SEARCH · Engineering Papers

Results for “Generative models”

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.

SourceResearch connectionFrom yearThrough year

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

At least 595 records · Page 33

All sources NASA NTRS DOE OSTI

DOE OSTI2025

PLUSWIND Derived Data

This dataset consists of annual CSV files containing multiple sources of modeled, hourly wind speeds and generation. For complete information about this dataset, including validation of modeled generation versus recorded generation, please see the Scientific Data article: Millstein, D., Jeong, S., Ancell, A., & Wiser, R. (2023). A database of hourly wind speed and modeled generation for US wind plants based on three meteorological models. Scientific Data, 10(1), 883. https://doi.org/10.1038/s41597-023-02804-w

17 WIND ENERGY↗

DOE OSTI2020

Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials

A major challenge in materials design is how to efficiently search the vast chemical design space to find the materials with desired properties. One effective strategy is to develop sampling algorithms that can exploit both explicit chemical knowledge and implicit composition rules embodied in the large materials database. Here, we propose a generative machine learning model (MatGAN) based on a generative adversarial network (GAN) for efficient generation of new hypothetical inorganic materials. Trained with materials from the ICSD database, our GAN model can generate hypothetical materials not existing in the training dataset, reaching a novelty of 92.53% when generating 2 million samples. The percentage of chemically valid (charge-neutral and electronegativity-balanced) samples out of all generated ones reaches 84.5% when generated by our GAN trained with such samples screened from ICSD, even though no such chemical rules are explicitly enforced in our GAN model, indicating its capability to learn implicit chemical composition rules to form compounds. Our algorithm is expected to be used to greatly expand the range of the design space for inverse design and large-scale computational screening of inorganic materials.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Enhancing power grid resilience to winter storms via generator winterization with equity considerations

Here we develop two-stage stochastic programming models for generator winterization that enhance power grid resilience while incorporating social equity. The first stage in our models captures the investment decisions for generator winterization, and the second stage captures the operation of a degraded power grid, with the objective of minimizing load shed and social inequity. To incorporate equity into our models, we propose a concept called adverse effect probability that captures the disproportionate effects of power outages on communities with varying vulnerability levels. Grid operations are modeled using DC power flow, and equity is captured through mean or maximum adverse effects experienced by communities. We apply our models to a synthetic Texas power grid, using winter storm scenarios created from the generator outage data from the 2021 Texas winter storm. Our extensive numerical experiments show that more equitable outcomes, in the sense of reducing adverse effects experienced by vulnerable communities during power outages, are achievable with no impact on total load shed through investing in winterization of generators in different locations and capacities.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2025

Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing

We demonstrate a multi-fidelity (MF) machine learning ensemble framework for the inverse design of photonic surfaces, trained on a dataset of 11,759 samples that we fabricate using high throughput femtosecond laser processing. The MF ensemble combines an initial low fidelity model for generating design solutions, with a high fidelity model that refines these solutions through local optimization. The combined MF ensemble can generate multiple disparate sets of laser-processing parameters that can each produce the same target input spectral emissivity with high accuracy (root mean squared errors < 2%). SHapley Additive exPlanations analysis shows transparent model interpretability of the complex relationship between laser parameters and spectral emissivity. Finally, the MF ensemble is experimentally validated by fabricating and evaluating photonic surface designs that it generates for improved efficiency energy harvesting devices. Our approach provides a powerful tool for advancing the inverse design of photonic surfaces in energy harvesting applications.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Data and Code for Understanding Generative AI Content with Embedding Models

This repository contains code for the experiments in the paper "Understanding Generative AI Content with Embedding Models". Constructing high-quality features is critical to any quantitative data analysis. While feature engineering was historically addressed by carefully hand-crafting data representations based on domain expertise, deep neural networks (DNNs) now offer a radically different approach. DNNs implicitly engineer features by transforming their input data into hidden feature vectors called embeddings. For embedding vectors produced by foundation models -- which are trained to be useful across many contexts -- we demonstrate that simple and well-studied dimensionality-reduction techniques such as Principal Component Analysis uncover inherent heterogeneity in input data concordant with human-understandable explanations. Of the many applications for this framework, we find empirical evidence that there is intrinsic separability between real samples and those generated by artificial intelligence (AI).

