CAREER: Modeling Movement and Behavior Responses to Environmental Disruptions

这个项目是关于分析不同地理和时间尺度上的重大环境破坏对人们行为的影响。使用移动作为位置标记，该项目将提供有关野火爆发、流行病和人与野生动物冲突局势等破坏性事件造成的环境变化后果的数据驱动的结果。有意运动是人类和动物共有的一个重要特征，也是地理环境动态的一个基本因素。这项研究将使科学家能够对破坏性事件造成的行为适应进行建模。这项研究中发展的跨学科方法对于理解社会和生态系统的适应具有普遍意义，为人类和关键物种的空间行为提供了新的知识。该项目的教育举措将提高地理意识，促进时空思维，并将扩大大学生和教育工作者对STEM教育和研究的参与。尽管跟踪技术取得了进步，但我们对运动模式的机制的了解仍然有限。这一跨学科项目将通过使用计算运动分析整合关于空间和时间变化的信息，从而改变地理信息科学的研究和教育。本研究将探讨三个核心研究问题：1)个人的运动和行为是否受其环境驱动，以及这些关系如何在空间尺度上变化？2)数据科学如何更好地捕捉反映行为变化的运动模式？3)如何将运动作为代理来理解和预测破坏性事件导致的个人行为适应？该项目将创建潜在的变革性计算方法，用于机器学习、建模和模拟环境中断中的空间行为，包括野火、新冠肺炎大流行和人类与濒危物种的互动。前两项研究侧重于人类运动对短期和长期环境变化的反应和适应，而后者则评估在经历土地利用逐渐变化的环境中的弹性。这一奖项反映了NSF的法定使命，并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。

This project is about analyzing the effects of significant environmental disruptions on peoples’ behavior across different geographic and temporal scales. Using movement as a positional marker, this project will provide data-driven results about the consequences of environmental change caused by disruptive events such as wildfire outbreaks, pandemics, and human-wildlife conflict situations. Intentional movement is an important trait shared among humans and animals and is a fundamental actor in the dynamics of geographical environments. This research will enable scientists to model behavioral adaptation caused by disruptive events. The transdisciplinary methods developed in this study are generalizable to understanding adaptation in both social and ecological systems, contributing new knowledge about spatial behavior of humans and keystone species. The project's educational initiatives will raise geography awareness and advance spatiotemporal thinking and will broaden participation of college students and educators in STEM education and research.Despite the advances in tracking technologies, there still exists limited in our understanding of the mechanisms governing movement patterns. This interdisciplinary project will transform research and education in geographic information science by integrating information on both spatial and temporal change using computational movement analytics. This study will investigate three core research questions: 1) Are individuals’ movement and behavior driven by their environment, and how do these relationships vary across spatial scales? 2) How can data science better capture movement patterns that reflect change in behavior? 3) How can movement be used as a proxy to understand and predict the behavioral adaptation of individuals caused by disruptive events? This project will create potentially transformative computational approaches for machine learning, modeling, and simulation of spatial behavior in environmental disruptions that includes wildfire, COVID-19 pandemic, and human interaction with endangered species. The first two studies focus on human movement responses and adaptation to short- and long- term environmental changes, while the latter evaluates resilience in an environment experiencing gradual land-use change.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.