SEARCH · Engineering Papers

Results for “hybrid learning”

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 487 records · Page 27

All sources NASA NTRS DOE OSTI

DOE OSTI2023

3P Program: Phenotyping X Prediction = Productivity (Final Scientific/Technical Report)

The goal of the 3P Program was to establish integrated, real-time phenotyping and to analyze above- and below-ground plant architecture and total carbon partitioning and allocation to predict heterosis and develop superior crop hybrids by fully leveraging the Sorghum gene pool. There were two overarching themes: 1) the development of a new crop improvement approach utilizing advances in high-throughput phenotyping (HTP), computing, and genomics for public dissemination and 2) leveraging this platform for sorghum crop improvement and commercialization. The Clemson team worked on creating genomic resources and using both statistical learning and high-throughput phenotyping in genomics-assisted breeding. Research was broadly interested in the genetics of carbon partitioning, with the aim of improving crop performance and achieving sustainability. The technology and resources created can be readily found in the public domain and serve to advance scientific understanding of crop genomics and breeding. Genomic prediction was able to identify top crosses to be made, and a hybrid prediction pipeline is in place to drive year-over-year genetic gain. Roots have long been ignored by plant breeders and agronomists, not because they are unimportant but because they are hard to measure. This is an untapped white space of potential insight and innovation. To address this, Hi Fidelity Genetics developed the RootTracker to measure roots in the field on a continuous basis. A database system called RootTracker Tracker was developed to handle data coming from the RootTrackers. In using this device, valuable data was observed for plant breeding, hydrochemical development, and other agricultural biology applications. Carnegie Mellon’s goal was developing new techniques to generate high-resolution 3D models of plants from data collected in the field. The idea was that more useful and more informative phenotypes could be extracted by resolving small features, such as seeds and flowers, and that by modeling in 3D, the spatial structure of plants could be examined. To achieve this, multiple images collected by a new small format structured light stereo imager were fused together. A sorghum panicle modeling pipeline was developed to allow the collection and processing of data. Carolina Seed Systems is an agricultural technology company focused on decarbonizing the agricultural system. Their technology pipeline serves to drive fundamental progress towards creation and distribution of carbon negative crops. The genomic and the engineering technology developed through the 3P Program was leveraged to deliver both value and sustainability from the grower to the consumer. Promising sorghum hybrids were scaled up and commercialized. The overall goal of our research was to integrate, create, and deploy genetic and engineering concepts and technologies to enhance crop productivity in a sustainable fashion. The combination of public and private partners allowed the basic research and hypothesis testing to be quickly accelerated for commercial application by the companies yet maintained that the core framework and academic insights remain in the public domain for continued market disruption, competition, and innovation.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2020

Using Machine Learning Tools to Predict Compressor Stall

Clean energy has become an increasingly important consideration in today’s power systems. As the push for clean energy continues, many coal-fired power plants are being decommissioned in favor of renewable power sources such as wind and solar. However, the intermittent nature of renewables means that dynamic load following traditional power systems is crucial to grid stability. With high flexibility and fast response at a wide range of operating conditions, gas turbine systems are poised to become the main load following component in the power grid. Yet, rapid changes in load can lead to fluid flow instabilities in gas turbine power systems. These instabilities often lead to compressor surge and stall, which are some of the most critical problems facing the safe and efficient operation of compressors in turbomachinery today. Although the topic of compressor surge and stall has been extensively researched, no methods for early prediction have been proven effective. This study explores the utilization of machine learning tools to predict compressor stall. The long short-term memory (LSTM) model, a form of recurrent neural network (RNN), was trained using real compressor stall datasets from a 100 kW recuperated gas turbine power system designed for hybrid configuration. Two variations of the LSTM model, classification and regression, were tested to determine optimal performance. The regression scheme was determined to be the most accurate approach, and a tool for predicting compressor stall was developed using this configuration. Overall, results show that the tool is capable of predicting stalls 5–20 ms before they occur. With a high-speed controller capable of 5 ms time-steps, mitigating action could be taken to prevent compressor stall before it occurs.