Vargas, Max [Pacific Northwest National Laboratory↗

DOE OSTI2023

Hydropower Energy Storage Capacity (HESC) Dataset

The Hydropower Energy Storage Capacity (HESC) Dataset catalogs characteristics that are relevant to evaluating reservoir storage and estimates of energy storage capacity based on varying levels of detail. Hydropower dams and reservoirs were included based on information from the National Inventory of Dams (NID; USACE, 2021) and Global Reservoir and Dam (GRanD v1.3) and Existing Hydropower Assets datasets. These data provide a foundation for understanding available resources at existing hydropower facilities and their potential to provide storage of energy and more flexible generation. Estimates of energy storage capacity include: • Level 1 – nominal energy storage capacity based on maximum storage capacities and hydraulic head • Level 2 – nominal energy storage capacity based on historical models or observations of reservoir volume and hydraulic head. These estimates are provided based on capacity from the entire historical period as well as monthly values. • Level 3 – modeled energy generation based on volume-elevation relationships, historical storage, observed/modeled inflows, and hydraulic capacity of turbines and calculated both as overall and on a monthly basis. • Level 4 – modeled energy generation incorporating information from Level 3 and operational constraints. For facilities where installed capacity is known, there are also estimates for discharge duration (the length of time when a facility could provide generation at a given capacity).

13 HYDRO ENERGY↗

DOE OSTI2022

An experimental and modeling study on autoignition of 2-phenylethanol and its blends with n-heptane

2-Phenylethanol (2-PE) is an aromatic alcohol with high research octane number, high octane sensitivity, and a potential to be produced using biomass. Considering that 2-PE can be used as a fuel additive for boosting the anti-knocking quality of gasoline in spark-ignition engines and as the low reactivity fuel or fuel component in dual-fuel reactivity controlled compression ignition (RCCI) engines, it is of fundamental and practical interest to understand the autoignition chemistry of 2-PE, especially at low-to-intermediate temperatures (<1000 K). Based upon the experimental ignition delay time (IDT) results of neat 2-PE obtained from our previous rapid compression machine (RCM) investigation and the literature shock tube study, a detailed chemical kinetic model of 2-PE is developed herein, covering low-to-high temperature regimes. Besides, RCM experiments using binary fuel blends of 2-PE and n-heptane (nC7) are conducted in this work to investigate the nC7/2-PE blending effects, as they represent a dual-fuel system for RCCI operations. Furthermore, the newly developed 2-PE model is merged with a well-validated nC7 kinetic model to generate the current nC7/2-PE binary blend model. Overall, the consolidated model reasonably predicts the experimental IDT data of neat 2-PE and nC7/2-PE blends, as well as captures the experimental effects of pressure, equivalence ratio, and blending ratio on autoignition. Finally, model-based chemical kinetic analyses are carried out to understand and identify the controlling chemistry accounting for the observed blending effects in RCM experiments. In conclusion, the analyses reveal that nC7 enhances 2-PE autoignition via providing extra $\dot{O}$H radicals to the shared radical pool, while the diminished nC7 promoting effect on 2-PE autoignition with increasing temperature is due to the negative temperature coefficient characteristics of nC7.

2-phenlyethanol↗

DOE OSTI2024

Large Ensemble Exploration of Global Energy Transitions Under National Emissions Pledges

Global climate goals require a transition to a deeply decarbonized energy system. Meeting the objectives of the Paris Agreement through countries' nationally determined contributions and long-term strategies represents a complex problem with consequences across multiple systems shrouded by deep uncertainty. Robust, large-ensemble methods and analyses mapping a wide range of possible future states of the world are needed to help policymakers design effective strategies to meet emissions reduction goals. This study contributes a scenario discovery analysis applied to a large ensemble of 5,760 model realizations generated using the Global Change Analysis Model. Eleven energy-related uncertainties are systematically varied, representing national mitigation pledges, institutional factors, and techno-economic parameters, among others. The resulting ensemble maps how uncertainties impact common energy system metrics used to characterize national and global pathways toward deep decarbonization. Results show globally consistent but regionally variable energy transitions as measured by multiple metrics, including electricity costs and stranded assets. Larger economies and developing regions experience more severe economic outcomes across a broad sampling of uncertainty. The scale of CO 2 removal globally determines how much the energy system can continue to emit, but the relative role of different CO 2 removal options in meeting decarbonization goals varies across regions. Previous studies characterizing uncertainty have typically focused on a few scenarios, and other large-ensemble work has not (to our knowledge) combined this framework with national emissions pledges or institutional factors. Our results underscore the value of large-ensemble scenario discovery for decision support as countries begin to design strategies to meet their goals.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2024

