Search NASA⌕ Search

SEARCH · Search NASA

Results for “Performance Model”

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 433 records · Page 24

LULESH Programming Model and Performance Ports Overview

This document gives a description of various versions of the LULESH proxy application described in [1]. All the the codes described in this document are available at https://codesign.llnl. gov/lulesh.php. This report describes versions that fall into three categories: performance tuning exploration, programming model exploration and other versions. In this document we focus on giving a brief overview of what makes each version different from the others. The purpose is to allow others to reuse our work as a starting point for their exploration. Therefore, references to publications and presentations are provided to allow those who want more detailed information to be able to find it.

97 MATHEMATICS AND COMPUTING↗

Evaluating mesoscale model predictions of diurnal speedup events in the Altamont Pass Wind Resource Area of California

Mesoscale model predictions of wind, turbulence, and wind energy capacity factors are evaluated in the Altamont Pass Wind Resource Area of California (APWRA), where the diurnal regional sea breeze and associated terrain-driven speedup flows drive wind energy production during the summer months. Results from the Weather Research and Forecasting model version 4.4 using a novel three-dimensional planetary boundary layer (3D PBL) scheme, which treats both vertical and horizontal turbulent mixing, are compared to those using a well-established one-dimensional (1D) scheme that treats only vertical turbulent mixing. Each configuration is evaluated over a nearly 3-month-long period during the Hill Flow Study, and due to the recurring nature of the observed speedup flows, diurnal composite averaging is used to capture robust trends in model performance. Both model configurations showed similar overall skill. The general timing and direction of the speedup flows is captured, but their magnitude is overestimated within a typical wind turbine rotor layer. Both also fail to capture a persistent observed near-surface jet-like flow, likely due to the limited grid resolution that is typical of mesoscale models. However, the 3D PBL configuration shows several minor improvements over the 1D PBL configuration, including improved wind speed and turbulence kinetic energy profiles during the accelerating phase of the speedup events, as well as reduced positive wind speed bias at surface stations across the APWRA region. Using a mesoscale wind farm parameterization, modeled capacity factors are also compared to monthly data reported to the US Energy Information Administration (EIA) during the study period. Although the monthly trend in the data is captured, both model configurations overestimate capacity factors by roughly 7 %–11 %. Through model evaluation, this study provides confidence in the 3D PBL scheme for wind energy applications in complex terrain and provides guidance for future testing.

17 WIND ENERGY↗

A CONDUCTION-BASED HEAT PIPE MODEL FOR ANALYZING THE ENTIRE PROCESS OF LIQUID-METAL HEAT PIPE STARTUP

The Heat Pipe-cooled Microreactor (HPM) is one of the micro nuclear reactor designs under active study at the U.S. Idaho National Laboratory. Among the major concerns of HPM research is to understand the startup behavior of the heat pipe-cooled system associated with the startup of the liquid-metal heat pipes initialing from frozen state. The startup of liquid-metal heat pipes typically involves a number of nonlinear mass and heat transport processes including the phase change from solid to liquid and vapor. Hence, it is still a huge challenge to simulate the liquid-metal heat pipe startup using conventional CFD methods and software. The major difficulties of numerical CFD modeling come from the phase-change process, multiphase interaction, microporous wick flow, and compressible gas dynamics that occur during startup of the liquid-metal heat pipes. This paper proposes a simplified conduction-based method to provide practical insights into the entire startup process of the liquid-metal heat pipes while mitigating the challenges of addressing all the complex physics. We discuss the theoretical basis and modeling assumptions to analyze the liquid-metal heat pipe startup from frozen state based solely on heat-conduction equations. Then, the proposed model is implemented into the commercial CFD software to verify the model performance. The model prediction results are discussed via the comparison with the experimental data obtained from sodium heat-pipe startup experiments.

