REU Site: Advancing high-performance computing opportunities in undergraduate research at UW-Eau Claire to meet challenges of multidisciplinary computational science

REU 网站：在威斯康星大学欧克莱尔分校本科生研究中推进高性能计算机会，应对多学科计算科学的挑战

• 批准号: 2150191
• 负责人: Rahul Gomes
• 金额: $ 38.58万
• 依托单位: University of Wisconsin-Eau Claire
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2150191&HistoricalAwards=false
• 关键词: REU; Site; Advancing; performance; computing

Recent years have witnessed a significant growth in computationally intensive scientific and engineering studies involving large-scale data processing, thereby driving groundbreaking innovations across STEM disciplines. These studies require an interdisciplinary approach, where a combination of domain-specific expertise and knowledge of developing scalable algorithms is necessary. The ten-week Research Experience for Undergraduates (REU) program at University of Wisconsin – Eau Claire will provide a comprehensive research experience in high performance computing (HPC) and inspire a diverse group of students to pursue careers in STEM disciplines related to multidisciplinary computational science. The REU site will support research for ten undergraduate students each summer engaging them in a collaborative research experience with the central theme of designing computationally intensive algorithms and simulation models using HPC. The goal of the program is to attract students to careers in STEM and train them to use advanced hardware and computing resources, providing an opportunity that most undergraduate students do not get to experience during their course of study. The REU site will also work to promote national STEM workforce diversity goals by recruiting students from underrepresented groups in STEM at two-year colleges, where research opportunities are limited. With its focus on HPC and its application in diverse scientific disciplines, the project will serve to fulfill several of the key goals of NSF: to advance discovery and learning, to promote inclusion in the science and engineering workforce, and provide an integrated strategy to advance the frontiers of knowledge.Through a focused research experience provided by research mentors, students will have the opportunity to develop new algorithms that utilize HPC infrastructure to solve scientific problems. Students will learn to complete research projects, develop simulation and predictive models, analyze results, prepare manuscripts for submission in journals, conference proceedings, and do technical presentations. A total of ten projects from five separate research domains in computational science will be made available to the students. These domains include (1) deep learning and computer vision with applications in biomedical imaging, pattern recognition, and geospatial data analysis, (2) machine learning and its application to social media analytics, (3) quantum chemical simulation to probe events at the electron level, (4) multiscale modeling and simulation to explore complex biomolecular structure and function, and (5) computational astrophysical study of stellar structure and evolution. Additionally, the REU program will develop leadership and interpersonal skills through seminars in undergraduate research, diversity in STEM, scientific writing, ethics in computing, preparing for graduate school, service learning, and career planning. The REU program will also engage students through invited guest speaker presentations and field trips. The success of the REU site will be assessed by internal evaluation along with evaluation resources and services offered through the Comparative Evaluation for NSF CISE Research Experiences for Undergraduates (CERP-REU).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.

近年来，涉及大规模数据处理的计算密集型科学和工程研究的显着增长，从而推动了跨STEM学科的开创性创新。这些研究需要一种跨学科的方法，在这种方法中，必须结合特定于领域的专业知识和开发可扩展算法的知识。威斯康星大学的本科生（REU）计划为期十周的研究经验 - EAU CLAIRE将提供高性能计算（HPC）的全面研究经验，并激发一群潜水员的学生从事与多学科计算科学有关的STEM学科的职业。 REU网站将每年夏天支持十个本科生的研究，以与使用HPC设计计算密集型算法和模拟模型的中心主题，参与他们的协作研究经验。该计划的目的是吸引学生从事STEM的职业，并训练他们使用高级硬件和计算资源，从而提供了一个机会，大多数本科生在学习过程中都无法体验。 REU网站还将通过在研究机会有限的两年学院的STEM中招募来自STEM代表性不足的群体的学生来促进国家STEM劳动力多样性目标。 With its focus on HPC and its application in Diverse scientific disciplines, the project will serve to fulfill several of the key goals of NSF: to advance discovery and learning, to promote inclusion in the science and engineering workforce, and provide an integrated strategy to advance the frontiers of knowing.Through a focused research experience provided by research mentors, students will have the opportunity to develop new algorithms that utilize HPC infrastructure to solve scientific problems.学生将学习完成研究项目，开发模拟和预测模型，分析结果，为在期刊，会议程序中提交的手稿准备手稿以及进行技术演示。来自计算科学中五个单独的研究领域的十个项目将为学生提供。这些领域包括（1）深度学习和计算机视觉，并在生物医学成像，模式识别和地理空间数据分析中应用，（2）机器学习及其在社交媒体分析中的应用，（3）量子化学模拟在电子水平上进行探测事件，（4）多重建模和多个模型，以探索复杂的生物分类结构和功能性的结构，以及（5）计算成分和繁星量，并启发出来。此外，REU计划将通过本科研究，STEM的多样性，科学写作，计算中的道德，为研究生院做准备，服务学习和职业计划的良好性来发展领导力和人际交往能力。 REU计划还将通过受邀的演讲嘉宾演讲和实地考察与学生互动。 REU站点的成功将通过内部评估以及通过对本科生的NSF CISE研究经验（CERP-REU）进行比较评估提供的评估资源和服务评估。该奖项反映了NSF的法定任务，并被认为是通过基金会的知识分子的智力和广泛的影响来评估Criteria的智力优点和广泛的Criteria，并被认为是值得的。

项目成果

Analysis of Swin-UNet vision transformer for Inferior Vena Cava filter segmentation from CT scans

CT 扫描中下腔静脉滤波器分割的 Swin-UNet 视觉变换器分析

• DOI: 10.1016/j.ailsci.2023.100084
• 发表时间: 2023
• 期刊: Artificial Intelligence in the Life Sciences
• 作者: Gomes, Rahul;Pham, Tyler;He, Nichol;Kamrowski, Connor;Wildenberg, Joseph
• 通讯作者: Wildenberg, Joseph

Deep Learning Patch-Based Approach for Hyperspectral Image Classification

• DOI: 10.1109/eit57321.2023.10187387
• 发表时间: 2023-05
• 期刊: 2023 IEEE International Conference on Electro Information Technology (eIT)
• 作者: Papia F. Rozario;E. Ruehmann;T. Pham;Tianqi Sun;Jacob Jensen;Hengrui Jia;Zhongyue Yu;Rahul Gomes