Urban Functional Zone Mapping By Integrating High Spatial Resolution Nighttime Light And Daytime Optical Imagery

Urban functional zones(UFZs)describe the human activity in a certain urban area,and its mapping work is fundamental to urban management,investigation,and research and can provide important data for the study of urban expansion and redevelopment,the understanding of urban environment and the health survey of urban dwellers.The existing urban functional zone mapping methods usually utilize visual features from high spatial resolution optical images,and focus on two-dimensional image features,such as texture and landscape.However,UFZ is a comprehensive concept including geographical,social,and economic aspects.Therefore,it is reasonable to simultaneously take into account the characteristics of both human activities and image visual features for its accurate interpretation.Multi-view optical satellite images can delineate the physical characteristics of a city,i.e.,3D structures;on the other hand,high spatial resolution nighttime light images are important signals of human activities.These two data sources can be complementary in representing urban landscapes.However,to our knowledge,in the current literature,neither multi-view images nor high spatial resolution nighttime light images have been used for UFZ mapping,and it is poorly understood whether their individual or combined use can achieve satisfactory results.Therefore,in this study,a daytime and nighttime data fusion method,that is,the fusion of daytime multi-view and high spatial resolution nighttime light images,was proposed for UFZ mapping.Specifically,the spectral and multi-view features are derived from Ziyuan3 multispectral and multi-view(forward,nadir,and backward)optical images(with the spatial resolution of 2.1 m),and nighttime light feature is calculated from Jilin1 nighttime light image(with the spatial resolution of 0.92 m).In particular,a building enhanced nighttime light index(BENI)was proposed to improve the ability of the nighttime light images in discriminating between different functional zones.Experiments were conducted in two megacities of China,i.e.,Beijing and Wuhan,where high spatial resolution Ziyuan3 multi-view image and Jilin7 nighttime light image were fused for urban functional mapping.Results indicated that: 1)the addition of multi-view features led to an overall accuracy(OA)increment of 5.3% in Beijing and 2.2% in Wuhan compared with the spectral features;and 2)the inclusion of nighttime light features achieved OA of 89.6% in Beijing and 85.2% in Wuhan,which further improved the OA of daytime features by 6.1% in Beijing and 1.5% in Wuhan.In particular,nighttime light features significantly improved the accuracy of commercial zones by 23.8% in Beijing and 10.2% in Wuhan.In the daytime-nighttime feature fusion,the spectral features made the largest contribution,followed by the multi-view and nighttime light features.Moreover,better performances of the BENI in theory and experiments were observed compared to the original brightness,showing that BENI was able to enhance the separability between various function zones.In general,this thesis verified the effectiveness and complementarity of daytime(including multi-spectral and multi-view images)and nighttime images in UFZ mapping,and provided new thoughts for daytime and nighttime data fusion and urban mapping.