42 ENGINEERING↗

High-fidelity multiphysics load following and accidental transient modeling of microreactors using NEAMS tools: Application of NEAMS codes to perform multiphysics modeling analyses of micro-reactor concepts

The feasibility of modeling microreactors using high-fidelity models with the Nuclear Energy Advanced Modeling and Simulation (NEAMS) tools is investigated in this report. Three overarching questions guided this research: can NEAMS tools readily be applied for high-fidelity multiphysics modeling of different types of transients in microreactor designs; how accurate are the results obtained; and are improvements needed in accuracy or user experience of NEAMS tools, especially considering newly developed capabilities? This work builds upon FY-2022 work, and two microreactor concepts considering heat pipe (HP-MR) and gas-cooled (GC-MR) technologies were further analyzed using high-fidelity multiphysics simulations. The NEAMS tools considered and coupled within the MultiApp environment are Griffin for neutronics, BISON for thermo-mechanics, Sockeye for heat pipe modeling (in HP-MR), SAM for 1D Fluid – 3D solid modeling of coolant channels and system modeling of balance of plant components (in GC-MR), and the SWIFT code for hydrogen redistribution in hydride moderator. The Heat Pipe MicroReactor (HP-MR) concept was further analyzed in FY-2023 to demonstrate the stochastic TRISO failure modeling capability in BISON to check operational limits of the TRISO fuel. A new full-core Gas-Cooled MicroReactor (GC-MR) model was developed based on the initial assembly-model used in Y-2022 and used for steady-state and accidental depressurization transient simulations. Accuracy of the simulations performed was assessed through 1) verification analyses completed on the different physics with code-to-code comparison, and 2) validation of the multiphysics simulations based on modeling of the Kilopower Reactor Using Stirling Technology (KRUSTY) experiment. In FY-2023, the mesh and model of KRUSTY was updated to closely match publicly available data, and the neutronic model was verified and validated against experimental control rod worth measurements. The multiphysics model of KRUSTY was developed and used for steady-state analysis and for modeling reactivity insertion transient. The calculated power increase and stabilization agrees well with experimental data following adjustment in fuel thermal expansion coefficient. As an important component of this project, the ANL team gathered experience with a wide range of NEAMS tools: the MOOSE Mesh System, Griffin, BISON, SWIFT, Sockeye, SAM, Workbench, and the MOOSE MultiApp System, and provided assessment of new capabilities. Noteworthy are the user assessment of the “vapor-only” flow model in Sockeye and development of a multiphysics startup transient in HP-MR unit cell for use as tutorial in Sockeye. The full-core GC-MR model was used for assessment of SAM for balance of plant modeling and for demonstrating the SWIFT code capability for hydrogen redistribution modeling in multiphysics transient analyses. In this process, several bugs/issues were identified and reported to developers. Finally, the assembly GC-MR model developed in FY-2022 coupling Griffin, BISON and SAM through flow blockage and rod ejection transients was published to the National Reactor Innovation Center (NRIC) Virtual Test Bed (VTB). The Heat Pipe MicroReactor (HP-MR) concept high-fidelity multiphysics coupling of Griffin/BISON/Sockeye in load-following and heat pipe failure transients was also published on the VTB. Those submissions are enabling thorough review of these models as well as wide distribution to industry, regulator, and university users. In this analysis, several new research questions were uncovered, and follow-up analyses are recommended to further improve some models, consider additional transients, and continue development of VTB models.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

The response of stomatal conductance to seasonal drought in tropical forests

Stomata regulate CO2 uptake for photosynthesis and water loss through transpiration. The approaches used to represent stomatal conductance (gs) in models vary. In particular, current understanding of drivers of the variation in a key parameter in those models, the slope parameter (i.e. a measure of intrinsic plant water-use-efficiency), is still limited, particularly in the tropics. Here we collected diurnal measurements of leaf gas exchange and water potential (?leaf), and a suite of plant traits from the upper canopy of 15 tropical trees in two contrasting Panamanian forests throughout the dry season of the 2016 El Niño. The plant traits included wood density, leaf-mass-per-area (LMA), leaf carboxylation capacity (Vc,max25), leaf water content, the degree of isohydry, and predawn ?leaf. We first investigated how the choice of four commonly used leaf-level gs models with and without the inclusion of ?leaf as an additional predictor variable influence the ability to predict gs, and then explored the abiotic (i.e. month, site-month interaction) and biotic (i.e. tree-species-specific characteristics) drivers of slope parameter variation. Our results show that the inclusion of ?leaf did not improve model performance and that the models that represent the response of gs to vapor pressure deficit performed better than corresponding models that respond to relative humidity. Within each gs model, we found large variation in the slope parameter, and this variation was attributable to the biotic driver, rather than abiotic drivers. We further investigated potential relationships between the slope parameter and the six available plant traits mentioned above, and found that only one trait, LMA, had a significant correlation with the slope parameter (R2=0.66, n=15), highlighting a potential path towards improved model parameterization. This study advances understanding of gs dynamics over seasonal drought, and identifies a practical, trait-based approach to improve modeling of carbon and water exchange in tropical forests.

