全球变化知识资源中心

Urban expansion has led to a significant increase in the proportion of areas with impervious surfaces, thereby affecting the weather system and changing local precipitation. Four nonstationary generalised extreme value (GEV) models were constructed to assess the impact of urbanisation on the annual maximum 1-day precipitation (Rx1day) and annual maximum consecutive 5-day precipitation (Rx5day). Among these models, the one that modelled the location parameter as a function of local factors, urban factors, suburban factors, and Pacific Decadal Oscillation (namely, the M4USP model), exhibited a better performance at fitting the Rx1day and Rx5day than the stationary GEV model for urban and rural stations, as well as for highly urbanised suburban stations. Comparing the M4USP model with a nonstationary model varying with Pacific Decadal Oscillation (namely, the M1P model), it is found that the urban expansion could increase the magnitudes of extreme precipitation and its recurrence levels under different return periods. Specifically, the recurrence levels of Rx1day and Rx5day increased by 25.9% and 59.1% for highly urbanised stations, 34.2% and 36.9% for lowly urbanised stations, and 30.7% and 61.5% for rural stations, respectively. The decision makers should strike a balance between urbanisation and extreme precipitation to adapt to a changing environment. (C) 2019 Elsevier B.V. All rights reserved.