Collaborative Research: CyberTraining: Pilot: A Cybertraining Program to Advance Data Acquisition, Processing, and Machine Learning-based Modeling in Marine Science

合作研究：网络培训：试点：一项网络培训计划，旨在推进海洋科学中的数据采集、处理和基于机器学习的建模

• 批准号: 2230046
• 负责人: Qianqian Liu
• 金额: $ 20.57万
• 依托单位: University of North Carolina at Wilmington
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-01-01 至 2024-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2230046&HistoricalAwards=false
• 关键词: Collaborative; Research; CyberTraining; Pilot; Cybertraining

Marine science researchers have access to a variety of cyberinfrastructure (CI), including software applications, facilities to host large datasets and provide computational power, and scientific tools that enable them to explore and predict the ever-changing ocean. However, the use existing CI resources are often not intuitive for new researchers. Furthermore, early-career marine science researchers have limited experience with advanced computing and data engineering techniques, which makes adoption of advanced research CI resources difficult. This project will carry out two summer training programs to educate and train early career researchers in marine science to promote CI awareness and related technical skills development to facilitate and support their research. The project team includes oceanographers and machine learning scientists. This project will create a publicly available training material repository on core CI skills for marine science researchers and provide two summer training programs in 2023 and 2024. The training will introduce the design principles of a data workflow for research projects on CI. To support researchers in the workflow-building process, this project will create a drag-and-drop tool that helps researchers generate scripts for common data workflow components such as data acquisition, data processing, and data visualization. The scripts generated can be added as components of a data workflow system and then deployed to advanced CI platforms. This project will train early-career researchers in marine science to integrate and use CI in their research through hands-on projects and hackathons to solve open-ended research questions. The training programs will be broadly disseminated through various outreach programs to encourage participation from researchers at community colleges and minority-serving institutions that have marine science or related programs.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.

海洋科学研究人员可以使用各种网络基础设施，包括软件应用程序、托管大型数据集和提供计算能力的设施，以及使他们能够探索和预测不断变化的海洋的科学工具。然而，使用现有的CI资源往往是不直观的新的研究人员。此外，早期的海洋科学研究人员在先进的计算和数据工程技术方面的经验有限，这使得采用先进的研究CI资源变得困难。该项目将开展两个暑期培训计划，教育和培训海洋科学的早期职业研究人员，以促进CI意识和相关技术技能的发展，以促进和支持他们的研究。该项目团队包括海洋学家和机器学习科学家。该项目将为海洋科学研究人员创建一个公开的核心CI技能培训材料库，并在2023年和2024年提供两个夏季培训项目。培训将介绍CI研究项目的数据工作流程的设计原则。为了在工作流构建过程中支持研究人员，该项目将创建一个拖放工具，帮助研究人员为常见的数据工作流组件（如数据采集，数据处理和数据可视化）生成脚本。生成的脚本可以作为数据工作流系统的组件添加，然后部署到高级CI平台。该项目将培训海洋科学的早期职业研究人员，通过动手项目和黑客马拉松来解决开放式研究问题，从而在他们的研究中整合和使用CI。培训计划将通过各种推广计划广泛传播，以鼓励社区学院和拥有海洋科学或相关项目的少数民族服务机构的研究人员参与。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Temporal Prediction of Coastal Water Quality Based on Environmental Factors with Machine Learning

• DOI: 10.3390/jmse11081608
• 发表时间: 2023-08
• 期刊: Journal of Marine Science and Engineering
• 影响因子: 2.9
• 作者: Junan Lin;Qianqian Liu;Yang Song;Jiting Liu;Yixue Yin;N. Hall