects for achieving the device density and switching speeds necessary to make electrochemical memory competitive with established digital technology.

97 MATHEMATICS AND COMPUTING↗

Nanoparticle self-assemblies with modern complexity

Thanks to decades of tireless efforts, nanoparticle assemblies have reached at an extremely high level of controllability, sophistication, and complexity, with new insights provided by integration with graph theory, cutting-edge characterization, and machine learning (ML)-based computation and modeling, as well as with ever-diversifying applications in energy, catalysis, biomedicine, optics, electronics, magnetics, organic biosynthesis, and quantum technology. Nanoparticle assemblies can be crystalline, known as superlattices or supracrystals. Their assembly entails a transition from disorder—dispersed nanoparticles—to order, which can be achieved through classical nucleation pathways or nonclassical pathways via prenucleation precursors or particle aggregation. Further, the periodic lattices allow facile manipulations of electrons, phonons, photons, and even spins, leading to advanced device components and metamaterials. Meanwhile, aperiodic assemblies out of nanoparticles, such as gels, networks, and amorphous solids, also start to attract attentions. Despite the loss of periodicity, symmetry-lowering or symmetry-breaking three-dimensional (3D) structures emerge with unique properties, such as chiroptical activity, topological mechanical strength, and quantum entanglement. Real-space imaging such as electron microscopy and X-ray based tomography methods are utilized to characterize these complex structures, while mathematical tools such as graph theories are in need to describe such complex structures. This issue aims to provide a timely review of the efforts in this greatly broadened materials design space including experiment, simulation, theory, and applications. Nine top experts (and their teams) from four countries deliver six review papers, summarizing fundamental mechanistic understandings of nanoparticle assemblies, highlighted with the developments of state-of-the-art in situ characterization tools and ML-assisted reverse engineering, and newly emergent applications of nanoarchitectures.

36 MATERIALS SCIENCE↗

Scalable fault tolerance runtime technology for petascale computers (Final Project Report)

With the massive number of components comprising the forthcoming petascale computer systems, hardware failures will be routinely encountered during execution of large-scale applications. Due to the multidisciplinary, multiresolution, and multiscale nature of scientific problems that drive the demand for high end systems, applications place increasingly differing demands on the system resources: disk, network, memory, and CPU. In addition to MPI, future applications are expected to use advanced programming models such as those developed under the DARPA HPCS program as well as existing global address space programming models such as Global Arrays, UPC, and Co-Array Fortran. While there has been a considerable amount of work in fault tolerant MPI with a number of strategies and extensions for fault tolerance proposed, virtually none of advanced models proposed for emerging petascale systems is currently fault aware. To achieve fault tolerance, development of underlying runtime and OS technologies able to scale to petascale level is needed. This project has evaluated range of runtime techniques for fault tolerance for advanced programming models.

97 MATHEMATICS AND COMPUTING↗

Lighting Technology Energy Solutions (LiTES) (Final Technical Report)

The Lighting Technologies Energy Solutions (LiTES) Program Final Technical Report is a collaborative effort between NextEnergy, Consumers Energy, DTE Energy (DTE) and the Detroit Joint Apprentice Training Center (DJATC) to evaluate customer and contractor experiences deploying advanced/networked lighting controls systems (ALC/NLC). The LiTES Program, funded by the US Department of Energy (DOE), sought to reduce energy use in small and medium commercial buildings (SMCB) by accelerating the adoption of ALC/NLC through contractor training and technology deployment. Leveraging recommendations already outlined by the Design Lights Consortium Commercial Advanced Lighting Controls (DLC CALC) project, NextEnergy led an effort to train contractors, evaluate the experience of ALC/NLC demonstration projects, identify opportunities to reduce market barriers, and accelerate the increased adoption of ALC/NLC technologies within SMCB. The LiTES Program defined SMCB as commercial buildings under 100,000 square feet. The LiTES Program efforts also included evaluating current ALC/NLC utility incentives, piloting ALC/NLC incentives specific to SMCB, and identifying opportunities to better align utility incentives with current ALC/NLC technology to support accelerating the adoption of ALC/NLC in SMCB. This report shares the survey results and M&V data findings, including energy savings, market barriers, experience of installations, impact of incentives/financing programs and provides recommendations for the increased deployment of ALC/NLC systems in small and medium commercial buildings. Utility survey results, incentive alternatives and recommendations, including a cost benefit analysis outlining energy and economic impacts of the provided ALC/NLC incentives on SMCB projects are also provided.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Project Title: Adaptive Vertical Grid Enhancement for E3SM (Final Technical Report)