42 ENGINEERING↗

DOE OSTI2025

Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties With Deep Learning Multi‐Member and Stochastic Parameterizations

Abstract Deep learning is a powerful tool to represent subgrid processes in climate models, but many application cases have so far used idealized settings and deterministic approaches. Here, we develop stochastic parameterizations with calibrated uncertainty quantification to learn subgrid convective and turbulent processes and surface radiative fluxes of a superparameterization embedded in an Earth System Model (ESM). We explore three methods to construct stochastic parameterizations: (a) a single Deep Neural Network (DNN) with Monte Carlo Dropout; (b) a multi‐member parameterization; and (c) a Variational Encoder Decoder with latent space perturbation. We show that the multi‐member parameterization improves the representation of convective processes, especially in the planetary boundary layer, compared to individual DNNs. The respective uncertainty quantification illustrates that methods (b) and (c) are advantageous compared to a dropout‐based DNN parameterization regarding the spread of convective processes. Hybrid simulations with our best‐performing multi‐member parameterizations remained challenging and crash within the first days. Therefore, we develop a pragmatic partial coupling strategy relying on the superparameterization for condensate emulation. Partial coupling reduces the computational efficiency of hybrid Earth‐like simulations but enables model stability over 5 months with our multi‐member parameterizations. However, our hybrid simulations exhibit biases in thermodynamic fields and differences in precipitation patterns. Despite this, the multi‐member parameterizations enable improvements in reproducing tropical extreme precipitation compared to a traditional convection parameterization. Despite these challenges, our results indicate the potential of a new generation of multi‐member machine learning parameterizations leveraging uncertainty quantification to improve the representation of stochasticity of subgrid effects.

Behrens, Gunnar [Deutsches Zentrum für Luft‐ und R↗

NASA NTRS2016

An Overview of Air-Breathing Propulsion Efforts for 2015 SBIR Phase I

NASA's Small Business Innovation Research (SBIR) program focuses on technological innovation by investing in development of innovative concepts and technologies to help NASA mission directorates address critical research needs for Agency programs. This report highlights 24 of the innovative SBIR 2015 Phase I projects that emphasize one of NASA Glenn Research Center's six core competencies-Air-Breathing Propulsion. The technologies cover a wide spectrum of applications such as hybrid nanocomposites for efficient aerospace structures; plasma flow control for drag reduction; physics-based aeroanalysis methods for open rotor conceptual designs; vertical lift by series hybrid power; fast pressure-sensitive paint systems for production wind tunnel testing; rugged, compact, and inexpensive airborne fiber sensor interrogators based on monolithic tunable lasers; and high sensitivity semiconductor sensor skins for multi-axis surface pressure characterization. Each featured technology describes an innovation and technical objective and highlights NASA commercial and industrial applications. This report provides an opportunity for NASA engineers, researchers, and program managers to learn how NASA SBIR technologies could help their programs and projects, and lead to collaborations and partnerships between the small SBIR companies and NASA that would benefit both.

aerospace structures↗

DOE OSTI2025

Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems

Resource allocation in High Performance Computing (HPC) environments presents a complex and multifaceted challenge for job scheduling algorithms. Beyond the efficient allocation of system resources, schedulers must account for and optimize multiple performance metrics, including job wait time and system throughput. Traditional heuristic-based scheduling algorithms increasingly struggle and lack the efficiency needed to meet the demands and address the complexity and scale of modern HPC systems. Consequently, recent research efforts have focused on leveraging advancements in Artificial Intelligence (AI) and Deep Learning (DL), particularly Reinforcement Learning (RL), to develop more adaptable and intelligent scheduling strategies. Previous RL-based scheduling approaches have explored a range of algorithms, from Deep Q-Networks (DQN) to Proximal Policy Optimization (PPO), and more recently, hybrid methods that integrate Graph Neural Networks (GNNs) with RL techniques. However, a common limitation across these methods is their reliance on relatively small datasets, with few methods being evaluated using large-scale, multi-million-job trace datasets representative of real-world HPC workloads. Moreover, existing RL schedulers face scalability issues due to centralized policy updates, which hinder training efficiency and performance when applied to large datasets. This study introduces a novel RL-based scheduler utilizing Decentralized Distributed Proximal Policy Optimization (DD-PPO) algorithm, which supports large-scale distributed training across multiple workers without requiring parameter synchronization at every step. By eliminating reliance on centralized updates to a shared policy, the DD-PPO scheduler enhances scalability, training efficiency, and sample utilization. Experimental validation using a large real-world dataset containing over 11.5 million job traces collected from petascale HPC systems over six years assesses the influence of dataset scale on training effectiveness and compares DD-PPO performance to traditional and advanced scheduling approaches. The experimental results demonstrate improved scheduling performance in comparison to both heuristic-based schedulers and existing RL-based scheduling algorithms.

