Proto-OKN Theme 1: Exploiting Federal Data and Beyond: A Multi-modal Knowledge Network for Comprehensive Wildlife Management under Climate Change

这个原型开放知识网络项目旨在为气候变化背景下的野生动物管理创建一个全面、综合的知识网络，称为KN-Wildlife。有效的野生动物管理对于保护任何地区的生物多样性、生态系统健康和经济稳定至关重要。迫在眉睫的气候变化威胁可能会破坏许多物种的分布、行为和种群动态，特别是那些入侵物种、受威胁物种或具有重要经济意义的物种。虽然物种分布模型（SDMs）已被用于预测物种对气候变化的响应，但其预测能力可能会受到一些影响因素的影响，如种间竞争、土地利用变化或各种物种的迁移能力。与这些考虑相关的一些数据来源包括美国地质调查局（USGS）、全球生物多样性信息设施和世界自然保护联盟濒危物种红色名录。然而，这些数据的有效利用目前受到与数据的异质性、空间和时间差异以及不同质量和完整性有关的因素的阻碍。KN-Wildlife将通过提供一个开放访问平台来解决这个问题，该平台将数据与可视化工具和预测模型相结合，将复杂的多模式数据提炼成一个直观、统一的管理物种表示。KN-Wildlife将有助于为决策过程提供信息，同时为利益相关者提供可行的见解。该项目将首先为美国印第安纳州和佛罗里达州这两个州的利益相关者提供有关物种的全面知识和预测模型。项目合作者包括来自这两个州的鱼类和野生动物委员会（FWC）和卫生部（DoH）的利益相关者。KN-Wildlife最初将专注于利益相关者感兴趣的约3000种管理物种，包括从真菌和细菌到鱼类和哺乳动物的广泛分类。该项目将与圣母大学露西家庭研究所合作，将KN-Wildlife的使用纳入美国国家科学基金会资助的跨学科社会责任和参与数据科学家培训（iTREDS）计划和数据科学暑期教育和参与（SEEDS）计划。这些计划专门为本科生提供以社会挑战为中心的数据科学培训，并为资源不足的学校和社区的学生提供K-12培训机会。所有kn野生动物资源都将向公众开放。该奖项反映了美国国家科学基金会的法定使命，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。

This Prototype-Open Knowledge Network project seeks to create a comprehensive, integrative knowledge network for the management of wildlife in the context of climate change, called KN-Wildlife. Effective wildlife management is essential for safeguarding biodiversity, ecosystem health, and economic stability of any region. The looming threat of climate change can disrupt the distribution, behavior, and population dynamics of many species, particularly those that are invasive or threatened or economically important. While Species Distribution Models (SDMs) have been used to predict species responses to climate change, their predictive capability can be hampered by the omission of several influencing factors like interspecies competition, changes in land use, or the migration ability of various species. A number of data sources are available that are relevant to these considerations including the United States Geological Survey (USGS), the Global Biodiversity Information Facility, and the IUCN Red List of Threatened Species. However, the effective use of these data is currently impeded by factors associated with the heterogeneity, spatial and temporal discrepancies, and varying quality and completeness of the data. KN-Wildlife will address this problem by providing an open-access platform that couples data with visualization tools and predictive models to distill complex multimodal data into an intuitive, unified representation of managed species. KN-Wildlife would help inform decision-making processes and while providing stakeholders with actionable insights. The project will begin by providing comprehensive knowledge and predictive models for species of concern to stakeholders in these two US states, viz., Indiana and Florida. Project collaborators include stakeholders from the Fish and Wildlife Commissions (FWC) and Departments of Health (DoH) from both of these states. KN-Wildlife will initially focus on around 3,000 managed species of interest to the stakeholders, encompassing a broad taxonomy from fungi and bacteria to fish and mammals. Working in collaboration with the Lucy Family Institute at the University of Notre Dame, the project will integrate use of KN-Wildlife into the NSF-funded Interdisciplinary Traineeship for Socially Responsible and Engaged Data Scientists (iTREDS) program and the Summer Education and Engagement for Data Science (SEEDS) Program. These initiatives are specifically designed to provide undergraduate data science training centered on societal challenges, and also provide K-12 training opportunities for those from under-resourced schools and communities. All KN-Wildlife resources will be publicly available.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.