carbon and water exchange, stomatal conductance mo↗

Automated Design Space Exploration with Aspen

Architects and applications scientists often use performance models to explore a multidimensional design space of architectural characteristics, algorithm designs, and application parameters. With traditional performance modeling tools, these explorations forced users to first develop a performance model and then repeatedly evaluate and analyze the model manually. These manual investigations proved laborious and error prone. More importantly, the complexity of this traditional process often forced users to simplify their investigations. To address this challenge of design space exploration, we extend our Aspen (Abstract Scalable Performance Engineering Notation) language with three new language constructs: user-defined resources, parameter ranges, and a collection of costs in the abstract machine model. Then, we use these constructs to enable automated design space exploration via a nonlinear optimization solver. We show how four interesting classes of design space exploration scenarios can be derived from Aspen models and formulated as pure nonlinear programs. The analysis tools are demonstrated using examples based on Aspen models for a three-dimensional Fast Fourier Transform, the CoMD molecular dynamics proxy application, and the DARPA Streaming Sensor Challenge Problem. Our results show that this approach can compose and solve arbitrary performance modeling questions quickly and rigorously when compared to the traditional manual approach.

Spafford, Kyle L.↗

Path-BigBird: An AI-Driven Transformer Approach to Classification of Cancer Pathology Reports

PURPOSE Surgical pathology reports are critical for cancer diagnosis and management. To accurately extract information about tumor characteristics from pathology reports in near real time, we explore the impact of using domain-specific transformer models that understand cancer pathology reports. METHODS We built a pathology transformer model, Path-BigBird, by using 2.7 million pathology reports from six SEER cancer registries. We then compare different variations of Path-BigBird with two less computationally intensive methods: Hierarchical Self-Attention Network (HiSAN) classification model and an offthe-shelf clinical transformer model (Clinical BigBird). We use five pathology information extraction tasks for evaluation: site, subsite, laterality, histology, and behavior. Model performance is evaluated by using macro and micro F 1 scores. RESULTS We found that Path-BigBird and Clinical BigBird outperformed the HiSAN in all tasks. Clinical BigBird performed better on the site and laterality tasks. Versions of the Path-BigBird model performed best on the two most difficult tasks: subsite (micro F 1 score of 72.53, macro F 1 score of 35.76) and histology (micro F 1 score of 80.96, macro F 1 score of 37.94). The largest performance gains over the HiSAN model were for histology, for which a Path-BigBird model increased the micro F 1 score by 1.44 points and the macro F 1 score by 3.55 points. Overall, the results suggest that a Path-BigBird model with a vocabulary derived from wellcurated and deidentified data is the best-performing model. CONCLUSION The Path-BigBird pathology transformer model improves automated information extraction from pathology reports. Although Path-BigBird outperforms Clinical BigBird and HiSAN, these less computationally expensive models still have utility when resources are constrained.

60 APPLIED LIFE SCIENCES↗

Machine Learning Accelerated First-Principles Study of the Hydrodeoxygenation of Propanoic Acid

The complex reaction network of catalytic biomass conversions often involves hundreds of surface intermediates and thousands of reaction steps, greatly hindering the rational design of metal catalysts for these conversions. Here, we present a framework of machine learning (ML)-accelerated first-principles studies for the hydrodeoxygenation (HDO) of propanoic acid over transition metal surfaces. The microkinetic model (MKM) is initially parametrized by ML-predicted energies and iteratively improved by identifying the rate-determining species and steps (RDS), computing their energies by density functional theory (DFT), and reparameterizing the MKM until all the RDS are computed by DFT. The Gaussian process (GP) model performs significantly better than the linear ridge regression model for predicting both the adsorption free energies and transition state free energies. Parameterized with energies from the GP model, only 5–20% of the full reaction network has to be computed by DFT for the MKM to possess DFT-level accuracy for the TOF and dominant reaction pathway. While the linear ridge regression model performs worse than the GP model, its performance is greatly improved when only transition states are predicted by the regression model and adsorption energies are computed by DFT. Overall, we find that a high accuracy in adsorption free energies is more important for a reliable MKM than a high accuracy in TS free energies. Lastly, based on the GP model with GOH and GCHCHCO as catalyst descriptors, we build two-dimensional volcano plots in activity and selectivity that can help design promising alloy catalysts for HDO reactions of organic acids.