Case study of a bore wind-ramp event from lidar measurements and HRRR simulations over ARM Southern Great Plains

The rapid change of wind speed and direction on 21 August 2017 is studied using Doppler lidar measurements at five sites of the Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) facility in north-central Oklahoma. The Doppler lidar data were investigated along with meteorological variables such as temperature, humidity, and turbulence available from the large suite of instrumentation deployed at the SGP Central Facility (C1) during the Land-Atmosphere Feedback Experiment in August 2017. Lidar measurements at five sites, separated by 55-70 km, allowed us to document the development and evolution of the wind flow over the SGP area, examine synoptic conditions to understand the mechanism that leads to the ramp event, and estimate the ability of the High-Resolution Rapid Refresh model to reproduce this event. The flow feature in question is an atmospheric bore, a small-scale phenomenon that is challenging to represent in models, that was generated by a thunderstorm outflow northwest of the ARM SGP area. The small-scale nature of bores, its impact on power generation, and the modeling challenges associated with representing bores are discussed in this paper. In conclusion, the results also provide information about model errors between sites of different surface and vegetation types.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

Development of new baseline models for U.S. medium office buildings based on commercial buildings energy consumption survey data

Building energy estimation for the building sector under various scenarios are needed for building energy regulation and policy making. This often starts with representative baselines (either empirical baseline or modeled baseline). Commercial Buildings Energy Consumption Survey (CBECS) data is a widely used empirical baseline for U.S. commercial buildings, but none of the existing baseline model are developed to represent the CBECS data. This paper aims to develop new baseline models for the U.S. medium office buildings, which can produce modeled baselines consistent with the CBECS data. Here, we introduced the methodology to create baseline models and the criteria to evaluate the performance of baseline models. The methodology consists of three phases: (1) identification of model inputs, (2) model calibration, and (3) model validation with uncertainty analysis. The evaluation index is the coefficient of variation of the root-mean-square deviation (CV(RMSD)) of site energy use intensities (EUIs) between the modeled baseline and empirical baseline. Then 30 new baseline models for two vintages (pre- and post-1980) and 15 climate zones were created. The evaluation shows that the CV(RMSD) is lower than 0.05 for the modeled baselines produced by the new baseline models. As a comparison, the CV(RMSD) is higher than 0.1 for the existing modeled baselines generated by DOE Commercial Reference Building Models. Further analysis shows that the new baseline models are able to capture the uncertainties of the representative features of existing buildings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2025

Firm Synthesizer and Supply-chain Simulator (SynthFirm) v2.0

SynthFirm is a national-scale agent-based freight demand model which generates a complete synthetic population of firms in the U.S. and the business-to-business commodity flows between them. Using publicly available data sources as inputs, SynthFirm simulates detailed firm and fleet characteristics, commodity production and consumption, formation of supply chains, and selection of shipping modes, all of which are essential drivers of commodity flow at a disaggregate level. The SynthFirm 2.0 version includes national commercial vehicle fleet generation, international trade simulation and automized model validation pipeline, which allows seemless deployment across the nation and build a comprehensive freight inventories at national scale or for selected region.

