Search NASA⌕ Search

Engineering topics

Yoo, Shinjae

Publications and source records attributed to Yoo, Shinjae.

At least 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Use of Physics to Improve Solar Forecast: Physics-Informed Persistence Models for Simultaneously Forecasting GHI, DNI, and DHI

Observation-based statistical models have been widely used in forecasting solar energy; however, existing models often lack a clear relation to physics and are limited largely to global horizontal irradiance (GHI) forecasts over relatively short time horizons (< 1 hour). Incorporating physics into observation-based models, increasing forecast time horizons and developing a model system for forecasting not only GHI but also direct normal irradiance (DNI) and diffuse horizontal irradiance (DHI) remain challenging, especially under cloudy conditions because of complex cloud-radiation interactions. This work attempts to address these challenges by developing a hierarchy of four new physics-informed persistence models that can be used to simultaneously forecast GHI, DNI and DHI. The decade-long measurements (1998 to 2014) at the U.S. Department of Energy's Atmospheric Radiation Measurement (ARM)'s Southern Great Plains (SGP) Central Facility site are used to evaluate the performance of the new models. Overall, the results show that the new physics-informed forecast models generally outperform the simple and smart persistence models, and improve the forecast accuracy at lead times from 1.25 hours up to 6 hours. Further analysis reveals that the forecast error is highly related to the error and temporal variability of the assumed cloud predictor. The best model for forecasting different radiative components can be explained by the relationship between solar irradiances and cloud properties.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

In situ compression artifact removal in scientific data using deep transfer learning and experience replay

The massive amount of data produced during simulation on high-performance computers has grown exponentially over the past decade, exacerbating the need for streaming compression and decompression methods for efficient storage and transfer of this data---key to realizing the full potential of large-scale computational science. Lossy compression approaches such as JPEG when applied to scientific simulation data realized as a stream of images can achieve good compression rates but at the cost of introducing compression artifacts and loss of information. This paper develops a unified framework for in situ compression artifact removal in which the fully convolutional neural network architectures are combined with scalable training, transfer learning, and experience replay to achieve superior accuracy and efficiency while significantly decreasing the storage footprint as compared with the traditional optimization-based approaches. We demonstrate the proposed approach and compare it with compressed sensing postprocessing and other baseline deep learning models using climate simulations and nuclear reactor simulations, both of which are driven by hyperbolic partial differential equations. Our approach when applied to remove the compression artifacts on the JPEG-compressed nuclear reactor simulation data (using a transfer-trained model that was pretrained on the climate simulation data and updated incrementally as the nuclear reactor simulation progressed), achieved a significant improvement---mean peak signal-to-noise ratio of 42.438 as compared with 27.725 obtained with the compressed sensing approach.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Supercomputer-Based Ensemble Docking Drug Discovery Pipeline with Application to Covid-19

In this work, we present a supercomputer-driven pipeline for in silico drug discovery using enhanced sampling molecular dynamics (MD) and ensemble docking. Ensemble docking makes use of MD results by docking compound databases into representative protein binding-site conformations, thus taking into account the dynamic properties of the binding sites. We also describe preliminary results obtained for 24 systems involving eight proteins of the proteome of SARS-CoV-2. The MD involves temperature replica exchange enhanced sampling, making use of massively parallel supercomputing to quickly sample the configurational space of protein drug targets. Using the Summit supercomputer at the Oak Ridge National Laboratory, more than 1 ms of enhanced sampling MD can be generated per day. We have ensemble docked repurposing databases to 10 configurations of each of the 24 SARS-CoV-2 systems using AutoDock Vina. Comparison to experiment demonstrates remarkably high hit rates for the top scoring tranches of compounds identified by our ensemble approach. We also demonstrate that, using Autodock-GPU on Summit, it is possible to perform exhaustive docking of one billion compounds in under 24 h. Finally, we discuss preliminary results and planned improvements to the pipeline, including the use of quantum mechanical (QM), machine learning, and artificial intelligence (AI) methods to cluster MD trajectories and rescore docking poses.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Chimbuko: A Workflow-Level Scalable Performance Trace Analysis Tool

Due to the sheer volume of data it is typically impractical to analyze the detailed performance of an HPC application running at-scale. While conventional small-scale benchmarking and scaling studies are often sufficient for simple applications, many modern workflow-based applications couple multiple elements with competing resource demands and complex inter-communication patterns for which performance cannot easily be studied in isolation and at small scale. This work discusses Chimbuko, a performance analysis framework that provides real-time, in situ anomaly detection. By focusing specifically on performance anomalies and their origin (aka provenance), data volumes are dramatically reduced without losing necessary details. To the best of our knowledge, Chimbuko is the first online, distributed, and scalable workflow-level performance trace analysis framework. We demonstrate the tool's usefulness on Oak Ridge National Laboratory's Summit system.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Chimbuko: A Workflow-Level Scalable Performance Trace Analysis Tool

