SEARCH · Engineering Papers
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.
SF-25-081 Utility software for creating high-performance data pipelines to extract, load, and transform raw electric power systems measurements. For use with anomaly detection models training workflows. The software supports the project: Adaptive Cybersecurity for DER: A Game-Theoretic and Machine Learning approach for Real-Time Threat Detection and Mitigation
During my internship at Lawrence Livermore National Laboratory, I contributed to the xPuSL project. The xPuSL project aimed to revolutionize multi-material 3D printing by combining DIW and PuSL techniques to produce complex geometries with functional materials. My role encompassed process engineering, control systems, experimentation, and CAD design, leading to a streamlined workflow from CAD models to xPuSL prints.
The organization of genomic DNA into chromatin is a fundamental determinant of genome stability, regulation, and cellular function. Nucleosomes, the basic repeating units of chromatin, assemble into higher-order structures whose organization and heterogeneity remain difficult to characterize using conventional ensemble-averaged techniques. A key need in the field is the development of experimental approaches capable of directly visualizing nucleosome assemblies and their structural variability at the single-molecule level. This LDRD Lab-Wide project focused on establishing and evaluating atomic force microscopy (AFM)–based approaches for the characterization of nucleosome assemblies. The work emphasized experimental workflows for preparing, imaging, and assessing multi-nucleosome systems, rather than isolated single nucleosomes. Through method development and exploratory measurements, the project demonstrated the feasibility of applying scanning probe microscopy to investigate chromatin-relevant assemblies and provided preliminary insight into the strengths and limitations of this approach for future quantitative studies. Results and lessons learned from this effort were disseminated to the broader scientific community through multiple national conference presentations, helping to position LLNL for continued work in chromatin and genome organization research.
Growing demands to understand PV deployment and reliability across an expanding range of climates, along with increasing computational power, are driving the need for simplified computing tools that support large-scale analysis and geospatial workflows. While existing open-source libraries and PV system modeling tools offer extensive collections of empirical and physical models, they often lack the ability to scale to large geospatial datasets. The tool presented here, GeoGridFusion, enables PV modelers to store and utilize gridded geospatial data from sources such as NSRDB, PVGIS, and others. GeoGridFusion harmonizes diverse datasets, taxonomies, and nomenclatures, and includes utilities that support intuitive geospatial area selection.
Lattice gauge theory research, with its computationally intensive simulations and complex multi‑stage workflows, is well positioned to benefit from agentic AI systems. We demonstrate how such tools can support key components of lattice gauge theory research, including novel simulation code development using standard LQCD frameworks, HPC job orchestration, simulation data analysis, and expert‑guided tuning of algorithmic parameters such as Hasenbusch mass preconditioning and multigrid solvers. Our results show that agentic AI can reduce manual effort, improve productivity, and accelerate the research cycle while maintaining essential human oversight.
In many university and healthcare projects, models are built for very different data types such as tables, institutional time series, and medical images, but they are deployed as separate applications. In this work, that separation made testing and maintenance difficult because each module had its own pipeline and runtime requirements. This paper presents an integrated AI lakehouse-style implementation that runs three model pipelines inside one containerized backend. For medical imaging, we used MRI datasets from IEEE DataPort: a four-class classification set with 7012 images (5708 train/1304 test) and a segmentation set with 3063 image–mask pairs. The classification model (ResNet50 transfer learning) is evaluated using a proper train–validation–test protocol across multiple splits (80/10/10, 70/10/20, 60/10/30, and 10/30/60), achieving a test accuracy of 99.00% under the standard 80/10/10 split. Additionally, a patient-level evaluation is conducted using an external glioma dataset to provide a more realistic assessment without data leakage. The segmentation model (DeepLabV3-ResNet50) achieved 83.09% validation mIoU and 88.79% Dice score. For university KPI forecasting, we used annual IPEDS and NSF HERD data from 2010 to 2023 for three universities (BSU, EOU, and UAB). To examine the effect of preprocessing on forecasting performance, two case studies are conducted. In the first case, linear interpolation is applied to generate semester-level data. In the second case, the original annual data is used directly without interpolation. Random Forest regression and ARIMA models are evaluated using MAE, RMSE, MAPE, and R 2 . The results showed that interpolation improved apparent forecasting performance due to smoothing, while evaluation on the original annual data provided a more realistic assessment of model behavior. To further validate the framework on a larger dataset, an additional case study is conducted using a student dropout dataset. For water potability, we trained and compared multiple tabular classifiers on a large dataset (1,048,575 samples). A Random Forest model (100 trees, max depth 10) achieved 85.86% test accuracy and high recall for unsafe samples (0.8447). All modules are served via FastAPI and deployed together using Docker, with workflow automation routing requests to the correct endpoint. System-level benchmarking indicates that the backend maintains stable throughput and latency under concurrent requests.