Yang, Hung-Chia [Lawrence Berkeley National Labora↗

DOE OSTI2023

Biophysical Impact of Land-Use and Land-Cover Change on Subgrid Temperature in CMIP6 Models

In this study, we investigate the air temperature response to land-use and land-cover change (LULCC; cropland expansion and deforestation) using subgrid land model output generated by a set of CMIP6 model simulations. Our study is motivated by the fact that ongoing land-use activities are occurring at local scales, typically significantly smaller than the resolvable scale of a grid cell in Earth system models. It aims to explore the potential for a multimodel approach to better characterize LULCC local climatic effects. On an annual scale, the CMIP6 models are in general agreement that croplands are warmer than primary and secondary land (psl; mainly forests, grasslands, and bare ground) in the tropics and cooler in the mid–high latitudes, except for one model. The transition from warming to cooling occurs at approximately 40°N. Although the surface heating potential, which combines albedo and latent heat flux effects, can explain reasonably well the zonal mean latitudinal subgrid temperature variations between crop and psl tiles in the historical simulations, it does not provide a good prediction on subgrid temperature for other land tile configurations (crop vs forest; grass vs forest) under Shared Socioeconomic Pathway 5–8.5 (SSP5–8.5) forcing scenarios. A subset of simulations with the CESM2 model reveals that latitudinal subgrid temperature variation is positively related to variation in net surface shortwave radiation and negatively related to variation in the surface energy redistribution factor, with a dominant role from the latter south of 30°N. We suggest that this emergent relationship can be used to benchmark the performance of land surface parameterizations and for prediction of local temperature response to LULCC.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

Global Teleconnections: Atmospheric Interactions Across Scales [Slides]

This project aims at an improved understanding of non-hydrostatic dynamics in atmospheric modeling using the DOE’s next generation climate model. One aspect that we have been focusing on is baroclinic instability which is closely related to mid-latitude cyclone genesis. The other aspect that we recently developed is E3SM simulations under Radiative-Convective Equilibrium (RCE), a prototype of tropical climate.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Development of the IES Plug-and-Play Framework

This report discusses the status of the flexible plug-and-play framework development currently ongoing that aims to integrate Modelica/Dymola with the Risk Analysis and Virtual ENvironment (RAVEN) software in terms of both Functional Mock-Up Interface (FMI)/Functional Mock-Up Unit (FMU) construction and repository structures that aim to ease the sharing and simulation of complex dynamic models. This report aims to provide an overview of all the performed activities resolving around the deployment of methods, software infrastructures, guidelines and workflow for the construction and usage of models, encapsulated using the FMI/FMU protocols and standards. In particular, the report is organized in three main macro-subjects, which are connected to each other: - FMI/FMU adaptors for modelica models - HYBRID repository new structure and open-source deployment - RAVEN FMI/FMU exporting capabilities and Artificial Intelligence (AI)-based analysis acceleration. The first part of the report discusses the FMI/FMU adaptors that have been created within the HYBRID repository to allow users to quickly export models, such as FMUs. Several examples are shown that highlight the step-by-step process of converting an existing Modelica model into an FMU for use within the Dymola platform. Simulation results demonstrate that, while minor differences may occur, the overall control, trends, and solution integrity are maintained between standard Modelica simulation and FMU simulation results. However, it is worth noting that, for small systems, the FMU results have a slower simulation time than the Modelica only simulation. Using this process, a company can provide models that contain proprietary information to entities without disclosing any of the information about the model that could be considered business sensitive. Such an ability would allow institutions to bypass the necessity of “whitewashing” data. In the second part of the report, the new structure of the HYBRID repository is discussed with a major focus on the series of updates that has been completed. These updates include the addition of Modelica system-level regression tests and software quality assurance documentation that ensure that modifications to the Modelica models do not alter system-level model results. The third and final part of the report aims to report the work that has been performed for the deployment of methods and workflows for the construction of RAVEN AI-based models compliant with the FMI/FMU standard. Such development represents the key for the deployment of the concept of “Flexible ecosystem” since it allows for the replacement of high-fidelity modelica models (or any other FMI/FMU compliant model) with RAVEN generated AI surrogate models. Overall, extensive work has been completed on developing FMUs and FMIs from existing models, understanding the requirements and limitations of FMUs, and open-sourcing the HYBRID repository with an integrated regression system.

