Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Scientific Machine 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.

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

At least 505 records · Page 28

28 NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning: Preprint

Integrating cloud services into advanced computing facilities provides significant new capabilities over focusing solely on traditional high performance computing (HPC) workloads. This brings complementary capabilities as well as enabling new focused roles for HPC. They are especially potent for workflows that fuse data streams, modeling and simulation ('modsim') and machine learning. A key challenge to adopting a hybrid edge-cloud-HPC model is to align optimal capability, data, and user intent on the right resources for each step in a workflow.?The NREL Stratus service provides a basis for this: Stratus layers capabilities needed to make?cloud services accessible to a lab-based scientific community on commercial offerings, and; currently supports upwards of 200 projects ranging from IOT integration to traditional modeling and simulation. This provides a real-world inventory of scientific workflow elements. A growing knowledge base enables placing these elements appropriately between the edge, cloud, and traditional HPC. This paper outlines a vision via reference architecture and the application of that architecture in a typical workflow highlighting multiple components: sensor data intake, cleaning and transforming (edge/cloud suitable); generation of synthetic data through modsim, computationally heavy ML training and hyperparameter optimization (HPC suitable), and; inference and deployment (cloud ideal). Every step in such a workflow involves a cost-benefit analysis regarding the data movement, computational efficiency, availability, latency, and resource capabilities. The reference architecture and examples outlined allow for understanding new opportunities in the context of emerging workflows that combine IOT, cloud, and HPC to bolster scientific productivity.

AI↗

DGaaS: GPU as a Service on Distributed Computing System

In the rapidly evolving landscape of scientific computing, Graphics Processing Units (GPUs) have become indispensable for their unparalleled ability to handle parallel tasks in complex calculations, simulations, and data analysis. Their utility is further magnified in machine learning and AI applications, where they significantly accelerate model training and predictive analytics. Within this context, the Triton Inference Server emerges as a pivotal open-source tool, specializing in AI inferencing and optimizing GPU utilization across various platforms and frameworks. This paper presents an in-depth study on distributed High Throughput Computing (HTC), specifically focusing on the HTCondor framework and its resource provisioning tools, GlideinWMS and HEPCloud. These systems enable large-scale scientific experiments like CMS and DUNE to efficiently access and utilize vast computational resources. The paper explores the core architectural components of GlideinWMS, including jobs, user pools, and worker nodes, and discusses their integration with GPUs and the Triton server. The primary aim of this research is to develop a solution that optimizes GPU utilization by leveraging Glideins and containers. This approach allows computational jobs, particularly those involving AI models, to use GPUs only when essential, thereby facilitating efficient sharing of limited GPU resources. To validate this architecture, the study conducted three key tests involving custom scripts, container-based servers, and Triton server deployments. However, the study faces challenges, notably in locating the Triton server and ensuring secure remote access. To address these issues, future work will focus on developing a proxy mechanism and enhancing security protocols. In conclusion, this study offers a comprehensive roadmap for effective and efficient GPU utilization in distributed High Throughput Computing. It aims to contribute significantly to the scientific community by solving pressing problems and implementing robust solutions in collaboration with the GlideinWMS and HEPCloud teams. The research sets the stage for a more efficient, scalable, and cost-effective paradigm in scientific computing.

97 MATHEMATICS AND COMPUTING↗

OPEN-Augmented Reality GUI for Bioenergy Crop Phenotyping and Precision Agriculture (Donald Danforth Plant Science Center Final Scientific Technical Report)