ABSTRACT Due to the sheer volume of data it is typically impractical to analyze the detailed performance of an HPC application running at-scale. While conventional small-scale benchmarking and scaling studies are often sufficient for simple applications, many modern workflow-based applications couple multiple elements with competing resource demands and complex inter-communication patterns for which performance cannot easily be studied in isolation and at small scale. This work discusses Chimbuko, a performance analysis framework that provides real-time, in situ anomaly detection. By focusing specifically on performance anomalies and their origin (aka provenance), data volumes are dramatically reduced without losing necessary details. To the best of our knowledge, Chimbuko is the first online, distributed, and scalable workflow-level performance trace analysis framework. We demonstrate the tool's usefulness on Oak Ridge National Laboratory's Summit system.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Image Collection Simulation Using High-Resolution Atmospheric Modeling

A new method is described for simulating the passive remote sensing image collection of ground targets that includes effects from atmospheric physics and dynamics at fine spatial and temporal scales. The innovation in this research is the process of combining a high-resolution weather model with image collection simulation to attempt to account for heterogeneous and high-resolution atmospheric effects on image products. The atmosphere was modeled on a 3D voxel grid by a Large-Eddy Simulation (LES) driven by forcing data constrained by local ground-based and air-based observations. The spatial scale of the atmospheric model (10–100 m) came closer than conventional weather forecast scales (10–100 km) to approaching the scale of typical commercial multispectral imagery (2 m). This approach was demonstrated through a ground truth experiment conducted at the Department of Energy Atmospheric Radiation Measurement Southern Great Plains site. In this experiment, calibrated targets (colored spectral tarps) were placed on the ground, and the scene was imaged with WorldView-3 multispectral imagery at a resolution enabling the tarps to be visible in at least 9–12 image pixels. The image collection was simulated with Digital Imaging and Remote Sensing Image Generation (DIRSIG) software, using the 3D atmosphere from the LES model to generate a high-resolution cloud mask. The high-resolution atmospheric model-predicted cloud coverage was usually within 23% of the measured cloud cover. The simulated image products were comparable to the WorldView-3 satellite imagery in terms of the variations of cloud distributions and spectral properties of the ground targets in clear-sky regions, suggesting the potential utility of the proposed modeling framework in improving simulation capabilities, as well as testing and improving the operation of image collection processes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Machine-Learning X-Ray Absorption Spectra to Quantitative Accuracy

Simulations of excited state properties, such as spectral functions, are often computationally expensive and therefore not suitable for high-throughput modeling. As a proof of principle, here we demonstrate that graph-based neural networks can be used to predict the x-ray absorption near-edge structure spectra of molecules to quantitative accuracy. Specifically, the predicted spectra reproduce nearly all prominent peaks, with 90% of the predicted peak locations within 1 eV of the ground truth. Besides its own utility in spectral analysis and structure inference, our method can be combined with structure search algorithms to enable high-throughput spectrum sampling of the vast material configuration space, which opens up new pathways to material design and discovery.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

ECP Report: Update on Proxy Applications and Vendor Interactions

The ExaLearn miniGAN team (Ellis and Rajamanickam) have released miniGAN, a generative adversarial network(GAN) proxy application, through the ECP proxy application suite. miniGAN is the first machine learning proxy application in the suite (note: the ECP CANDLE project did previously release some benchmarks) and models the performance for training generator and discriminator networks. The GAN's generator and discriminator generate plausible 2D/3D maps and identify fake maps, respectively. miniGAN aims to be a proxy application for related applications in cosmology (CosmoFlow, ExaGAN) and wind energy (ExaWind). miniGAN has been developed so that optimized mathematical kernels (e.g., kernels provided by Kokkos Kernels) can be plugged into to the proxy application to explore potential performance improvements. miniGAN has been released as open source software and is available through the ECP proxy application website (https://proxyapps.exascaleproject.ordecp-proxy-appssuite/) and on GitHub (https://github.com/SandiaMLMiniApps/miniGAN). As part of this release, a generator is provided to generate a data set (series of images) that are inputs to the proxy application.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Machine learning prediction of incidence of Alzheimer’s disease using large-scale administrative health data

