BD Spokes: SPOKE: MIDWEST: Digital Agriculture - Unmanned Aircraft Systems, Plant Sciences and Education

BD 发言：发言：中西部：数字农业 - 无人机系统、植物科学和教育

• 批准号: 1636865
• 负责人: Aaron Bergstrom
• 金额: $ 99.57万
• 依托单位: University of North Dakota Main Campus
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1636865&HistoricalAwards=false
• 关键词: BD; Spokes; SPOKE; MIDWEST; Digital

The Digital Agriculture Spoke of the Midwest Big Data Hub seeks to organize academic, industrial, and governmental sectors around the development of policies and best practices for data science and Big Data applications in agriculture, with a particular focus on automating the Big Data lifecycle for unmanned aircraft systems (UAS) and for plant sciences, phenomics, and genomics. This effort is necessitated by the projected growth in the global population (9.5 billion people by 2050), which will require the global agricultural workforce to produce 70% more food than our farmers do today. Historically, agricultural revolutions in cultivation, social organization, and industrialization have provided the means to increase food production. However, future revolutions must leverage the advantages provided by the modern information society. This project will serve as a catalyst for this data-driven revolution, which will be broad and societal in nature and address the triple-bottom line of being economically viable, socially acceptable, and environmentally sensible. Whereas the initial focus areas are specific, the resulting best practices and partnership-building will translate to and enable other areas such as remote sensing systems and farm management techniques. An expected outcome is improved and efficient use of UAS, imaging, and genomics in agricultural sciences, ultimately leading to a more sustainable global food and nutrition system. Coordination of these activities will be enhanced through a Digital Agriculture open web portal of data science resources, designed to integrate existing information silos, facilitate collaboration, and contribute to workforce development. Educational activities and tools will be leveraged from pre-existing traineeship programs and collaborative entities, and broadened with newly developed annual workshops. Special issue-teams of academic, industrial, and governmental representatives will be used to conduct deep-learning analysis of project educational activities to identify and refine mechanisms for broadening and diversifying participation. Through these efforts, the collaboration will improve access to data assets, train a workforce with relevant skills and expertise, and will contribute to solving the Sustainable Global Food and Nutrition Security challenge.This project will focus on two knowledge domains important to agriculture, UAS, and Plant Sciences. These two themes of Intellectual Merit will be melded with cross-cutting activities designed to improve the management, accessibility, automation, and value of the lifecycle for data that are generated by multiple, high-throughput sensor and measurement platforms in contexts related to agriculture and agriculture production. Best practices for transport, storage, dissemination, and analysis of Big Data will be translatable and scalable to other areas such as farm management systems and precision agriculture, and will enable the access to and use of valuable data assets related to UAS and plant sciences, thereby accelerating progress toward sustainable agricultural production. Many of the ideas and methods developed under this project and the partnership-building activities that link multiple public institutions and private entities will be transferable to other disciplines that require Big Data, such as transportation, health sciences, and food, energy, and water, and will therefore generate innovation and discovery from many and complex data resources. One aspect of these partnerships is the desire to build a workforce with strong data science skillsets. To accomplish this, project activities include participation by undergraduate, graduate, and early career scientists in annual meetings, Zoom events, and webinars. Interested participants from the academic, industrial, and governmental sectors will be supported and encouraged to engage in cutting-edge research and development areas such as direct data collection of plant features by UAS, biological feature extraction through image analysis, Big Data processing pipelines, and techniques for data management and sharing. Diversity of innovation related to UAS and Plant Sciences will be encouraged through a suite of issue teams who analyze in-person and web-based trainings, goal-oriented Meetups, and conference events for diversity using deep learning techniques. These modalities for deep learning were selected for their scalability and improved access by underrepresented groups. The project has a heavy emphasis on workforce training and best practices. Workshops and webinars, including hackathons and datathons, will help both students and people already in the workforce expand their professional development.