The project led by the Donald Danforth Plant Science Center, in collaboration with Arizona State University, George Washington University, and Saint Louis University, has made significant strides in advancing the phenotypic analysis of bioenergy crops through the development of an innovative AI processing pipeline. This initiative was primarily funded by ARPA-E, with additional cost-sharing provided by the participating institutions. The project successfully utilized a variety of sensors—3D scanners, thermal, RGB, and hyperspectral—to refine algorithms for data-driven trait signature identification and improve the classification and visualization of plant traits. The developed AI processing pipeline is capable of handling the complex, multidimensional data characteristic of dynamic agricultural environments. 1) Contributions to understanding: The research has advanced the field of plant phenomics by showcasing the synergistic use of various sensor data to enhance the precision of trait analysis in bioenergy crops. Through the integration of 3D scanners, thermal, RGB, and hyperspectral sensors, the project has developed robust data-driven trait signature algorithms and visualization techniques. These innovations have facilitated detailed monitoring and management of plant traits, providing vital insights into plant growth dynamics and stress responses. Further, the project has broadened our understanding of how machine learning can be effectively applied in multi-sensor environments to refine trait analysis. By leveraging diverse datasets, the research has not only improved the accuracy of phenotypic assessments but also established a versatile methodological framework that can be extended beyond agriculture to other fields requiring detailed phenotypic analysis. 2) Technical effectiveness and economic feasibility: The AI processing pipeline developed in this project demonstrated significant technical effectiveness, achieving high throughput analysis of extensive phenotypic data and meeting targeted accuracies. This system exemplified the capability of advanced machine learning technologies to efficiently manage and analyze large, complex datasets. Economically, the implementation of the project-developed pipelines may offer substantial cost savings across multiple sectors. It enhances data analysis processes and significantly reduces the need for manual data interpretation, thereby decreasing both the time and resources required. 3) Public benefit: The project has significantly broadened the scope of agricultural methodologies to enhance phenotypic analysis, with potential applications in various sectors beyond agriculture. Additionally, the initiative fostered an enriching educational and collaborative environment, significantly enhancing the technical skills of participants. It also made substantial contributions to the scientific community by providing open-access data sets and tools, encouraging ongoing research and development across various disciplines. Overall, the project not only met its scientific goals but also showcased the extensive utility of integrating advanced machine learning and sensor data analysis technologies. These advancements have proven instrumental in driving forward both theoretical research and practical applications, setting a strong foundation for future explorations and innovations in data-driven science.

60 APPLIED LIFE SCIENCES↗

Machine Detection of Enhanced Electromechanical Energy Conversion in PbZr 0.2 Ti 0.8 O 3 Thin Films

Many energy conversion, sensing, and microelectronic applications based on ferroic materials are determined by the domain structure evolution under applied stimuli. New hyperspectral, multidimensional spectroscopic techniques now probe dynamic responses at relevant length and time scales to provide an understanding of how these nanoscale domain structures impact macroscopic properties. Such approaches, however, remain limited in use because of the difficulties that exist in extracting and visualizing scientific insights from these complex datasets. Using multidimensional band-excitation scanning probe spectroscopy and adapting tools from both computer vision and machine learning, an automated workflow is developed to featurize, detect, and classify signatures of ferroelectric/ferroelastic switching processes in complex ferroelectric domain structures. This approach enables the identification and nanoscale visualization of varied modes of response and a pathway to statistically meaningful quantification of the differences between those modes. Lastly, among other things, the importance of domain geometry is spatially visualized for enhancing nanoscale electromechanical energy conversion.

36 MATERIALS SCIENCE↗

New approaches to Bayesian uncertainty quantification for Nuclear Science (Final Technical Report)

Inverse problems play a central role in experimentation and theory/data comparisons for many areas of modern Nuclear Physics (NP) and High-Energy Physics (HEP). Bayes’s Theorem is a powerful tool for solving Inverse Problems, providing conceptually transparent and unbiased constraints on theoretical parameters and their uncertainties (“Bayesian Inference”) and enabling the quantification of agreement or tension between models and data. However, analyses based on Bayesian Inference are often challenging for NP and HEP applications, either because of the large number of parameters in the problem, the high computational cost, or both. We propose a multi-institutional collaboration to develop and deploy novel Bayesian analysis tools that advance the scientific scope of a broad range of current and future NP experiments. This project brings together NP domain scientists working on several high-profile NP projects for which new, high-performance Bayesian Uncertainty Quantification (“Bayesian UQ”) methods are essential to carry out the science, and data scientists who are developing state-of-the-art methods applicable to these problems. The NP projects in this proposal comprise measurements of the mass and fundamental nature of the neutrino; study of the Quark-Gluon Plasma that filled the early universe; and mapping of natural and anthropogenic radiation environments. While these NP projects have very different scientific goals, with datasets and analysis approaches that differ significantly, they share common requirements for improving computationally intensive Bayesian analyses using advanced Machine Learning algorithms and will benefit strongly from a coherent effort to develop general solutions. This proposal brings together these projects and forefront ML-based data science algorithms to develop such general solutions. The methods developed in this project will also be more widely applicable, thereby advancing science in the larger Nuclear Physics portfolio.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Machine Learning Techniques for Pile-Up Rejection in Cryogenic Calorimeters

CUORE Upgrade with Particle IDentification (CUPID) is a foreseen ton-scale array of Li 2 MoO 4 (LMO) cryogenic calorimeters with double readout of heat and light signals. Its scientific goal is to fully explore the inverted hierarchy of neutrino masses in the search for neutrinoless double beta decay of 100 Mo. Pile-up of standard double beta decay of the candidate isotope is a relevant background. We generate pile-up heat events via injection of Joule heater pulses with a programmable waveform generator in a small array of LMO crystals operated underground in the Laboratori Nazionali del Gran Sasso, Italy. This allows to label pile-up pulses and control both time difference and underlying amplitudes of individual heat pulses in the data. We present the performance of supervised learning classifiers on data and the attained pile-up rejection efficiency.