Nationwide population-based cohort provides a new opportunity to build an automated risk prediction model based on individuals’ history of health and healthcare beyond existing risk prediction models. We tested the possibility of machine learning models to predict future incidence of Alzheimer’s disease (AD) using large-scale administrative health data. From the Korean National Health Insurance Service database between 2002 and 2010, we obtained de-identified health data in elders above 65 years (N = 40,736) containing 4,894 unique clinical features including ICD-10 codes, medication codes, laboratory values, history of personal and family illness and socio-demographics. To define incident AD we considered two operational definitions: “definite AD” with diagnostic codes and dementia medication (n = 614) and “probable AD” with only diagnosis (n = 2026). We trained and validated random forest, support vector machine and logistic regression to predict incident AD in 1, 2, 3, and 4 subsequent years. For predicting future incidence of AD in balanced samples (bootstrapping), the machine learning models showed reasonable performance in 1-year prediction with AUC of 0.775 and 0.759, based on “definite AD” and “probable AD” outcomes, respectively; in 2-year, 0.730 and 0.693; in 3-year, 0.677 and 0.644; in 4-year, 0.725 and 0.683. The results were similar when the entire (unbalanced) samples were used. Important clinical features selected in logistic regression included hemoglobin level, age and urine protein level. This study may shed a light on the utility of the data-driven machine learning model based on large-scale administrative health data in AD risk prediction, which may enable better selection of individuals at risk for AD in clinical trials or early detection in clinical settings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Data and Models: A Framework for Advancing AI in Science

On June 5, 2019, the Office of Science (SC) organized a one-day roundtable to focus on enhancing access to high-quality and fully traceable research data, models, and computing resources to increase the value of such resources for artificial intelligence (AI) research and development and the SC mission.1 In this report, we consider AI to be inclusive of, for example, machine learning (ML), deep learning (DL), neural networks (NN), computer vision, and natural language processing (NLP). We consider “data for AI” to mean the digital artifacts used to generate AI models and/or employed in combination with AI models during inference. In part, this roundtable was motivated by the recognition that a large portion of science data currently are not well suited for AI.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

System Deterioration Detection and Root Cause Learning on Time Series Graphs

System deterioration detection and root cause analysis is crucial for today's industrial society. However, the design and operation of mechanic system is getting more and more complex, which makes it hard at identifying deterioration with noisy data. Our research focus on solving such problem on time-evolving sensor graphs in a streaming setting. Given a sequence of graphs, the ability to identify 1) any gradual and stable structured change and 2) the root cause components is of importance for early warning and system diagnosis. Existing methods either raise too many false alerts on instant changes or are too sensitive to noise. To address these problems, we propose Robust Failure Detection and Diagnosis (RoFaD). RoFaD can capture failure propagation given a time series of graph. By optimizing a matrix based Taylor expansion, RoFaD can identify system deterioration in the presence of noise and immediate changes, and diagnose the root cause components. Experiments on both synthetic and real world datasets demonstrate that RoFaD is more effective than the popular baselines.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Failure Analysis on Multivariate Time-series Data given Uncertain Labels

Machine failure analysis and detection is critical to today’s industrial society. Given a number of failure events on multivariate temporal data, the ability to identify 1) the discriminative patterns prior to the events and 2) the most relevant features to the failure has practical use for early warning and root cause analysis. However, since these patterns are not necessarily adjacent to the onset of failure in time, faulty labels are often with uncertainty, which makes traditional supervised detection methods inapplicable. To address the label uncertainty and learn the complicated correlation in multivariate time series, we design Failure Analysis on Multivariate Time-series Data (MAMT) that jointly selects the most failure-relevant features and time-instances by a novel dynamic and directional label diffusion process. Extensive experiments demonstrate that MAMT is more effective while more efficient than popular baselines.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

PCS: A Productive Computational Science Platform

As modern supercomputers continue to be increasingly heterogeneous with diverse computational accelerators, software becomes a critical aspect necessary to fully exploit these accelerators while not increasing the effort and time required to make variable scientific discovery in the face of complicated programming environments introduced by these accelerators. This paper presents PCS, a productive computational science platform for cluster-scale heterogeneous computing. The PCS platform by design follows a basic principle that, multiple programming models in a unified programming environment, is essential to facilitate large-scale, accelerator-aware, heterogeneous computing for next-generation scientific applications. We propose a new scheme — Edge Neural Network — for managing regularity in large dataflow graphs using higher-order bulk synchronous operators, providing a foundation for formalizing computational models for cluster-wide dataflow programming of heterogeneous clusters.

Ojika, David↗