Collaborative Research: Digitization TCN: Extending Anthophila research through image and trait digitization (Big-Bee)

蜜蜂数量的减少影响了自然和农业系统中植物与传粉者的相互作用。虽然蜜蜂和其他昆虫为大多数野生植物授粉，对维持全球粮食生产的很大比例至关重要，但它们的数量和多样性都在减少。我们对导致这些下降的因素的了解有限，因为我们缺乏关于蜜蜂物种分布的足够数据，以及可能使它们对人类诱导的环境变化(如栖息地丧失和气候变化)脆弱或有弹性的行为和解剖特征。幸运的是，研究人员收集了野生蜜蜂，并将其保存在自然历史收藏中超过100年，保留了可以从标本图像中提取的丰富相关属性。该项目将从这些历史标本中以数字方式捕获数据和图像，开发工具来从这些图像中测量蜜蜂的特征，并生成一个全面的蜜蜂特征和图像数据集来测量随时间的变化。这将增加我们对使蜜蜂物种面临衰退风险的特定特征的理解--这是维持我们的农业经济和保护我们的自然资源的迫切需要。此外，该项目创建的大型图像数据集可以用于新的人工智能识别工具，这将有助于改进我们未来的传粉者观察和监测工作。大蜜蜂主题收集网络(Big-Bee TCN)将创建100多万张高分辨率的蜜蜂标本2D和3D图像，代表全球5000多个蜜蜂物种，包括美国所有主要的授粉物种。Big-Bee网络包括13个机构和与美国政府机构的合作伙伴关系。将开发共享图像数据集的新机制，并将通过开放的数据门户网站蜜蜂图书馆提供蜜蜂特征数据集，用于研究和教育。Big-Bee项目将通过众包特征测量和图像数据转录，通过社区科学吸引普通公众参与研究。此外，将通过创建和实施以蜜蜂特性和物种鉴定为重点的研讨会，为自然历史收集工作人员、研究人员和大学生提供数据科学方面的培训和专业发展。这一奖项产生的所有数据将与国家数字化生物收集资源iDigBio.org共享并公开提供。该奖项反映了NSF的法定使命，并已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。

Declining populations of bees impact plant-pollinator interactions in both natural and agricultural systems. While bees and other insects pollinate most wild plants, and are critical to sustain a large proportion of global food production, they are decreasing in both numbers and diversity. Our understanding of the factors driving these declines is limited because we lack sufficient data on the distribution of bee species, and on the behavioral and anatomical traits that may make them either vulnerable or resilient to human-induced environmental changes, such as habitat loss and climate change. Fortunately, wild bees have been collected by researchers and deposited in natural history collections for over 100 years, retaining a wealth of associated attributes that can be extracted from specimen images. This project will digitally capture data and images from these historic specimens, develop tools to measure bee traits from these images, and generate a comprehensive bee trait and image dataset to measure changes through time. This will increase our understanding of specific traits that put bee species at risk of decline - a critical need for both sustaining our agricultural economy and the conservation of our natural resources. In addition, the large image datasets created by this project can be used for new artificial intelligence identification tools that will help improve our future pollinator observation and monitoring efforts.The Big-Bee Thematic Collection Network (Big-Bee TCN) will create over one million high-resolution 2D and 3D images of bee specimens, representing over 5,000 worldwide bee species, including all of the major pollinating species of the United States. The Big-Bee network includes 13 institutions and partnerships with US government agencies. Novel mechanisms for sharing image datasets will be developed and datasets of bee traits will be available through an open data portal, the Bee Library, for research and education. The Big-Bee project will engage the general public in research through community science via crowdsourcing trait measurements and data transcription from images. In addition, training and professional development for natural history collection staff, researchers, and university students in data science will be provided through the creation and implementation of workshops focusing on bee traits and species identification. All data resulting from this award will be shared with and publicly available through the national digitized biocollections resource, iDigBio.org.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.