整合DMSP/OLS和NPP/VIIRS夜间灯光遥感数据的长江三角洲城市格局时空演化研究

Study on the Spatio-Temporal Evolution of the Yangtze River Delta Urban Agglomeration by Integrating Dmsp/Ols and Npp/Viirs Nighttime Light Data

本文基于1992—2012年DMSP/OLS和2012—2018年NPP/VIIRS夜间灯光遥感数据,对长江三角洲城市群时空演化格局进行监测。考虑到不同卫星夜间灯光遥感数据之间的不一致性以及城市核心区亮度过饱和问题,对DMSP/OLS和NPP/VIIRS数据进行连续性校正、去饱和处理和一致性校正,构建长江三角洲区域1992—2018年长时间序列多源夜间灯光遥感数据集。利用二分法基于该数据逐年提取长江三角洲城市群各城市建成区空间分布,计算加权标准差椭圆和Zipf系数进行重心变化和方向性分布变化、规模体系变化等监测。结果表明:(1)本研究采用的连续性校正、去饱和处理和一致性校正方法能够构建稳定的长时间序列多源夜间灯光遥感数据集;(2)基于二分法提取的建成区面积平均绝对误差为6.85 km^(2),平均相对误差为8.10%;(3)长三角城市群重心较为稳定,始终在苏州市境内的太湖沿岸附近,呈现出向东南方向移动的趋势城市群呈西北—东南方向分布,且分布方向有向南北方向转动的趋势,标准差椭圆的扁率持续减小,表明城市群的方向性分布减弱;(4)Zipf系数始终在1附近且呈缓慢降低的趋势,城市规模分布较为均衡。

Accurately quantifying the spatiotemporal evolution of urban agglomerations is important for city management plan and urban agglomeration development strategy.In this study,the spatiotemporal evolution of the Yangtze River Delta(YRD)urban agglomeration was characterized based on the DMSP/OLS nighttime light(NTL)data from 1992 to 2012 and the NPP/VIIRS NTL data from 2012 to 2018.Considering that the discrepancy between the NTL data from different satellites or sensors and the oversaturation of DMSP/OLS NTL data in urban areas limit the applications of integrating NPP/VIIRS and DMSP/OLS NTL data in monitoring the urban expansion dynamics,discrepancy correction and saturation correction were conducted to produce a temporally consistent NTL dataset combining the two NTL datasets during 1992—2018.Using the city-level built-up data obtained from the statistical yearbook as the reference,the optimal threshold values were determined by a dichotomy method to extract annual urban build-up areas in the YRD urban agglomeration from the long-term NTL dataset.Based on the extracted annual urban build-up areas,the expansion rate,centroid(center of gravity),directional distribution,and city-size distribution of the YRD urban agglomeration were analyzed using the standard deviation ellipsoid method and the Zipf coefficient.Our results show that:(1)The discrepancy correction and saturation correction procedures employed in this study effectively improved the continuity and comparability of multi-source NTL data with less reference data.We produced a temporally consistent nighttime light dataset during the period of 1982—2018;(2)The annual build-up areas in the YRD urban agglomeration extracted by the dichotomy method achieved a good accuracy,with a mean relative error of8.10%and a mean absolute error of 6.85 km^(2);(3)The city centroid of the YRD urban agglomeration was located along the Taihu Lake in Suzhou city and showed a trend of slowly moving southeast from 1982 to 2018.The YRD urban agglomeration was distributed along northwest-southeast direction,and the direction gradually shifted to the north-south then.The oblateness of weighted standard deviation ellipse gradually decreased,indicating a decrease of the directional distribution of the YRD urban agglomeration over time.This trend also suggested that the development of cities in this urban agglomeration had become more balanced in past two decades;(4)The Zipf index of the YRD urban agglomeration was close to 1 and slowly decreased,suggesting a relatively balanced pattern of the city-size distribution of this urban agglomeration.