adsorption↗

Integrated Disposal Facility Performance Assessment: Modeling Consistency to Support Regulatory Decision Making at Hanford - 17398

Under DOE Order 435.1, 'Radioactive Waste Management', Washington River Protection Solutions, LLC and INTERA, Inc are currently preparing a performance assessment for the Hanford Integrated Disposal Facility, a near-surface low-activity waste disposal facility located on the Hanford Site in southeast Washington State. The disposal facility is expected to receive vitrified low-activity waste produced at the Hanford Waste Treatment and Immobilization Plant, as well as other secondary solid wastes generated during the treatment process. The performance assessment performs the analyses that will be relied upon to receive the Disposal Authorization Statement, establish waste acceptance criteria, modify the RCRA permit for the facility and make a waste-incidental-to-reprocessing determination for the vitrified tank waste. In January 2006 in the case State of Washington v. Bodman (Civil No. 2:03-cv-05018-AAM), DOE, the Washington State Department of Ecology (Ecology) and the State of Washington Attorney General's office reached a settlement agreement in Ecology's claim regarding off-site waste shipments to Hanford and the adequacy of modeling in the environmental impact statement. In response to the agreement, the DOE Office of Environmental Management set a policy to establish a consistent use of commercially available and public domain software for a vadose zone and groundwater model platform to support regulatory decisions at Hanford. In October 2012, the Associate Principal Deputy Assistant Secretary for Environmental Management released a memorandum to the manager of the Richland Operation Office directing how future environmental modeling activities to support regulatory decision making on the Hanford Site would be undertaken to be consistent with the 2006 settlement agreement. The preparation of the performance assessment must meet DOE Order 435.1 requirements and the additional direction provided by DOE. This paper will identify the approach taken to comply with the requirements in the 2012 memorandum. The paper will describe how environmental modeling performed for the 2017 Integrated Disposal Facility Performance Assessment was planned in a phased approach and how the current modeling is tied to the analyses that supported the decisions made in the environmental impact statement published in 2012. Additionally, the selection and qualification of the software selected to perform modeling activities for the performance assessment will be described. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Laying a Foundation for Performance Assessment (PA) Model Development - 19267

Performance Assessment (PA) models are abstractions of real-world conditions. As abstractions, modelers must make a number of decisions regarding model complexity and which features, events, and processes (FEPs) will be represented. To ensure that such decisions are transparent to stakeholders, modelers should document their approach and how this approach influences conceptual model development. This paper describes one such approach. Examples are used to describe an analysis of the potential FEPs. Through the FEPs analysis, all potentially relevant FEPs can be identified. These potentially relevant FEPs are then used to develop a detailed conceptual model known as the Central Scenario, which includes a description of the assessment context, the key features of the site and the closure system, and the expected processes of the system. From this Central Scenario conceptual model, mathematical models can be developed and implemented within modeling software and used to demonstrate compliance to PA performance objectives. FEPs which are beyond the scope of the Central Scenario are identified and used as the basis for developing alternative conceptual models (ACMs) or sensitivity analyses. Once these models and modeling cases are defined, the necessary inputs can be identified and defined. (author)

97 MATHEMATICS AND COMPUTING↗

Profiling the BLAST bioinformatics application for load balancing on high-performance computing clusters

Abstract Background The Basic Local Alignment Search Tool (BLAST) is a suite of commonly used algorithms for identifying matches between biological sequences. The user supplies a database file and query file of sequences for BLAST to find identical sequences between the two. The typical millions of database and query sequences make BLAST computationally challenging but also well suited for parallelization on high-performance computing clusters. The efficacy of parallelization depends on the data partitioning, where the optimal data partitioning relies on an accurate performance model. In previous studies, a BLAST job was sped up by 27 times by partitioning the database and query among thousands of processor nodes. However, the optimality of the partitioning method was not studied. Unlike BLAST performance models proposed in the literature that usually have problem size and hardware configuration as the only variables, the execution time of a BLAST job is a function of database size, query size, and hardware capability. In this work, the nucleotide BLAST application BLASTN was profiled using three methods: shell-level profiling with the Unix “time” command, code-level profiling with the built-in “profiler” module, and system-level profiling with the Unix “gprof” program. The runtimes were measured for six node types, using six different database files and 15 query files, on a heterogeneous HPC cluster with 500+ nodes. The empirical measurement data were fitted with quadratic functions to develop performance models that were used to guide the data parallelization for BLASTN jobs. Results Profiling results showed that BLASTN contains more than 34,500 different functions, but a single function, RunMTBySplitDB, takes 99.12% of the total runtime. Among its 53 child functions, five core functions were identified to make up 92.12% of the overall BLASTN runtime. Based on the performance models, static load balancing algorithms can be applied to the BLASTN input data to minimize the runtime of the longest job on an HPC cluster. Four test cases being run on homogeneous and heterogeneous clusters were tested. Experiment results showed that the runtime can be reduced by 81% on a homogeneous cluster and by 20% on a heterogeneous cluster by re-distributing the workload. Discussion Optimal data partitioning can improve BLASTN’s overall runtime 5.4-fold in comparison with dividing the database and query into the same number of fragments. The proposed methodology can be used in the other applications in the BLAST+ suite or any other application as long as source code is available.