47 OTHER INSTRUMENTATION↗

Bayesian experimental design and parameter estimation for ultrafast spin dynamics

Abstract Advanced experimental measurements are crucial for driving theoretical developments and unveiling novel phenomena in condensed matter and materials physics, which often suffer from the scarcity of large-scale facility resources, such as x-ray or neutron scattering centers. To address these limitations, we introduce a methodology that leverages the Bayesian optimal experimental design paradigm to efficiently uncover key quantum spin fluctuation parameters from x-ray photon fluctuation spectroscopy (XPFS) data. Our method is compatible with existing theoretical simulation pipelines and can also be used in combination with fast machine learning surrogate models in the event that real-time simulations are unfeasible. Our numerical benchmarks demonstrate the superior performance in predicting model parameters and in delivering more informative measurements within limited experimental time. Our method can be adapted to many different types of experiments beyond XPFS and spin fluctuation studies, facilitating more efficient data collection and accelerating scientific discoveries.

97 MATHEMATICS AND COMPUTING↗

Bibliometric review and recent advances in total scattering pair distribution function analysis: 21 years in retrospect

Global research activities have been driven by the quest to develop and characterize novel materials for technological advancements. The total scattering pair distribution function (TSPDF) is a powerful and versatile characterization technique for examining the structural details of diverse complex materials including liquid, amorphous, disordered crystalline, and nanostructured materials. Thus, it is critical to keep track of research progress, identify research gaps, and future research directions of the application of the TSPDF technique in materials development and discovery. In this work, a bibliometric analysis of literature regarding the TSPDF technique between 2000 and 2021 was conducted using datasets retrieved from the Web of Science database. The research trends based on publication outputs, research subject distribution, co-authorships among institutions, countries/regions, co-citation of referenced sources, and keyword co-occurrence are evaluated and discussed herein. The impact of the TSPDF technique is projected to increase due to its importance in probing emerging functional materials, and the advances in specialized facilities and instrumentation among the scientific communities engaged with it. Finally, current and emerging research hotspots related to TSPDF technique such as catalysis, computer modeling and simulation, pharmaceutics, machine learning, hydrogen storage, battery materials, and layered structured materials are also identified and discussed.

36 MATERIALS SCIENCE↗

Dial

A key step in almost all scientific endeavors is answering the question: Given this data I already collected, what new data do I expect will yield the most useful information toward my scientific objective? The area of (sequential) experimental design has long been investigating answers to this question, but in recent years techniques from the machine learning subfield of active learning are increasingly applied. Researchers need a simple software tool for active learning applied to experimental design that can easily integrate into their existing workflows. This computer code, Dial, provides a microservice in ORNL's INTERSECT ecosystem for active learning applied to experimental design. By being part of the INTERSECT ecosystem, Dial is simple to integrate into any INTERSECT-based workflow. Dial provides multiple backend options, where a backend is an implementation of a specific active learning method. Users can select the backend that performs best for their application. Developers can also add new backends as needed. At its core, Dial receives a set of pre-existing measurements and input parameter bounds and then recommends one or more new sets of parameters to measure. Dial also includes interfaces to other microservices in the INTERSECT ecosystem so that it can be incorporated into INTERSECT campaigns. Dial provides a simple, yet powerful interface to convert automated INTERSECT workflows into autonomous workflows that adapt based on the results that are obtained. A shared microservice for active learning prevents duplicated effort by each application team implementing its own adaptive design of experiments tool.

Drane, Lance [Oak Ridge National Laboratory (ORNL)↗

Characterizing Machine Learning I/O Workloads on Leadership Scale HPC Systems

High performance computing (HPC) is no longer solely limited to traditional workloads such as simulation and modeling. With the increase in the popularity of machine learning (ML) and deep learning (DL) technologies, we are observing that an increasing number of HPC users are incorporating ML methods into their workflow and scientific discovery processes, across a wide spectrum of science domains such as biology, earth science, and physics. This gives rise to a diverse set of I/O patterns than the traditional checkpoint/restart-based HPC I/O behavior. The details of the I/O characteristics of such ML I/O workloads have not been studied extensively for large-scale leadership HPC systems. This paper aims to fill that gap by providing an in-depth analysis to gain an understanding of the I/O behavior of ML I/O workloads using darshan - an I/O characterization tool designed for lightweight tracing and profiling. We study the darshan logs of more than 23, 000 HPC ML I/O jobs over a time period of one year running on Summit - the second-fastest supercomputer in the world. This paper provides a systematic I/O characterization of ML I/O jobs running on a leadership scale supercomputer to understand how the I/O behavior differs across science domains and the scale of workloads, and analyze the usage of parallel file system and burst buffer by ML I/O workloads.