AI↗

DOE OSTI2022

Seeking regularity from irregularity: unveiling the synthesis–nanomorphology relationships of heterogeneous nanomaterials using unsupervised machine learning

Nanoscale morphology of functional materials determines their chemical and physical properties. However, despite increasing use of transmission electron microscopy (TEM) to directly image nanomorphology, it remains challenging to quantify the information embedded in TEM data sets, and to use nanomorphology to link synthesis and processing conditions to properties. We develop an automated, descriptor-free analysis workflow for TEM data that utilizes convolutional neural networks and unsupervised learning to quantify and classify nanomorphology, and thereby reveal synthesis–nanomorphology relationships in three different systems. While TEM records nanomorphology readily in two-dimensional (2D) images or three-dimensional (3D) tomograms, we advance the analysis of these images by identifying and applying a universal shape fingerprint function to characterize nanomorphology. After dimensionality reduction through principal component analysis, this function then serves as the input for morphology grouping through unsupervised learning. We demonstrate the wide applicability of our workflow to both 2D and 3D TEM data sets, and to both inorganic and organic nanomaterials, including tetrahedral gold nanoparticles mixed with irregularly shaped impurities, hybrid polymer-patched gold nanoprisms, and polyamide membranes with irregular and heterogeneous 3D crumple structures. In each of these systems, unsupervised nanomorphology grouping identifies both the diversity and the similarity of the nanomaterial across different synthesis conditions, revealing how synthetic parameters guide nanomorphology development. Our work opens possibilities for enhancing synthesis of nanomaterials through artificial intelligence and for understanding and controlling complex nanomorphology, both for 2D systems and in the far less explored case of 3D structures, such as those with embedded voids or hidden interfaces.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Novel Proposals for FAIR, Automated, Recommendable, and Robust Workflows

Lightning talks of the Workflows in Support of Large-Scale Science (WORKS) workshop are a venue where the workflow community (researchers, developers, and users) can discuss work in progress, emerging technologies and frameworks, and training and education materials. This paper summarizes the WORKS 2022 lightning talks, which cover five broad topics: data integrity of scientific workflows; a machine learning-based recommendation system; a Python toolkit for running dynamic ensembles of simulations; a cross-platform, high-performance computing utility for processing shell commands; and a meta(data) framework for reproducing hybrid workflows.

Abhinit, Ishan↗

DOE OSTI2026

Bridging Cloud and Edge Computing at NREL Using CONNECT: Cloud Optimized Networking for Next-Gen Edge Computing Technologies [Slides]

CONNECT is an innovative on-premise hardware and software solution that integrates edge and cloud computing infrastructure at NREL. Built on the AWS Greengrass middleware and leveraging the MQTT protocol, CONNECT enables real-time data streaming from IoT devices and gateways to both cloud and local services, empowering researchers to rapidly capture, analyze, and act upon edge-generated data while leveraging cloud capabilities. The platform addresses research infrastructure challenges by providing a pre-approved platform which is already configured with the correct networking and cybersecurity baselines thus eliminating procurement delays and enabling on-demand availability. CONNECT's hybrid architecture efficiently manages burstable workloads, allowing research teams to dynamically scale computational capacity, handle peak data loads, and reduce operational bottlenecks. Advanced capabilities include built-in GPU support for executing machine learning models which enables low-latency inference at the edge from models trained in the cloud. This architecture supports real-time analytics and filtering, providing a mechanism to allow only transmitting and processing high-value data. Cloud-based configuration management permits engineers to manage on-premise systems remotely, optimizing operational efficiency. By bridging edge and cloud computing, CONNECT provides NREL researchers with a flexible, scalable platform that accelerates scientific discovery while maintaining robust security and performance standards.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Scaling kinetic Monte-Carlo simulations of grain growth with combined convolutional and graph neural networks

Graph neural networks (GNN) have emerged as a promising machine learning method for microstructure simulations such as grain growth. However, accurate modeling of realistic grain boundary networks requires large simulation cells, which GNN has difficulty scaling up to. To alleviate the computational costs and memory footprint of GNN, we suggest a hybrid architecture combining a convolutional neural network (CNN) based bijective autoencoder to compress the spatial dimensions, and a GNN that evolves the microstructure in the latent space of reduced spatial sizes. Our results demonstrate that the new design significantly reduces computational costs with using fewer message passing layer (from 12 down to 3) compared with GNN alone. The reduction in computational cost becomes more pronounced as the spatial size increases, indicating strong computational scalability. For the largest mesh evaluated (160 3 ), our method reduces memory usage and runtime in inference by 117× and 115×, respectively, compared with GNN-only baseline. More importantly, it shows higher accuracy and stronger spatiotemporal capability than the GNN-only baseline, especially in long-term testing. Such combination of scalability and accuracy is essential for simulating realistic material microstructures over extended time scales. The improvements can be attributed to the bijective autoencoder’s ability to compress information losslessly from spatial domain into a high dimensional feature space, thereby producing more expressive latent features for the GNN to learn from, while also contributing its own spatiotemporal modeling capability. Training data are generated from stochastic grain growth simulations, providing realistic variability for learning robust microstructure evolution. Comprehensive system validation confirms that the model is accurate, robust, and scalable.