Modern large-scale scientific discovery requires multidisciplinary collaboration across diverse computing facilities, including High Performance Computing (HPC) machines and the Edge-to-Cloud continuum. Integrated data analysis plays a crucial role in scientific discovery, especially in the current AI era, by enabling Responsible AI development, FAIR, Reproducibility, and User Steering. However, the heterogeneous nature of science poses challenges such as dealing with multiple supporting tools, cross-facility environments, and efficient HPC execution. Building on data observability, adapter system design, and provenance, we propose MIDA: an approach for lightweight runtime Multi-workflow Integrated Data Analysis. MIDA defines data observability strategies and adaptability methods for various parallel systems and machine learning tools. With observability, it intercepts the dataflows in the background without requiring instrumentation while integrating domain, provenance, and telemetry data at runtime into a unified database ready for user steering queries. We conduct experiments showing end-to-end multi-workflow analysis integrating data from Dask and MLFlow in a real distributed deep learning use case for materials science that runs on multiple environments with up to 276 GPUs in parallel. We show near-zero overhead running up to 100,000 tasks on 1,680 CPU cores on the Summit supercomputer.
Creating Apptainer Workflows with Docker-Compose-like Utilities In this presentation, I will explore the utilization of a tool called process-compose, inspired by docker-compose, to create Apptainer-based services. This approach allows for easy deployment and management of fully containerized applications on High Performance Computing (HPC) systems without requiring elevated privileges. Benefits to the Ecosystem: By incorporating process-compose and Apptainer, I aim to address several key challenges in the HPC ecosystem: Simplified Workflow Management: Process-compose provides a user-friendly interface for defining and managing complex containerized application services, reducing the setup time and lowering the barrier to entry for new users. Enhanced Portability: Apptainer ensures that containerized applications can run consistently across different HPC environments, promoting greater portability and reducing compatibility issues. Process-compose is also a single binary that does not need to be installed by admin level users. Community Driven Solutions: This approach aligns with the goals of the High Performance Software Foundation (HPSF) to advance community-driven solutions. By sharing our experiences and insights, I hope to foster collaboration and innovation within the HPC community. Increased Productivity: The combination of process-compose and Apptainer streamlines the serve deployment process, allowing researchers and developers to focus more on their scientific work rather than the intricacies of system or service administration. Through this presentation, attendees will gain valuable insights into the practical implementation of containerized workflows on HPC systems, learn about the benefits of using process-compose and Apptainer, and understand how these tools can contribute to a more efficient HPC ecosystem.
The ESnet-JLab FPGA Accelerated Transport system is a solution for streaming high-speed scientific measurement data from Data Acquisition Systems (DAQs) to high-performance computing facilties. It is generally compatible with many science workflows, and makes no assumptions about the specifics of any particular experiment. This program (udplbd version 2) implements the control plane for the system. It is responsible for programming network forwarding rules into the data plane (implemented by the hardware designed named udplb, described separately). It also implements the control loop necessary to match up offered workload with available capacity on high-performance compute nodes.
Kessel is a tool to create and drive continuous integration (CI) and developer workflows through a unified interface across multiple code projects and environments. It serves as a driver and integration layer for build systems and package managers, providing a flexible library of reusable components to build and execute complex workflows consistently.