During the first phase of the project (2018/05-2021/05), we proved the hypothesis that, without tuning, high vertical resolution improves the representation of unresolved, parameterized low altitude clouds such as stratocumulus clouds in global climate models. We evaluated the effectiveness of the newly developed computational framework, Framework for Improvement by Vertical Enhancement (FIVE) by implementing it into E3SM. FIVE aims to improve representation of the target cloud, low level cloud for this project, with use of a locally high vertical resolution for computation of selected processes. FIVE was assessed via direct comparison among E3SM, E3SM-FIVE, and satellite data as well as a newly developed ensemble artificial neural network methodology. We demonstrated that E3SM-FIVE remarkably improves marine stratocumulus representation. To advance the FIVE methodology, we took a first step toward the adaptive vertical grid in the FIVE method by modifying the E3SM single column model. For future application of FIVE to the global storm resolving model with a few km horizontal grid resolution, we developed the vertical-meridional two-dimensional (2D) Hadley circulation model, which allows one to run simulations with much higher vertical resolution and significantly longer duration than current three-dimensional global storm resolving model. During the second phase of the project (2021/05-2023/11; period for this technical report), we sought a way to appropriately transform FIVE to a regionalized version of FIVE, which allows one to select locations with/without FIVE. In parallel, we demonstrated that E3SM-FIVE with a 25-km mesh significantly reduced the bias associated with coastal stratocumulus. Furthermore, we showed that the same improvement was able to be obtained with the use of both the Regional Refined Model (RRM) targeted to one of the stratocumulus regions with 25-km resolution and FIVE. We explored a new implementation strategy of FIVE with our 2D Hadley circulation model. In parallel we applied the 2D Hadley circulation model to study the double intertropical convergence zone bias with storm resolving model resolution and aerosol-cloud interactions within the Hadley circulation with near large eddy simulation resolution. Last, we have been investigating Arctic mixed-phase stratocumulus clouds with large eddy simulations in order to improve their representation in global models. During the course of the entire project, 6 journal articles were published, and 3 manuscripts are currently in preparation. We gave a total of 30 presentations at various domestic and international conferences. In addition we gave 6 seminar talks at universities and a national laboratory. E3SM- FIVE is available as a branch of E3SM.

54 ENVIRONMENTAL SCIENCES↗

Deep learning with mixup augmentation for improved pore detection during additive manufacturing

In additive manufacturing (AM), process defects such as keyhole pores are difficult to anticipate, affecting the quality and integrity of the AM-produced materials. Hence, considerable efforts have aimed to predict these process defects by training machine learning (ML) models using passive measurements such as acoustic emissions. This work considered a dataset in which keyhole pores of a laser powder bed fusion (LPBF) experiment were identified using X-ray radiography and then registered both in space and time to acoustic measurements recorded during the LPBF experiment. Due to AM’s intrinsic process controls, where a pore-forming event is relatively rare, the acoustic datasets collected during monitoring include more non-pores than pores. In other words, the dataset for ML model development is imbalanced. Moreover, this imbalanced and sparse data phenomenon remains ubiquitous across many AM monitoring schemes since training data is nontrivial to collect. Hence, we propose a machine learning approach to improve this dataset imbalance and enhance the prediction accuracy of pore-labeled data. Specifically, we investigate how data augmentation helps predict pores and non-pores better. This imbalance is improved using recent advances in data augmentation called Mixup, a weak-supervised learning method. Convolutional neural networks (CNNs) are trained on original and augmented datasets, and an appreciable increase in performance is reported when testing on five different experimental trials. When ML models are trained on original and augmented datasets, they achieve an accuracy of 95% and 99% on test datasets, respectively. We also provide information on how dataset size affects model performance. Lastly, we investigate the optimal Mixup parameters for augmentation in the context of CNN performance.

42 ENGINEERING↗