36 MATERIALS SCIENCE↗

DOE OSTI2022

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

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

58 GEOSCIENCES↗

DOE OSTI2024

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction is of paramount importance for both preclinical drug screening studies and clinical treatment design. To build drug response prediction models, treatment response data need to be generated through screening experiments and used as input to train the prediction models. In this study, we investigate various active learning strategies of selecting experiments to generate response data for the purposes of (1) improving the performance of drug response prediction models built on the data and (2) identifying effective treatments. Here, we focus on constructing drug-specific response prediction models for cancer cell lines. Various approaches have been designed and applied to select cell lines for screening, including a random, greedy, uncertainty, diversity, combination of greedy and uncertainty, sampling-based hybrid, and iteration-based hybrid approach. All of these approaches are evaluated and compared using two criteria: (1) the number of identified hits that are selected experiments validated to be responsive, and (2) the performance of the response prediction model trained on the data of selected experiments. The analysis was conducted for 57 drugs and the results show a significant improvement on identifying hits using active learning approaches compared with the random and greedy sampling method. Active learning approaches also show an improvement on response prediction performance for some of the drugs and analysis runs compared with the greedy sampling method.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2023

Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation Approach

Not Available

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Stable Machine‐Learning Parameterization of Subgrid Processes in a Comprehensive Atmospheric Model Learned From Embedded Convection‐Permitting Simulations

Modern climate projections often suffer from inadequate spatial and temporal resolution due to computational limitations, resulting in inaccurate representations of sub-grid processes. A promising technique to address this is the multiscale modeling framework (MMF), which embeds a kilometer-resolution cloud-resolving model (CRM) within each atmospheric column of a host climate model to replace traditional convection and cloud parameterizations. Machine learning offers a unique opportunity to make MMF more accessible by emulating the embedded CRM and reducing its substantial computational cost. Although many studies have demonstrated proof-of-concept success of achieving stable hybrid simulations, it remains a challenge to achieve near operational-level success with real geography and comprehensive variable emulation that includes, for example, explicit cloud condensate coupling. In this study, we present a stable hybrid model capable of integrating for at least 5 years with near operational-level complexity, including coarse-grid geography, seasonality, explicit cloud condensate and wind predictions, and land coupling. Our model demonstrates skillful online performance, achieving a 5-year zonal mean tropospheric temperature bias within 2 K, water vapor bias within 1 g/kg, and a precipitation root mean square error of 0.96 mm/day. Key factors contributing to our online performance include an expressive U-Net architecture and physical thermodynamic constraints for microphysics. With microphysical constraints mitigating unrealistic cloud formation, our work is the first to demonstrate realistic multi-year cloud condensate climatology under the MMF framework. Despite these advances, online diagnostics reveal persistent biases in certain regions, highlighting the need for innovative strategies to further optimize online performance.

Hu, Zeyuan [NVIDIA Corporation, Santa Clara, CA (U↗

DOE OSTI2024

A Summary of Advances in Document Summarization from 2023-2024

In computer science, Document Summarization is the task of condensing some quantity of text and related content through automated means. In this document, we review recent literature in text summarization. “Hybrid” extractive-abstractive approaches continue to be explored. Some of the latest efforts have also sought to enable users to adjust summaries with queries or other structure and begun to test reinforcement-learning style agentic LLM-based solutions.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Replace Human Intelligence with Fast and Smart Geometric Reasoning and Graph Neural Network to Accelerate Next Gen ModSim Workflows

