报 告 人：张朝生 教授 爱尔兰国立大学

报告时间：2019 年 05 月 29 日 15:00-16:30

报告地点：环境与规划学院四楼研讨厅

主办单位：环境与规划学院

邀 请 人：马建华

主 持 人：马建华 教授

报告人简介：张朝生教授目前是爱尔兰国立大学莱恩 GIS 研究中心主任（Ryan Institute GIS Centre），以及爱尔兰国立大学地理学院环境变化研究中心主任。曾在瑞、美国、澳大利亚、牙买加等国家从事研究工作，曾任香港浸会大学研究员（2013），有着丰富的国际研究经历。其研究领域涉及环境地学、地理信息系统及空间统计学。在环境数据的定量表征及空间分析方面独具特色，研究成果获得国际同行认可，研究水平处于国际前沿，已经发表 SCI 论文 100 多篇。担任国际 SCI 期刊 Science of the Total Environment 的编委，Environmental Geochemistry and Health 的协调编辑。担任国际医学地质学联合会（International Medical Geology Association，IMGA）创会主席，国际环境地球化学与健康协会（Society for Environmental Geochemistry and Health，SEGH）副主席。曾发起和组织了环境质量和人类健康（SEGH 2010 International Conference and Workshops on Environmental Quality and Human Health）、中欧环境与健康（SESEH 2012 Sino-European Symposium on Environment and Health）等有广泛影响力的国际会议。

观点综述：It is hard to identify the influencing environmental factors on health problems due their complicated relationships. One of the issues which has not been well recognized is that such relationships are “spatially varying”, meaning that they are different at different spatial locations. On the other hand, with growing databases available at regional, national, and global scales, studies on environment and health are facing the challenges of “big data”, but new opportunities arise for the exploration of such spatially varying relationships. In the meantime, the rapidly developing techniques in machine learning become useful tools for classification, identification of clusters/patterns, identification of relationships and prediction in big data. The geographically weighted regression (GWR) offers new opportunities to explore the relationships between environmental factors and health at the local level, which is effective in identifying the complex spatially varying relationships. In this presentation, examples are provided to demonstrate the power of GWR in revealing the spatially varying relationships in geochemical databases, with an aim to expand it in health.