Collaborative Research: REU Site: Advancing Data-Driven Deep Coupling of Computational Simulations and Experiments

该项目在华盛顿州立大学、温哥华大学和休斯顿大学克里湖分校建立了本科生研究经验(REU)网站。REU网站每年接待全国十名本科生，为期三年，参与各种研究项目，开发和优化用于心律失常检测、健康行为智能监测和癌细胞检测的数据驱动和数据密集型科学工作流程。REU网站为本科生提供了一个极好的平台，让他们对高性能计算(HPC)和数据密集型工作流有新的见解和潜在的兴趣。该项目为新一代教学模块提供了与科学数据分析、机械工程中的大规模模拟和高性能计算系统优化相关的各个方面的信息。REU网站为来自社区大学、主要是本科院校和拉美裔服务机构的未被充分代表的学生提供机会，从一群代表不同种族、性别和文化的研究人员那里获得跨学科研究的经验。数据密集型工作流(即科学工作流)目前广泛应用于大多数数据驱动的研究学科，通常利用丰富多样的数据资源和并行和分布式计算平台。在拟议的暑期研究计划中，本科生参与各种项目，重点关注开发数据密集型和依赖数据的科学工作流的各个方面，从使用它们作为分析和处理来自HPC应用程序的大规模真实世界数据的技术，到调查用于加速执行这些工作流的底层计算机软件和硬件支持。REU网站专注于现实世界的科学问题，包括用于管理大型风电场的流动模拟、用于先进制造的液滴喷射建模、液体活检中的微流控癌细胞检测。现场活动包括培训学生使用数据驱动的方法(例如，机器学习、先进的系统软件和新兴硬件)来解决这些科学研究问题的大数据问题。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This project establishes a Research Experiences for Undergraduate (REU) site at Washington State University Vancouver and University of Houston Clear Lake. The REU site hosts a diverse cohort of ten undergraduate students across the nation per year for three years to participate in various research projects on developing and optimizing data-driven and data-intensive scientific workflows used for arrhythmia detection, intelligent monitoring of health behavior, cancer cell detection. The REU site provides an excellent platform for undergraduate students to gain new insights into and potential interests in high-performance computing (HPC) and data-intensive workflows. The project informs a generation of teaching modules on various aspects related to scientific data analysis, large-scale simulation in mechanical engineering, and optimization of HPC systems. The REU site provides underrepresented students, from community colleges, primarily undergraduate institutions, and Hispanic-serving institutions, opportunities to gain experience in interdisciplinary research from a group of researchers representing different races, genders, and cultures.Data-intensive workflows (i.e., scientific workflows) are widely used in most data-driven research disciplines today, often exploiting rich and diverse data resources and parallel and distributed computing platforms. In the proposed summer research program, undergraduate students participate a variety of projects focusing on various aspects of developing data-intensive and data-dependent scientific workflows, from their use as a technique to analyze and process large-scale, real-world data from HPC applications to investigating the underlying computer software and hardware support for accelerating the execution of those workflows. The REU site focuses on real-world scientific problems, including flow simulations for managing large wind farms, droplet ejection modeling for advanced manufacture, microfluidic cancer cell detection in liquid biopsy. The site activities include students training on using data-driven approaches (e.g., machine learning, advanced system software, and emerging hardware) to address the big data issues in the study of these scientific research problems.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.