59 BASIC BIOLOGICAL SCIENCES↗

Better practices for inferring ecosystem water use strategy from eddy covariance data

Eddy covariance data are critical for inferring ecosystem water use strategies. Yet, such inferences are sensitive to a range of assumptions applied across studies, hindering our understanding of water use strategies within and across eddy covariance sites. A recent analysis across 151 FLUXNET2015 and AmeriFlux-FLUXNET datasets found that poor model performance was the key driver of non-robust inferences of ecosystem water use strategies. Here, we leverage this previous analysis to (i) identify the specific assumptions that improve inference model performance across most sites, (ii) explain the mechanisms behind the performance improvements, and (iii) check whether better performance improves water use inference. We find that the common practice of fitting a model to canopy conductance (G c ) derived from the evapotranspiration (ET) observations, rather than to observed ET itself, artificially amplifies data errors and degrades the model performance. Next, accounting for vegetation dynamics by applying a growing season filter or incorporating satellite LAI data improves performance, but the former practice may remove soil water stress periods. Lastly, using the leaf-to-air vapor pressure deficit (VPD l ) derived from ET observations as a model input may artificially inflate performance. Based on these results, we recommend selecting observed ET (rather than derived G c ) as the response variable, carefully accounting for vegetation dynamics, and avoiding derived VPD l as a model input; these best practices improve model performance by c. 20% and robustness by c. 80% across all eddy covariance sites. Nevertheless, the performance improvements do not always correspond to more robust inference of water use strategies, as model parameter selection and surface energy budget closure corrections still strongly influence the ecosystem water use parameter estimation in a site-specific manner.

AmeriFlux↗

Comparing quantile regression forest and mixture density long short-term memory models for probabilistic post-processing of satellite precipitation-driven streamflow simulations

Abstract. Deep learning (DL) and machine learning (ML) are widely used in hydrological modelling, which plays a critical role in improving the accuracy of hydrological predictions. However, the trade-off between model performance and computational cost has always been a challenge for hydrologists when selecting a suitable model, particularly for probabilistic post-processing with large ensemble members. This study aims to systematically compare the quantile regression forest (QRF) model and countable mixtures of asymmetric Laplacians long short-term memory (CMAL-LSTM) model as hydrological probabilistic post-processors. Specifically, we evaluate their ability in dealing with biased streamflow simulations driven by three satellite precipitation products across 522 nested sub-basins of the Yalong River basin in China. Model performance is comprehensively assessed using a series of scoring metrics from both probabilistic and deterministic perspectives. Our results show that the QRF model and the CMAL-LSTM model are comparable in terms of probabilistic prediction, and their performances are closely related to the flow accumulation area (FAA) of the sub-basin. The QRF model outperforms the CMAL-LSTM model in most sub-basins with smaller FAA, while the CMAL-LSTM model has an undebatable advantage in sub-basins with FAA larger than 60 000 km2 in the Yalong River basin. In terms of deterministic predictions, the CMAL-LSTM model is preferred, especially when the raw streamflow is poorly simulated and used as input. However, setting aside the differences in model performance, the QRF model with 100-member quantiles demonstrates a noteworthy advantage by exhibiting a 50 % reduction in computation time compared to the CMAL-LSTM model with the same ensemble members in all experiments. As a result, this study provides insights into model selection in hydrological post-processing and the trade-offs between model performance and computational efficiency. The findings highlight the importance of considering the specific application scenario, such as the catchment size and the required accuracy level, when selecting a suitable model for hydrological post-processing.