The hardware landscape used in HEP and NP is changing from homogeneous multi-core systems towards heterogeneous systems with many different computing units, each with their own characteristics. To achieve maximum performance with data processing, the main challenge is to place the right computing on the right hardware. In this paper, we discuss CLAS12 charge particle tracking workflow orchestration that allows us to utilize both CPU and GPU to improve the performance. The tracking application algorithm was decomposed into micro-services that are deployed on CPU and GPU processing units, where the best features of both are intelligently combined to achieve maximum performance. In this heterogeneous environment, CLARA aims to match the requirements of each micro-service to the strength of a CPU or a GPU architecture. A predefined execution of a micro-service on a CPU or a GPU may not be the most optimal solution due to the streaming data-quantum size and the data-quantum transfer latency between CPU and GPU. So, the CLARA workflow orchestrator is designed to dynamically assign micro-service execution to a CPU or a GPU, based on the online benchmark results analyzed for a period of real-time data-processing.
Next generation of science workflows are expected to be executed over complex federations composed of supercomputers, science instruments, storage systems and networks, with new additions of the edge and cloud systems and services. The sheer complexity of these multi-domain federations makes it hard to manage them and optimize their performance, as small impedance mismatches (that can dynamically develop between systems) could drastically degrade the entire federation performance. Recent proliferation of Software Defined Everything (SDX) technologies combined with containerization frameworks provide custom instruments that can monitor and collect critical measurements at various levels to support diagnoses and performance optimization; but their data too enormous for human operators and analysts to process and generate decisions. Machine Learning (ML) methods that extract critical parameters, relationships and trends from the data offer general solutions. Artificial Intelligence (AI) and ML methods must be custom-developed for these problems based on solid, rigorous foundations, since black-box approaches are often ineffective and unsound.We propose to develop comprehensive AI-Science for the performance of science federations to (i) monitor and control storage, networks, experiments, and computing systems across multiple domains via softwarization layers, at speeds and scales orders of magnitude superior to current practice, (ii) optimally realize and orchestrate complex workflows with high performance by using dynamic state and performance estimation methods, and (iii) aggregate measurements across sites and time to develop infrastructure-level profiles, optimizations and diagnoses using AI-Science based on foundational principles from ML, game theory, and information fusion areas.
This proposal addresses a critical issue of performance prediction identified in the report from the ASCR \Computational Modeling of Big Networks (COMBINE)" workshop: "end-to-end performance is not predictable due to a variety of factors. Even when some performance forecasts or predictions can be made, they often cannot explain the reasons why some predictions fail." We will develop new analytical models to predict the end-to-end performance of scientific workflows on DOE computing infrastructures, and use simulations and experimentation to validate and refine these models, as well as to pinpoint the sources of model inaccuracy. We will also use these models to help diagnose application and infrastructure problems, and to adapt the system based on this diagnosis. This section provides background in the areas relevant to the proposed work. RPI’s specific tasks within the Panorama project are as follows: (1) Develop Aspen-Simulation interface for Workflow Model Driven Simulation. (2) Validate manual performance models of two target workflow scenarios with empirical measurement and simulation. (3) Extend ROSS-Aspen API to simulate workflow descriptions when required. (4) Validate Aspen performance models of two target workflow scenarios with automatic performance model empirical measurement and simulation. (5) Design and implement final system to automatically generate Aspen performance models from workflow descriptions (including methods to compensate for limitations of Aspen analytical models). (6) Validate improved Aspen performance models with target workflow on production infrastructure. To date, all the project milestones assigned to us where reached within the best of our abilities over the course of the project performance period. Below describes the key outcome from our collaborative research in a system named, Durango .
This presentation discusses the development of a Nearly Autonomous Management and Control (NAMAC) system for advanced reactors. This presentation first introduces the NAMAC-enabled plant control. Next, this presentation introduces major technologies of implementing NAMAC, including operational workflow, digital twin, and advanced machine learning algorithms. To demonstrate the capability of the NAMAC system, NAMAC is connected with a simulator of the Experimental Breeder Reactor II, where NAMAC is activated to provide recommendations during a single loss of flow accident.