42 ENGINEERING↗

DOE OSTI2021

Development of the IES Plug-and-Play Framework

14 SOLAR ENERGY↗

DOE OSTI2023

Porting the WAVEWATCH III (v6.07) wave action source terms to GPU

Abstract. Surface gravity waves play a critical role in several processes, including mixing, coastal inundation, and surface fluxes. Despite the growing literature on the importance of ocean surface waves, wind–wave processes have traditionally been excluded from Earth system models (ESMs) due to the high computational costs of running spectral wave models. The development of the Next Generation Ocean Model for the DOE’s (Department of Energy) E3SM (Energy Exascale Earth System Model) Project partly focuses on the inclusion of a wave model, WAVEWATCH III (WW3), into E3SM. WW3, which was originally developed for operational wave forecasting, needs to be computationally less expensive before it can be integrated into ESMs. To accomplish this, we take advantage of heterogeneous architectures at DOE leadership computing facilities and the increasing computing power of general-purpose graphics processing units (GPUs). This paper identifies the wave action source terms, W3SRCEMD, as the most computationally intensive module in WW3 and then accelerates them via GPU. Our experiments on two computing platforms, Kodiak (P100 GPU and Intel(R) Xeon(R) central processing unit, CPU, E5-2695 v4) and Summit (V100 GPU and IBM POWER9 CPU) show respective average speedups of 2× and 4× when mapping one Message Passing Interface (MPI) per GPU. An average speedup of 1.4× was achieved using all 42 CPU cores and 6 GPUs on a Summit node (with 7 MPI ranks per GPU). However, the GPU speedup over the 42 CPU cores remains relatively unchanged (∼ 1.3×) even when using 4 MPI ranks per GPU (24 ranks in total) and 3 MPI ranks per GPU (18 ranks in total). This corresponds to a 35 %–40 % decrease in both simulation time and usage of resources. Due to too many local scalars and arrays in the W3SRCEMD subroutine and the huge WW3 memory requirement, GPU performance is currently limited by the data transfer bandwidth between the CPU and the GPU. Ideally, OpenACC routine directives could be used to further improve performance. However, W3SRCEMD would require significant code refactoring to make this possible. We also discuss how the trade-off between the occupancy, register, and latency affects the GPU performance of WW3.

58 GEOSCIENCES↗

DOE OSTI2022

Language models for the prediction of SARS-CoV-2 inhibitors

The COVID-19 pandemic highlights the need for computational tools to automate and accelerate drug design for novel protein targets. We leverage deep learning language models to generate and score drug candidates based on predicted protein binding affinity. We pre-trained a deep learning language model (BERT) on ∼9.6 billion molecules and achieved peak performance of 603 petaflops in mixed precision. Our work reduces pre-training time from days to hours, compared to previous efforts with this architecture, while also increasing the dataset size by nearly an order of magnitude. For scoring, we fine-tuned the language model using an assembled set of thousands of protein targets with binding affinity data and searched for inhibitors of specific protein targets, SARS-CoV-2 Mpro and PLpro. We utilized a genetic algorithm approach for finding optimal candidates using the generation and scoring capabilities of the language model. Our generalizable models accelerate the identification of inhibitors for emerging therapeutic targets.

Blanchard, Andrew E.↗

DOE OSTI2022

Synthetic data generation for machine learning model training for energy theft scenarios using cosimulation

Abstract Technical and non‐technical losses in distribution circuits result in significant economic costs to power utilities. One type of non‐technical loss is energy theft by various means including illegal tapping of feeders, bypassing the meter, and billing fraud. These losses are usually hard to detect, and can remain undetected for long periods of time. Machine learning models have been proven effective in detecting these conditions, but rely on the availability of large, good‐quality training data sets. The problem is exacerbated by the imbalanced nature of data related to these conditions—energy theft, though costly, is very rare. The available data sets generally have very few samples of theft with most of the data pertaining to normal operation. Such data sets are generally not suitable to train machine learning models. In this paper, an overview of energy theft detection techniques, the challenges with their data needs, and the limitations of current techniques to bridge such data limitations is presented. A co‐simulation framework is proposed to generate reliable training data for machine learning algorithms for theft detection. An example scenario is presented and a machine learning model is built to detect certain kinds of energy theft.

24 POWER TRANSMISSION AND DISTRIBUTION↗