Geology↗

W17_geowave “3D full waveform geophysical models”

Performance of the MCMC inversion according to the number of cores for the computation. A) 64 cores. B) 480 cores. C) 816 cores. The true model is represented by the black line. Vsv is the wave speed of S waves polarized in the vertical plane, ξ is an anisotropy parameter. The Earth is highly anisotropics; the wavespeed of seismic waves depends on the polarization of the wave. Seismic inversion of the elastic structure is usually limited to isotropic information such as Vsv. Our research looked at the inversion of Earth anisotropy.

58 GEOSCIENCES↗

Streamlining the Coupling of BISON and Dakota Through the NEAMS Workbench

Metallic nuclear fuels for use in advanced reactors are an active area of research and development. Robust, accurate metallic fuel performance models are necessary for the design, analysis, and licensing of such reactors. However, metallic fuel performance models require additional development; they are not as mature as uranium dioxide fuel performance models. To support further metallic fuel development, Oak Ridge National Laboratory and the University of Florida have streamlined the coupling of the BISON fuel performance code with Design Analysis Kit for Optimization and Terascale Applications (Dakota) statistical analysis tool through the Nuclear Energy Advanced Modeling and Simulation (NEAMS) Workbench. This work included performing three different sensitivity analyses on metallic nuclear fuel models in BISON. The analyses examined were a general model of the IFR-1 experiment, the X430 experiment T654 pin, and the X430 experiment T651 pin. The results suggest that BISON and Dakota can be integrated through NEAMS Workbench to perform sensitivity and uncertainty analyses and visualize the results.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Comparison of Mesoscale Model Setups for Offshore Wind Resource Assessment: A New Jersey Case Study

As the offshore wind energy industry begins to emerge on the U.S. northeast coast, there is an urgent need for an accurate characterization of the offshore wind resource. The offshore regime features various resource characteristics not seen onshore, including frequent coastal low-level jets, non-steady surface conditions (e.g. waves), complex air-sea and land-sea interactions, and coastal mesoscale circulations (e.g. sea breeze). An accurate characterization of these phenomena in mesoscale models is critical to support accurate energy production estimates and forecasting for future offshore wind farms. However, a robust validation of mesoscale model performance in the offshore U.S. has been limited due to sparse data and difficulty obtaining offshore measurements. Consequently, it is unclear how mesoscale models perform offshore and which suite of parameterizations and input data are best suited for accurate resource characterization. To begin addressing this knowledge gap, the National Renewable Energy Laboratory, in collaboration with the Rutgers Center for Ocean Observing Leadership, conducted a mesoscale model validation campaign in the offshore environment. The Weather Research and Forecasting (WRF) model was assessed and the New Jersey offshore coastal area served as the validation domain. An ensemble of WRF simulations conducted over a one-year period sampled from a range of model setups, including different reanalysis and forecast data inputs, sea surface temperature data inputs, planetary boundary layer parameterizations, and WRF versions. The performance of each ensemble member was validated against a network of observations including offshore floating lidars, coastal met towers, offshore platform measurements, and offshore buoys. Model performance was assessed on annual, seasonal, and diurnal scales with particular emphasis on the vertical wind speed profile and temperature stratification. Preliminary results from this validation work will be presented here. The key WRF inputs and parameters driving changes in the modeled wind resource will be discussed and preliminary recommendations on WRF setups for offshore wind resource modeling will be proposed. The application of this validation exercise to other proposed offshore wind energy areas in the U.S. will also be discussed. mesoscale circulations (e.g. sea breeze). An accurate characterization of these phenomena in mesoscale models is critical to support accurate energy production estimates and forecasting for future offshore wind farms. However, a robust validation of mesoscale model performance in the offshore U.S. has been limited due to sparse data and difficulty obtaining offshore measurements. Consequently, it is unclear how mesoscale models perform offshore and which suite of parameterizations and input data are best suited for accurate resource characterization. To begin addressing this knowledge gap, the National Renewable Energy Laboratory, in collaboration with the Rutgers Center for Ocean Observing Leadership, conducted a mesoscale model validation campaign in the offshore environment. The Weather Research and Forecasting (WRF) model was assessed and the New Jersey offshore coastal area served as the validation domain. An ensemble of WRF simulations conducted over a one-year period sampled from a range of model setups, including different reanalysis and forecast data inputs, sea surface temperature data inputs, planetary boundary layer parameterizations, and WRF versions. The performance of each ensemble member was validated against a network of observations including offshore floating lidars, coastal met towers, offshore platform measurements, and offshore buoys. Model performance was assessed on annual, seasonal, and diurnal scales with particular emphasis on the vertical wind speed profile and temperature stratification. Preliminary results from this validation work will be presented here. The key WRF inputs and parameters driving changes in the modeled wind resource will be discussed and preliminary recommendations on WRF setups for offshore wind resource modeling will be proposed. The application of this validation exercise to other proposed offshore wind energy areas in the U.S. will also be discussed.