Fusion energy experiments and simulations provide critical information needed to plan future fusion reactors. As next-generation devices like ITER move toward long-pulse experiments, analyses, including AI and ML, should be performed in a wide range of time and computing constraints, from near-real-time constraints, between-shot analysis, and to campaign-wide long-term analysis. However, the data volume, velocity, and variety make it extremely challenging for analyses using only local computational resources. Researchers need the ability to compose and execute workflows spanning edge resources to large-scale high-performance computing facilities.We present Delta, a system to address data analysis challenges, including AI/ML, in fusion science, by leveraging the ADIOS I/O library and middleware, to support executing science workflows over the wide area network for near-real-time streaming. We discuss the data federation challenges in performing remote workflows, focusing on on-going research work in (1) managing, reducing, and streaming data to minimize I/O and data movement overheads, (2) decompressing and reorganizing data for analysis, and (3) executing workflows for automated data analysis. We introduce examples for deep-learning based data analysis for the fusion domain and demonstrate how we use Delta to construct end-to-end workflows for a fusion device in Korea, connecting a remote DOE facility in the USA. The capability demonstrated by this project is the basis for improving the state of the art for near-real-time data federation amongst remote facilities.
Full integration of building energy modelling into the design and retrofit process has long been a goal of building scientists and practitioners. However, significant barriers still exist. Among them are the lack of available: (1) configurable technology stacks for performing both small- and large-scale analyses, (2) different classes of algorithms compatible with common design workflows, and (3) analysis tools for effectively visualizing large-scale simulation results. This article discusses the OpenStudio® Analysis Framework: a scalable analysis framework for building energy modelling that was developed to overcome the three barriers listed above. The framework is open-source and scalable to facilitate wider adoption and has a clearly defined application programming interface upon which other applications can be built. It runs on high-performance computing systems, within cloud infrastructure, and on laptops, and uses a common workflow to enable different classes of algorithms. Lessons learned from previous development efforts are also discussed.
Directed evolution is a powerful method to optimize proteins and metabolic reactions towards user-defined goals. It usually involves subjecting genes or pathways to iterative rounds of mutagenesis, selection and amplification. While powerful, systematic searches through large sequence-spaces is a labour-intensive task, and can be further limited by a priori knowledge about the optimal initial search space, and/or limits in terms of screening throughput. Here, we demonstrate an integrated directed evolution workflow for metabolic pathway enzymes that continuously generate enzyme variants using the recently developed orthogonal replication system, OrthoRep and screens for optimal performance in high-throughput using a transcription factor-based biosensor. We demonstrate the strengths of this workflow by evolving a rate-limiting enzymatic reaction of the biosynthetic pathway for cis,cis-muconic acid (CCM), a precursor used for bioplastic and coatings, in Saccharomyces cerevisiae. After two weeks of simply iterating between passaging of cells to generate variant enzymes via OrthoRep and high-throughput sorting of best-performing variants using a transcription factor-based biosensor for CCM, we ultimately identified variant enzymes improving CCM titers > 13-fold compared with reference enzymes. Taken together, the combination of synthetic biology tools as adopted in this study is an efficient approach to debottleneck repetitive workflows associated with directed evolution of metabolic enzymes.
Today’s connected lighting systems have the potential to reduce energy consumption and operational costs via the use of the data they collect and share with other building systems (e.g., HVAC, building automation, security). However, many market available products are new to being networked, and when networked components in lighting and other building systems are not sufficiently secured, they present opportunities for criminals to exploit. Further, security vulnerabilities in one system can be used as lateral steppingstones that allow access to other prized assets on the same network. These cybersecurity concerns could deter the adoption and use of connected systems, which then could jeopardize long-term national objectives for reduced energy usage. The workflows described here and presented in more detail in the referenced reports are examples of how these frameworks and tools can be put to practical use during system design and specification.