中西部大数据中心的数字农业论坛旨在组织学术、工业和政府部门，围绕农业数据科学和大数据应用的政策和最佳实践的发展，特别关注无人机系统（UAS）和植物科学、表型组学和基因组学的大数据生命周期自动化。这一努力是全球人口预计增长（到2050年将达到95亿人）所必需的，这将要求全球农业劳动力比我们今天的农民多生产70%的粮食。从历史上看，农业革命在种植、社会组织和工业化方面提供了增加粮食产量的手段。然而，未来的革命必须利用现代信息社会提供的优势。该项目将成为这场数据驱动革命的催化剂，它将具有广泛的社会性质，并解决经济上可行、社会上可接受和环境上合理的三重底线。虽然最初的重点领域是具体的，但由此产生的最佳做法和建立伙伴关系将转化为其他领域，如遥感系统和农场管理技术。预期的结果是在农业科学中改进和有效地使用无人机，成像和基因组学，最终导致更可持续的全球粮食和营养系统。这些活动的协调将通过数字农业开放的数据科学资源门户网站得到加强，旨在整合现有的信息孤岛，促进协作，并促进劳动力发展。教育活动和工具将利用现有的培训计划和合作实体，并扩大新开发的年度讲习班。由学术界、工业界和政府代表组成的特别问题小组将对项目教育活动进行深入的学习分析，以确定和完善扩大和多样化参与的机制。通过这些努力，该合作将改善对数据资产的获取，培训具有相关技能和专业知识的劳动力，并将为解决可持续全球粮食和营养安全挑战做出贡献。该项目将重点关注对农业、无人机系统和植物科学重要的两个知识领域。智力价值的这两个主题将与交叉活动相结合，旨在改善农业和农业生产相关背景下由多个高通量传感器和测量平台生成的数据的管理、可访问性、自动化和生命周期价值。大数据的运输、存储、传播和分析的最佳实践将可转化和扩展到其他领域，如农场管理系统和精准农业，并将使与无人机系统和植物科学相关的宝贵数据资产的访问和使用成为可能，从而加速实现可持续农业生产的进程。在本项目下开发的许多想法和方法，以及将多个公共机构和私营实体联系起来的伙伴关系建设活动，将可转移到需要大数据的其他学科，如交通、卫生科学、食品、能源和水，并因此将从许多复杂的数据资源中产生创新和发现。这些合作伙伴关系的一个方面是希望建立一支拥有强大数据科学技能的员工队伍。为了实现这一目标，项目活动包括由本科生、研究生和早期职业科学家参加年度会议、Zoom活动和网络研讨会。来自学术、工业和政府部门的感兴趣的参与者将被支持和鼓励从事尖端的研究和开发领域，如通过无人机直接收集植物特征，通过图像分析提取生物特征，大数据处理管道，以及数据管理和共享技术。将通过一系列问题团队来鼓励与UAS和植物科学相关的创新多样性，这些团队将分析面对面和基于网络的培训、目标导向的聚会以及使用深度学习技术的多样性会议活动。选择这些深度学习模式是因为它们具有可扩展性，并且可以改善代表性不足群体的访问。该项目非常强调劳动力培训和最佳实践。研讨会和网络研讨会，包括黑客马拉松和数据马拉松，将帮助学生和已经在职的人扩大他们的专业发展。

项目成果

Big data, data privacy, and plant and animal disease research using GEMS

使用 GEMS 进行大数据、数据隐私以及动植物疾病研究

• DOI: 10.1002/agj2.20933
• 发表时间: 2021
• 期刊: Agronomy Journal
• 影响因子: 2.1
• 作者: Senay, Senait D.;Shurson, Gerald C.;Cardona, Carol;Silverstein, Kevin A. T.
• 通讯作者: Silverstein, Kevin A. T.

Agriculture data sharing: Conceptual tools in the technical toolbox and implementation in the Open Ag Data Alliance framework

农业数据共享：技术工具箱中的概念工具以及开放农业数据联盟框架中的实施

• DOI: 10.1002/agj2.21007
• 发表时间: 2022
• 期刊: Agronomy Journal
• 影响因子: 2.1
• 作者: Ault, Aaron;Palacios, Servio;Evans, John
• 通讯作者: Evans, John

Agricultural data management and sharing: Best practices and case study

农业数据管理和共享：最佳实践和案例研究

• DOI: 10.1002/agj2.20639
• 发表时间: 2022
• 期刊: Agronomy Journal
• 影响因子: 2.1
• 作者: Moore, Eli K.;Kriesberg, Adam;Schroeder, Steven;Geil, Kerrie;Haugen, Inga;Barford, Carol;Johns, Erica M.;Arthur, Dan;Sheffield, Megan;Ritchie, Stephanie M.
• 通讯作者: Ritchie, Stephanie M.

Examining the social and biophysical determinants of U.S. Midwestern corn farmers’ adoption of precision agriculture

研究美国中西部玉米种植者采用精准农业的社会和生物物理决定因素

• DOI: 10.1007/s11119-019-09681-7
• 发表时间: 2019
• 期刊: Precision Agriculture
• 影响因子: 6.2
• 作者: Gardezi, Maaz;Bronson, Kelly
• 通讯作者: Bronson, Kelly

Big data promises and obstacles: Agricultural data ownership and privacy

大数据的前景和障碍：农业数据所有权和隐私

• DOI: 10.1002/agj2.21182
• 发表时间: 2022
• 期刊: Agronomy Journal
• 影响因子: 2.1
• 作者: Wilgenbusch, James Charles;Pardey, Philip G.;Bergstrom, Aaron
• 通讯作者: Bergstrom, Aaron