17 WIND ENERGY↗

Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Prediction

Abstract The rapid rise of deep learning (DL) in numerical weather prediction (NWP) has led to a proliferation of models which forecast atmospheric variables with comparable or superior skill than traditional physics-based NWP. However, among these leading DL models, there is a wide variance in both the training settings and architecture used. Further, the lack of thorough ablation studies makes it hard to discern which components are most critical to success. In this work, we show that it is possible to attain high forecast skill even with relatively off-the-shelf architectures, simple training procedures, and moderate compute budgets. Specifically, we train a minimally modified Swin Transformer V2 (SwinV2) on ERA5 data and find that it attains superior skill in terms of mean-square errors of deterministic forecasts when compared against the European Centre for Medium-Range Weather Forecasts’ Integrated Forecasting System (IFS). Almost all DL–NWP systems share a core set of hyperparameters and design decisions. To aid and expedite future DL–NWP research, we present an in-depth, systematic exploration of different loss functions, model sizes and depths, patch sizes, and multistep training objectives. We also examine the model performance with metrics beyond the typical accuracy (ACC) and RMSE and investigate how the performance scales with model size. Through our open-source code, scoring pipelines, and models, we share our findings on key aspects of the training pipeline. These ablations reduce the necessity for expensive hyperparameter tuning and lower the barrier to entry for future DL–NWP research. Significance Statement This study investigates the potential of using large-scale transformer-based models for weather prediction, showing that it is possible to achieve high forecast accuracy with simpler, off-the-shelf architectures. By training a minimally modified SwinV2 transformer on ERA5 data, we show that the model achieves competitive forecast skill in terms of mean-square error for key variables, outperforming the European Centre for Medium-Range Weather Forecasts’ Integrated Forecasting System (IFS) at all lead times. Our findings suggest that effective training strategies, such as multistep fine-tuning and channel-weighted losses, significantly enhance the model’s performance. However, we also highlight that these improvements come with trade-offs in other areas, such as ensemble spread and high-frequency spatial detail. This work highlights the promise of deep learning in improving weather forecasts, which could lead to better preparedness and response to weather events, ultimately benefiting society by providing more reliable weather predictions.

Willard, Jared D. [Lawrence Berkeley National Labo↗

What Makes You Hold on to That Old Car? Joint Insights From Machine Learning and Multinomial Logit on Vehicle-Level Transaction Decisions

What makes you hold on to that old car? While the vast majority of household vehicles are still powered by conventional internal combustion engines, the progress of adopting emerging vehicle technologies will critically depend on how soon the existing vehicles are transacted out of the household fleet. Leveraging a nationally representative longitudinal data set, the Panel Study of Income Dynamics, this study examines how household decisions to dispose of or replace a given vehicle are: 1) influenced by the vehicle’s attributes, 2) mediated by households’ concurrent socio-demographic and economic attributes, and 3) triggered by key life cycle events. Coupled with a newly developed machine learning interpretation tool, TreeExplainer, we demonstrate an innovative use of machine learning models to augment traditional logit modeling to both generate behavioral insights and improve model performance. We find the two gradient-boosting-based methods, CatBoost and LightGBM, are the best performing machine learning models for this problem. The multinomial logistic model can achieve similar performance levels after its model specification is informed by TreeExplainer. Both machine learning and multinomial logit models suggest that while older vehicles are more likely to be disposed of or replaced than newer ones, such probability decreases as the vehicles serve the family longer. Pickup trucks and sport utility vehicles are less likely to be disposed of or replaced than cars, and leased vehicles are more likely to be transacted than owned vehicles. We find that married families, families with higher education levels, homeowners, and older families tend to keep their vehicles longer. Life events such as childbirth, residential relocation, and change of household composition and income are found to increase vehicle disposal and/or replacement. We provide additional insights on the timing of vehicle replacement or disposal, in particular, the presence of children and childbirth events are more strongly associated with vehicle replacement among younger parents.

33 ADVANCED PROPULSION SYSTEMS↗