Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Performance Modeling”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Blind photovoltaic modeling intercomparison: A multidimensional data analysis and lessons learned

The Photovoltaic (PV) Performance Modeling Collaborative (PVPMC) organized a blind PV performance modeling intercomparison to allow PV modelers to blindly test their models and modeling ability against real system data. Measured weather and irradiance data were provided along with detailed descriptions of PV systems from two locations (Albuquerque, New Mexico, USA, and Roskilde, Denmark). Participants were asked to simulate the plane-of-array irradiance, module temperature, and DC power output from six systems and submit their results to Sandia for processing. The results showed overall median mean bias (i.e., the average error per participant) of 0.6% in annual irradiation and –3.3% in annual energy yield. While most PV performance modeling results seem to exhibit higher precision and accuracy as compared to an earlier blind PV modeling study in 2010, human errors, modeling skills, and derates were found to still cause significant errors in the estimates.

14 SOLAR ENERGY↗
DOE OSTI2023

Exploring Randomly Wired Neural Networks for Climate Model Emulation

Exploring the climate impacts of various anthropogenic emissions scenarios is key to making informed decisions for climate change mitigation and adaptation. State-of-the-art Earth system models can provide detailed insight into these impacts but have a large associated computational cost on a per-scenario basis. This large computational burden has driven recent interest in developing cheap machine learning models for the task of climate model emulation. In this paper, we explore the efficacy of randomly wired neural networks for this task. We describe how they can be constructed and compare them with their standard feedforward counterparts using the ClimateBench dataset. Specifically, we replace the serially connected dense layers in multilayer perceptrons, convolutional neural networks, and convolutional long short-term memory networks with randomly wired dense layers and assess the impact on model performance for models with 1 million and 10 million parameters. We find that models with less-complex architectures see the greatest performance improvement with the addition of random wiring (up to 30.4% for multilayer perceptrons). Furthermore, of 24 different model architecture, parameter count, and prediction task combinations, only one had a statistically significant performance deficit in randomly wired networks relative to their standard counterparts, with 14 cases showing statistically significant improvement. We also find no significant difference in prediction speed between networks with standard feedforward dense layers and those with randomly wired layers. These findings indicate that randomly wired neural networks may be suitable direct replacements for traditional dense layers in many standard models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

A machine learning approach for identifying variables associated with risk of developing neutralizing antidrug antibodies to factor VIII

A key unmet need in the management of hemophilia A (HA) is the lack of clinically validated markers that are associated with the development of neutralizing antibodies to Factor VIII (FVIII) (commonly referred to as inhibitors). This study aimed to identify relevant biomarkers for FVIII inhibition using Machine Learning (ML) and Explainable AI (XAI) using the My Life Our Future (MLOF) research repository. The dataset includes biologically relevant variables such as age, race, sex, ethnicity, and the variants in the F8 gene. In addition, we previously carried out Human Leukocyte Antigen Class II (HLA-II) typing on samples obtained from the MLOF repository. Using this information, we derived other patient-specific biologically and genetically important variables. These included identifying the number of foreign FVIII derived peptides, based on the alignment of the endogenous FVIII and infused drug sequences, and the foreign-peptide HLA-II molecule binding affinity calculated using NetMHCIIpan. The data were processed and trained with multiple ML classification models to identify the top performing models. The top performing model was then chosen to apply XAI via SHAP, (SHapley Additive exPlanations) to identify the variables critical for the prediction of FVIII inhibitor development in a hemophilia A patient. Using XAI we provide a robust and ranked identification of variables that could be predictive for developing inhibitors to FVIII drugs in hemophilia A patients. These variables could be validated as biomarkers and used in making clinical decisions and during drug development. The top five variables for predicting inhibitor development based on SHAP values are: (i) the baseline activity of the FVIII protein, (ii) mean affinity of all foreign peptides for HLA DRB 3, 4, & 5 alleles, (iii) mean affinity of all foreign peptides for HLA DRB1 alleles), (iv) the minimum affinity among all foreign peptides for HLA DRB1 alleles, and (v) F8 mutation type.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

High-Performance Accelerator Modeling: Toward Improving Controls and Diagnostics for High-Brightness Beams in Experiment

One of the main charges of beam physics is to improve the overall beam quality delivered to experiments and applications, which is generally quantified by the beam brightness. High brightness beams have numerous applications, including x-ray free electron lasers and ultrafast electron diffraction (UED). To these ends, this thesis details efforts to use high-performance models --- high-fidelity models that execute quickly --- for controls and diagnostics. To demonstrate the generality of these techniques, this thesis focuses on three of the most successful photoinjector designs currently used worldwide: the UCLA/SLAC/BNL-type high-gradient S-band gun, the continuous-wave high-repetition rate VHF APEX gun and the L-band DESY-PITZ-type gun. Work will be shown from Pegasus (UCLA), HiRES (LBNL) and FAST (FNAL).Specifically, data-driven models for online virtual diagnostics are presented, in this case, in the context of UED at HiRES, leading to a temporal resolution improvement. Methods for improving the fidelity of physics-based models are discussed, with examples at HiRES, Pegasus and FAST. Markov-chain Monte Carlo analysis is applied to match simulations, in the context of photocathode studies at HiRES and Pegasus. Lastly, the augmentation of online model-based predictions with model-independent optimization is explored in a fluctuating environment at Pegasus and HiRES. A central theme of this dissertation is working with parameter fluctuations when modeling an accelerator beamline. Long-term drifts and shot-to-shot jitter exist in every accelerator to a varying degree and therefore play an important role in every chapter of this dissertation. This thesis attempts to address the issues associated with these fluctuations when trying to develop faithful model representations of the system.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