Paul, Arnab↗

Editorial: Predicting near-earth space environment: new perspective and capabilities in the AI age

Editorial on the Research Topic Predicting near-earth space environment: new perspective and capabilities in the AI age The near-Earth space environment is not only an operational hazard for space missions, but also a scientific laboratory for advancing our understanding and prediction of space plasma populations. This Research Topic is organized around three interconnected themes: observational datasets, machine-learning (ML) model development, and the discovery of new physical insights through those models. Its primary goal is to highlight the emerging capabilities in space environment prediction that are enabled, or will be enabled, by integrating advanced techniques—including AI/ML methods—with long-term curated datasets.

58 GEOSCIENCES↗

Developing a simulator-based satellite dataset for using machine learning techniques to derive aerosol-cloud-precipitation interactions in models and observations in a consistent framework

Aerosol-cloud-precipitation interactions (ACPI) remain a major uncertainty in understanding the Earth’s radiation budget and water cycle (including extremes). After decades of active research, various observationally based metrics have been developed to constrain ACPI in Earth System Models (ESMs), but direct comparison of model and data estimates can confound scientific understanding because limitations and uncertainties in sampling and retrieval procedures may combine with model deficiencies in process representations of ACPI to obstruct understanding. Furthermore, conventional ACPI metrics often vary from one regime to another, and the ACPI process representation in ESMs is also typically derived based on only a limited area/regime (even though the parameterization applies globally). To bridge the gap between models and data and to correctly describe ACPI in all regimes, we propose to construct a new CALIPSO-CloudSat merged dataset that is produced by the same algorithms used in satellite simulators in ESMs, and to use machine learning techniques to derive new ACPI metrics that can be accurately estimated by satellites and can provide meaningful constraints on cloud microphysical process representations in ESMs. The dataset will include measured and retrieved variables for aerosol, cloud, and precipitation from CALIPSO and CloudSat, and environmental variables from meteorological reanalysis. The data will be used to train a neural network to construct the ACPI metrics as a function of environmental conditions. The new ACPI formula will be used to constrain the ACPI in the Energy Exascale Earth System Model (E3SM), and to augment/reformulate the ACPI process representation in the E3SM to improve the simulation of the evolution of the atmosphere under different environmental conditions.

54 ENVIRONMENTAL SCIENCES↗

A Deep Look Into the Future of Quantitative Imaging in Oncology: A Statement of Working Principles and Proposal for Change

The adoption of enterprise digital imaging, along with the development of quantitative imaging methods and the re-emergence of statistical learning, has opened the opportunity for more personalized cancer treatments through transformative data science research. In the last 5 years, accumulating evidence has indicated that noninvasive advanced imaging analytics (i.e., radiomics) can reveal key components of tumor phenotype for multiple lesions at multiple time points over the course of treatment. Many groups using homegrown software have extracted engineered and deep quantitative features on 3-dimensional medical images for better spatial and longitudinal understanding of tumor biology and for the prediction of diverse outcomes. These developments could augment patient stratification and prognostication, buttressing emerging targeted therapeutic approaches. Unfortunately, the rapid growth in popularity of this immature scientific discipline has resulted in many early publications that miss key information or use underpowered patient data sets, without production of generalizable results. Quantitative imaging research is complex, and key principles should be followed to realize its full potential. The fields of quantitative imaging and radiomics in particular require a renewed focus on optimal study design and reporting practices, standardization, interpretability, data sharing, and clinical trials. Standardization of image acquisition, feature calculation, and statistical analysis (i.e., machine learning) are required for the field to move forward. A new data-sharing paradigm enacted among open and diverse participants (medical institutions, vendors and associations) should be embraced for faster development and comprehensive clinical validation of imaging biomarkers. In this review and critique of the field, we propose working principles and fundamental changes to the current scientific approach, with the goal of high-impact research and development of actionable prediction models that will yield more meaningful applications of precision cancer medicine.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Asynchronous Execution of Heterogeneous Tasks in ML-Driven HPC Workflows

Heterogeneous scientific workflows consist of numerous types of tasks that require execution on heterogeneous resources. Asynchronous execution of those tasks is crucial to improve resource utilization, task throughput and reduce workflows' makespan. Therefore, middleware capable of scheduling and executing different task types across heterogeneous resources must enable asynchronous execution of tasks. In this paper, we investigate the requirements and properties of the asynchronous task execution of machine learning (ML)-driven high-performance computing (HPC) workflows. We model the degree of asynchronicity permitted for arbitrary workflows and propose key metrics that can be used to determine qualitative benefits when employing asynchronous execution. Our experiments represent relevant scientific drivers, we perform them at scale on Summit, and we show that the performance enhancements due to asynchronous execution are consistent with our model.

