SCC-IRG Track 2: Toxic-Free Footprints to Improve Community Health against Respiratory Hazards

SCC-IRG 第 2 轨道：无毒足迹改善社区健康，预防呼吸系统危害

• 批准号: 2125326
• 负责人: Qi Wang
• 金额: $ 150万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2125326&HistoricalAwards=false
• 关键词: SCC; IRG; Track; Toxic; Free

Fifty years after the passing of the Clean Air Act in the U.S., nearly half of the nation’s population is estimated to live with and breathe polluted air in 2020. The recent acceleration in the number and intensity of wildfires driven by climate change and the devastating COVID-19 pandemic have made air pollution effects on public health an even more heightened concern. This Smart and Connected Communities project builds and enhances technological, economic, political, and social infrastructures in vulnerable communities to better sense and monitor air quality, prevent exposure to respiratory hazards, and raise awareness of and battle misinformation on air quality. The research aims to build smart and connected toxic-free communities, which resonates with NSF’s mission “to advance the national health, prosperity, and welfare.” The research team collaborates with local grass-root organizations, communities, research centers, and planning agencies in two communities, Roxbury, Boston, MA and St. John the Baptist Parish, LA. The new technological approaches and air quality data generated by the project along with the deep community engagement will potentially influence and enhance policies and benefit underserved communities with more equitable access to a healthy environment.In this research project, the research team (1) develops data-driven approaches to seamlessly link human mobility (i.e., a person’s footprints within and beyond the residential place) and respiratory hazards measured by air quality monitors; (2) designs real-time AI technologies to connect information and communities that support both network-based interventions; and (3) deploys the methodology in two representative local communities characterized with minority and diversity both burdened by air pollution. The research focuses on volatile organic compounds (VOCs) and particulate matter (e.g., PM2.5) for their known health impacts of causing lung cancers and cardiovascular and respiratory diseases. The key deliverables of work include: (1) a data-driven and real-time AI-based framework that links multi-model data streams (e.g., geolocations, air quality, social networks, etc.) to quantify and predict air pollution exposures associated with human footprints; (2) social network-based interventions strategies developed interactively with and tested by two communities burdened by air pollution (Roxbury, Boston, MA and St. John Parish, New Orleans, LA); and (3) real-time AI-powered mobile application (App), Toxic-Free Life, for mainstream smartphones that allows real-time estimations of air exposure and supports network-based interventions.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.

美国《清洁空气法案》通过 50 年后，预计到 2020 年，美国近一半人口将生活在受污染的空气中。最近，气候变化和毁灭性的新冠疫情导致野火数量和强度加速增加-19 大流行使空气污染对公共卫生的影响成为更加广泛的问题。这个智能互联社区项目在脆弱社区建设和加强技术、经济、政治和社会基础设施，以更好地感知和监测空气质量，预防疾病。该研究旨在建立智能、互联的无毒社区，这与 NSF“促进国民健康、繁荣和福利”的使命相呼应。与马萨诸塞州波士顿罗克斯伯里和路易斯安那州圣约翰浸信会教区两个社区的当地基层组织、社区、研究中心和规划机构合作，该项目生成的新技术方法和空气质量数据。深入的社区参与可能会影响和增强政策并让服务不足的社区受益，让他们更公平地获得健康的环境。在这个研究项目中，研究团队 (1) 开发了数据驱动的方法，将人类流动性（即一个人在居住地内外的足迹）和呼吸系统无缝联系起来通过空气质量监测器测量危害；(2) 设计实时人工智能技术来连接信息和社区，支持基于网络的干预措施；(3) 在两个具有代表性的当地社区部署该方法，这些社区都受到空气的影响；研究重点。挥发性有机化合物（VOC）和颗粒物（例如 PM2.5）已知的导致肺癌以及心血管和呼吸系统疾病的健康影响的主要工作成果包括：（1）数据驱动的实时研究。基于人工智能的框架，连接多模型数据流（例如地理位置、空气质量、社交网络等），以量化和预测与人类足迹相关的空气污染暴露；（2）与人类足迹交互开发的基于社交网络的干预策略并由两个受空气污染困扰的社区（马萨诸塞州波士顿罗克斯伯里和路易斯安那州新奥尔良圣约翰教区）进行了测试；(3) 主流的实时人工智能移动应用程序 (App)，Toxic-Free Life；该奖项反映了 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。

项目成果

Reliant: Fair knowledge distillation for graph neural networks.

Reliant：图神经网络的公平知识蒸馏。

• 发表时间: 2023-08
• 期刊: ACM
• 作者: Dong, Yushun;Zhang, Binchi;Yuan, Yiling;Zhou, Na;Wang, Qi;and Li, Jundong
• 通讯作者: and Li, Jundong

Percolation transitions in urban mobility networks in America's 50 largest cities

美国 50 个最大城市的城市交通网络的渗透转变

• DOI: 10.1016/j.scs.2023.104435
• 发表时间: 2023-04
• 期刊: Sustainable Cities and Society
• 影响因子: 11.7
• 作者: Wang, Ruoxi;Wang, Qi;Li, Nan
• 通讯作者: Li, Nan

Estimating comparable distances to tipping points across mutualistic systems by scaled recovery rates

通过缩放回收率来估计互惠系统中到临界点的可比距离

• DOI: 10.1038/s41559-022-01850-8
• 发表时间: 2022-08-29
• 期刊: Nature Ecology & Evolution
• 影响因子: 16.8
• 作者: Huixin Zhang;Qi Wang;W. Zhang;S. Havlin;Jianxi Gao
• 通讯作者: Jianxi Gao

A spatiotemporal decay model of human mobility when facing large-scale crises

面临大规模危机时人类流动性的时空衰减模型

• DOI: 10.1073/pnas.2203042119
• 发表时间: 2022-08-08
• 期刊: Proceedings of the National Academy of Sciences of the United States of America
• 影响因子: 11.1
• 作者: Weiyu Li;Qi Wang;Yuanyuan Liu;M. Small;Jianxi Gao
• 通讯作者: Jianxi Gao