To Exascale and Beyond—The Simple Cloud-Resolving E3SM Atmosphere Model (SCREAM), a Performance Portable Global Atmosphere Model for Cloud-Resolving Scales

The new generation of heterogeneous CPU/GPU computer systems offer much greater computational performance but are not yet widely used for climate modeling. One reason for this is that traditional climate models were written before GPUs were available and would require an extensive overhaul to run on these new machines. In addition, even conventional “high–resolution” simulations don't currently provide enough parallel work to keep GPUs busy, so the benefits of such overhaul would be limited for the types of simulations climate scientists are accustomed to. The vision of the Simple Cloud-Resolving Energy Exascale Earth System (E3SM) Atmosphere Model (SCREAM) project is to create a global atmospheric model with the architecture to efficiently use GPUs and horizontal resolution sufficient to fully take advantage of GPU parallelism. After 5 years of model development, SCREAM is finally ready for use. In this paper, we describe the design of this new code, its performance on both CPU and heterogeneous machines, and its ability to simulate real-world climate via a set of four 40 day simulations covering all 4 seasons of the year.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

An Efficient Storage-Driven Machine Learning Model for Performance in the Era of Multimodal Scientific Data

Scientific workflows are increasingly relying on machine learning (ML), simulation, and hybrid techniques to predict, understand, and optimize the behavior of complex experiments. High-performance computing has greatly improved researchers’ ability to acquire diverse data modalities in these workflows. Recent studies suggest that the performance of machine learning models can be improved by integrating data from various sources. Unfortunately, these workloads pose unprecedent pressure on the network storage to meet the demands associated with accessing these multimodal data. To mitigate the impact of intensive IO, we propose a solution that utilizes a multi-tier High-Performance Computing (HPC) distributed storage and data processing framework, placing computation where the data resides for better performance. By adopting this project, the scientific community will gain new opportunities to explore multimodal storage-driven possibilities, integrating multiple scientific data sources with advanced streaming frameworks. Additionally, our framework effectively utilizes computing resources and bridges the gaps identified by HPC experts. Our proposed approach tackles scalability and persistence challenges by leveraging native persistency, which has posed difficulties in traditional approaches. Furthermore, we seek to enhance fault-tolerance and load-balance of computations by leveraging real-time streaming in diverse scientific computing environments, thereby propelling advanced scientific computing research into the next generation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

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↗
DOE OSTI2022

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↗
DOE OSTI2023

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↗
DOE OSTI2024

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↗
DOE OSTI2024

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↗
DOE OSTI2022

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↗
DOE OSTI2025

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↗
DOE OSTI2023

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↗
DOE OSTI2025

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↗
DOE OSTI2022

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↗
DOE OSTI2026

Education for PV Modeling Professionals: Survey of Educators

We report a survey of instructors at universities offering courses that address PV performance modeling. We confirm our earlier finding that most courses lack the level of detail sought by the professional community. We recommend that the PV Performance Modeling Collaborative (PVPMC), or a university, sponsor a committee to produce a curriculum outline for PV system performance modeling, and that the PVPMC solicit industry for well-documented examples of PV system designs and accompany

Hansen, Clifford [Sandia National Laboratories (SN↗
DOE OSTI2022

Uncertainty propagation in pore water chemical composition calculation using surrogate models

Performance assessment in deep geological nuclear waste repository systems necessitates an extended knowledge of the pore water chemical conditions prevailing in host-rock formations. In the last two decades, important progress has been made in the experimental characterization and thermodynamic modeling of pore water speciation, but the influence of experimental artifacts and uncertainties of thermodynamic input parameters are seldom evaluated. In this respect, we conducted an uncertainty propagation study in a reference geochemical model describing the pore water chemistry of the Callovian-Oxfordian clay formation. Nineteen model input parameters were perturbed, including those associated to experimental characterization (leached anions, exchanged cations, cation exchange selectivity coefficients) and those associated to generic thermodynamic databases (solubilities). A set of 13 quantities of interest were studied by the use of polynomial chaos expansions built non-intrusively with a least-squares forward stepwise regression approach. Training and validation sets of simulations were carried out using the geochemical speciation code PHREEQC. The statistical results explored the marginal distribution of each quantity of interest, their bivariate correlations as well as their global sensitivity indices. The influence of the assumed distributions for input parameters uncertainties was evaluated by considering two parametric domain sizes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