Puffins: Exploring how narrative, data science, and artificial intelligence enhance the study of ecology in middle school

海雀的研究可以为数据和生态系统的综合学习提供一个迷人的学科领域。海雀曾因猎杀而在当地灭绝，如今它们戏剧性而脆弱地卷土重来，并在缅因州中部海岸的历史悠久的筑巢岛屿上重新安家。该项目结合了海雀恢复的科学冒险故事和学生指导的关于海雀健康与环境因素之间关系的数据调查。学生们将研究几十年来国家奥杜邦协会关于海雀的数据的趋势和相关性，使用一个可访问的开源教育数据工具来研究各种变量之间的关系，包括海面温度、孵化岛、海雀饮食中的鱼、初生体重和生存到繁殖年龄。他们将使用海雀网络摄像头和录音的当前数据来补充他们的历史数据集。学生将训练一个人工智能（AI）系统来区分海雀的叫声，学习数据偏差的概念，并研究海雀叫声的模式如何与海雀行为和健康的其他方面相关联。学生们还将在学校安装自己的网络摄像头，以概括他们对当地鸟类行为的研究，并了解科学家如何使用网络摄像头。最后，学生们将与来自不同背景的前实习生互动，他们曾在缅因州的海雀岛工作过，以了解如何使用数据来研究鸟类学和气候变化。该项目将使缅因州的农村和城市学生、母语不是英语的学生、新移民和不认为自己是科学取向的学生能够体验地方和社区的真实数据，并对一个有魅力的物种进行自己的研究。该项目由“面向学生和教师的创新技术体验”（ITEST）项目资助，该项目支持有助于提高学生对科学、技术、工程和数学（STEM）以及信息和通信技术（ICT）职业的知识和兴趣的实践、项目要素、背景和过程的理解。这个项目的目标是探索数据科学和人工智能，结合一本关于海雀的非小说类书籍的科学叙述，如何增强中学生对生态系统的学习。该项目解决了三个研究问题：1)学生如何使用数据工具来理解大型生态数据集？2)学生如何组织和使用从网络摄像头收集的数据，例如海雀从事各种行为的图像或海雀发出的声音，以及他们如何使用人工智能来扩展他们的观察；3)使用数据工具，结合非小说类书籍，对学生更广泛地了解海雀生态学和生态系统有什么影响？该项目将采用基于设计的研究方法，由几位中学教师与项目工作人员共同设计一个为期三周的课程模块。这些教师还将为研究计划提供意见，该计划基于课堂观察以及七个教室中每个教室中少数学生的案例研究。案例研究将对学生对海雀数据的理解进行更深入的分析，并将涉及学生工作的收集以及学生将被要求解释他们的发现的个人访谈。此外，我们将收集参与项目的所有500名学生的调查数据，以确定他们对STEM的整体兴趣、参与度、职业知识以及对数据科学和生态学的兴趣是如何受到影响的。项目的可交付成果包括海雀课程模块和一个关于海雀的奥杜邦数据集的修改版本，该数据集将免费提供给所有教育工作者。我们将向研究人员、教育工作者和公众公布该项目的研究结果。教师讲习班，包括一个侧重于吸引代表性不足的学生学习数据科学的讲习班，将向全国观众介绍。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。

The study of puffins can provide a fascinating subject area for the integrated learning of data and ecosystems. Once hunted to local extinction, puffins have made a dramatic yet fragile comeback and been re-established to historic nesting islands in mid-coast Maine. This project combines a scientific adventure story about puffin restoration with student-directed data investigations about the relationships between puffin health and environmental factors. Students will examine trends and correlations in several decades of curated National Audubon Society data about puffins, using an accessible open-source education data tool to examine relationships among variables including sea surface temperature, hatch island, fish in the puffin diet, fledgling weight, and survival to breeding age. They will use present-day data from puffin webcams and sound recordings to supplement their work with historical datasets. Students will train an artificial intelligence (AI) system to distinguish among puffin vocalizations, learn concepts of data biases, and examine how patterns of puffin calls associate with other aspects of puffin behavior and health. Students also will install their own webcams at school to generalize their study on the behavior of local birds and learn how scientists use webcams. Finally, students will interact with former interns from diverse backgrounds who have worked on Maine’s puffin islands to learn how data are being used to study ornithology and climate change. The project will enable Maine’s rural and urban students, students whose first language is not English, new immigrants, and students who do not consider themselves science-oriented to experience place and community-based authentic data and perform their own research on a charismatic species. This project is funded by the Innovative Technology Experiences for Students and Teachers (ITEST) program, which supports projects that build understandings of practices, program elements, contexts and processes contributing to increasing students' knowledge and interest in science, technology, engineering, and mathematics (STEM) and information and communication technology (ICT) careers.The goal of this project is to explore how data science and AI, combined with the scientific narrative of a nonfiction book about puffins, enhances middle school students’ learning about an ecological system. The project addresses three research questions: 1) How do students use data tools to make sense of large ecological datasets?; 2) How do students organize and use data gathered from webcams, such as images of puffins engaged in various behaviors or the sounds puffins make, and how do they use AI to extend their observations?; and 3) What is the impact of using data tools, combined with a nonfiction book, on students’ learning about puffin ecology and ecological systems more generally? The project will use a design-based research approach in which several middle school teachers co-design a three-week curriculum module in conjunction with project staff. These teachers will also provide input to the research plan, which is based on classroom observations as well as case studies of a small number of students from each of seven classrooms. The case study research will provide a deeper analysis of students’ understanding of puffin data, and will involve the collection of student work as well as individual interviews in which students will be asked to explain their findings. In addition, we will collect survey data from all 500 students who participate in the project to determine how their overall STEM interest, engagement, career knowledge, and interest in data science and ecology have been impacted. Project deliverables include the puffin curriculum module and a modified version of an Audubon dataset about puffins that will be made freely available for all educators. We will publish the project’s findings for researchers, educators, and the general public. Teacher workshops, including one focused on attracting under-represented students to data science, will be presented to national audiences.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.