We present an agent-guided approach to CAD geometry decomposition that automates hex/hybrid meshing with graph neural networks (GNNs) to accelerate next-generation ModSim workflows. Our end-to-end pipeline (i) reduces 3D boundary-representation (B-Rep) models to a 2D chordal axis skeleton (CAT) and then to a 1D bipartite graph of surface and curve nodes, (ii) assigns per node labels as Cubit® WebCut actions, (iii) trains a multi-action GNN under supervised learning, and (iv) predicts five surface-node and three curve-node actions on out-of-distribution test geometries. Each graph node carries geometric, topological, and meshing attributes drawn from the B-Rep “skin” and CAT “skeleton,” with two-way mappings across 3D↔2D↔1D representations to maintain traceability back to 3D CAD. The supervised learning model exhibits stable convergence of the binary cross-entropy loss and achieves 98.7% accuracy on unseen lattice models. To operationalize decision-making, we rank predicted commands by geometric significance and prototyped the agent-guided workflow through the Cubit® Meshing PowerTool GUI. As a stretch goal, we explore reinforcement learning (RL) to reduce or remove label requirements and to learn policies for action sequences that maximize total reward (e.g., size of hex-meshable regions and resulting hex mesh quality). When all-hex meshing is not feasible, the agent assists in producing hybrid meshes—prioritizing hex in critical regions and transitioning to tetrahedral elements (tets) elsewhere—maintaining fidelity while ensuring robustness. The overarching objective is to replace manual, heuristics-based decomposition with data-driven, reproducible automation, cutting meshing turnaround time by orders of magnitude. We anticipate direct impact on simulation workflows through intelligent, scalable decomposition of complex CAD models into hex-meshable subdomains.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Closing the Loop between In Situ Stress Complexity and EGS Fracture Complexity

42 ENGINEERING↗

DOE OSTI2025

Intelligently Partitioned Phasor-EMT Hybrid Simulations of Large-Scale, High-IBR Power Systems

As the penetration level of power electronics-interfaced renewables such as photovoltaics (PV) and wind has surged in modern electric grids, new operational risks caused by the dynamics of those inverter-based resources (IBRs) are emerging in parallel. Lessons learned from various grid events include that the impact of IBRs on system-level grid stability will become prominent along with the increase of renewables and that the short-timescale dynamic impacts of IBRs on grid stability are not fully captured by current commercial dynamic simulation tools [1] [2]. For example, IBRs can be controlled to mitigate those destabilizing interactions, but conventional phasor-domain tools (e.g. PSS/E, PSLF) often cannot capture that; likewise, the existing electromagnetic transient (EMT) simulation tools (e.g. PSCAD, EMTP) can simulate detailed IBR controls, but for large power systems with many IBRs, slow simulation speeds severely impede the ability to study dynamic events [3] [4]. Massively paralleling simulations using high-performance computing (HPC) can help address this, especially now that cloud-based HPC capability is widely available, but today s EMT tools are not HPC-compatible, and parallelization of dynamic simulation solvers is not trivial because each region can dynamically affect the others. Thus, dynamic simulation of grids with very large numbers of IBRs potentially poses a barrier to the ongoing energy transition.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2025

High‐Resolution National‐Scale Water Modeling Is Enhanced by Multiscale Differentiable Physics‐Informed Machine Learning

Abstract The National Water Model (NWM) is a key tool for flood forecasting, planning, and water management. Key challenges facing the NWM include calibration and parameter regionalization when confronted with big data. We present two novel versions of high‐resolution (∼37 km 2 ) differentiable models (a type of hybrid model): one with implicit, unit‐hydrograph‐style routing and another with explicit Muskingum‐Cunge routing in the river network. The former predicts streamflow at basin outlets whereas the latter presents a discretized product that seamlessly covers rivers in the conterminous United States (CONUS). Both versions use neural networks to provide a multiscale parameterization and process‐based equations to provide a structural backbone, which were trained simultaneously (“end‐to‐end”) on 2,807 basins across the CONUS and evaluated on 4,997 basins. Both versions show great potential to elevate future NWM performance for extensively calibrated as well as ungauged sites: the median daily Nash‐Sutcliffe efficiency of all 4,997 basins is improved to around 0.68 from 0.48 of NWM3.0. As they resolve spatial heterogeneity, both versions greatly improved simulations in the western CONUS and also in the Prairie Pothole Region, a long‐standing modeling challenge. The Muskingum‐Cunge version further improved performance for basins >10,000 km 2 . Overall, our results show how neural‐network‐based parameterizations can improve NWM performance for providing operational flood predictions while maintaining interpretability and multivariate outputs. The modeling system supports the Basic Model Interface (BMI), which allows seamless integration with the next‐generation NWM. We also provide a CONUS‐scale hydrologic data set for further evaluation and use.

Song, Yalan [Civil and Environmental Engineering T↗