Urban vulnerability

气候对人类健康的影响已在几项研究中得到证实，特别是城市热应激与死亡率、发病率以及生活质量下降有关。然而，到目前为止，很少有人知道的空间格局和过程中的热应力风险在城市范围内的社会经济和生物物理层面的脆弱性。因此，本单元的目标是：（1）对人口对城市热压力的脆弱性进行多尺度分析，（2）对选定的脆弱人口群体进行室内和室外城市热压力风险分析，（3）在不同备选方案下，对未来可能的脆弱性和风险进行设想。为了解释异质和多维数据集，并探索影响变量之间的条件依赖关系，我们专注于城市热应力的机器学习建模方法。预期成果是机器学习方法的发展，以模拟脆弱性和风险，并深入了解城市热应激，以进一步制定应对战略。

The impact of climatic effects on human health has been proven in several studies and particularly urban heat stress has been linked to mortality, morbidity as well as a reduced quality of life. However, up to now little is known about the spatial patterns and processes of heat stress risk on a city-wide scale linking socioeconomic and biophysical dimensions of vulnerability. The objectives of this module are therefore (1) A multiscale analysis of vulnerability of the population to urban heat stress, (2) A risk analysis to indoor and outdoor urban heat stress for selected vulnerable population groups, (3) Scenario development of likely future vulnerability and risk under different alternatives of options. To account for the heterogeneous und multidimensional datasets and to explore conditional dependencies between influencing variables we focus on a machine-learning modelling approach for urban heat stress. The expected outcomes are methodological developments of machine-learning for modelling vulnerability and risk and insights on urban heat stress for further developing coping strategies.