97 MATHEMATICS AND COMPUTING↗

A Review of Recent and Emerging Machine Learning Applications for Climate Variability and Weather Phenomena

Abstract Climate variability and weather phenomena can cause extremes and pose significant risk to society and ecosystems, making continued advances in our physical understanding of such events of utmost importance for regional and global security. Advances in machine learning (ML) have been leveraged for applications in climate variability and weather, empowering scientists to approach questions using big data in new ways. Growing interest across the scientific community in these areas has motivated coordination between the physical and computer science disciplines to further advance the state of the science and tackle pressing challenges. During a recently held workshop that had participants across academia, private industry, and research laboratories, it became clear that a comprehensive review of recent and emerging ML applications for climate variability and weather phenomena that can cause extremes was needed. This article aims to fulfill this need by discussing recent advances, challenges, and research priorities in the following topics: sources of predictability for modes of climate variability, feature detection, extreme weather and climate prediction and precursors, observation–model integration, downscaling, and bias correction. This article provides a review for domain scientists seeking to incorporate ML into their research. It also provides a review for those with some ML experience seeking to broaden their knowledge of ML applications for climate variability and weather.

54 ENVIRONMENTAL SCIENCES↗

Active anomaly detection for time-domain discoveries

Aims. We present the first evidence that adaptive learning techniques can boost the discovery of unusual objects within astronomical light curve data sets. Methods. Our method follows an active learning strategy where the learning algorithm chooses objects which can potentially improve the learner if additional information about them is provided. This new information is subsequently used to update the machine learning model, allowing its accuracy to evolve with each new information. For the case of anomaly detection, the algorithm aims to maximize the number of scientifically interesting anomalies presented to the expert by slightly modifying the weights of a traditional Isolation Forest (IF) at each iteration. In order to demonstrate the potential of such techniques, we apply the Active Anomaly Discovery (AAD) algorithm to 2 data sets: simulated light curves from the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC) and real light curves from the Open Supernova Catalog. We compare the AAD results to those of a static IF. For both methods, we performed a detailed analysis for all objects with the ~2% highest anomaly scores. Results. We show that, in the real data scenario , AAD was able to identify ~80% more true anomalies than the IF. This result is the first evidence that AAD algorithms can play a central role in the search for new physics in the era of large scale sky surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

Building the I (Interoperability) of FAIR for performance reproducibility of large-scale composable workflows in RECUP

Abstract-Scientific computing communities increasingly run their experiments using complex data- and compute-intensive workflows that utilize distributed and heterogeneous architectures targeting numerical simulations and machine learning, often executed on the Department of Energy Leadership Computing Facilities (LCFs). We argue that a principled, systematic approach to implementing FAIR principles at scale, including fine-grained metadata extraction and organization, can help with the numerous challenges to performance reproducibility posed by such workflows. We extract workflow patterns, propose a set of tools to manage the entire life cycle of performance metadata, and aggregate them in an HPC-ready framework for reproducibility (RECUP). We describe the challenges in making these tools interoperable, preliminary work, and lessons learned from this experiment.

97 MATHEMATICS AND COMPUTING↗

Strategies for Integrating Deep Learning Surrogate Models with HPC Simulation Applications

The emerging trend of the convergence of high performance computing (HPC), machine learning/deep learning (ML/DL), and big data analytics presents a host of challenges for large-scale computing campaigns that seek best practices to interleave traditional scientific simulation-based workloads with ML/DL models. A portfolio of systematic approaches to incorporate deep learning into modeling and simulation serves a vital need when we support AI for science at a computing facility. In this paper, we evaluate several strategies for deploying deep learning surrogate models in a representative physics application on supercomputers at the Oak Ridge Leadership Computing Facility (OLCF). We discuss a set of recommended deployment architectures and implementation approaches. We analyze and evaluate these alternatives and show their performance and scalability up to 1000 GPUs on two mainstream platforms equipped with different deep learning hardware and software stacks.

Yin, Junqi↗