DeepDPM: Dynamic Population Mapping via Deep Neural Network

Abstract

Dynamic high resolution data on human population distribution is of great importance for a wide spectrum of activities and real-life applications, but is too difficult and expensive to obtain directly. Therefore, generating fine-scaled population distributions from coarse population data is of great significance. However, there are three major challenges: 1) the complexity in spatial relations between high and low resolution population; 2) the dependence of population distributions on other external information; 3) the difficulty in retrieving temporal distribution patterns. In this paper, we first propose the idea to generate dynamic population distributions in full-time series, then we design dynamic population mapping via deep neural network(DeepDPM), a model that describes both spatial and temporal patterns using coarse data and point of interest information. In DeepDPM, we utilize super-resolution convolutional neural network(SRCNN) based model to directly map coarse data into higher resolution data, and a timeembedded long short-term memory model to effectively capture the periodicity nature to smooth the finer-scaled results from the previous static SRCNN model. We perform extensive experiments on a real-life mobile dataset collected from Shanghai. Our results demonstrate that DeepDPM outperforms previous state-of-the-art methods and a suite of frequent data-mining approaches. Moreover, DeepDPM breaks through the limitation from previous works in time dimension so that dynamic predictions in all-day time slots can be obtained.

Development of a City-Scale Approach for Façade Color Measurement with Building Functional Classification Using Deep Learning and Street View Images

“…Many automatic building classification methods have emerged with the development of measurement tools and data sources [21]. The classification methods combined with street view images and deep learning are open source and favored by city researchers in urban analytics and urban computing, showing great potential for many applications, such as urban population mapping [22], density analysis [23], or urban utility planning [24]. However, there are usually multiple buildings in street view photos, and it is necessary to move beyond the single-label classification tasks to precisely describe the building classification in the image.…”

Using Satellite Imagery to Understand and Promote Sustainable Development

“…This is currently the leading approach in most computer vision applications, including in the satellite space when training data are plentiful. Use of this approach in sustainable development applications has proliferated in recent years, including in the measurement of population, [24][25][26] economic livelihoods, [27][28][29][30] infrastructure quality, 31,32 land use, 33,34 informal settlements, 35,36 fishing activity, 37,38 and many others.…”

Road Network Guided Fine-Grained Urban Traffic Flow Inference

“…Due to its great social benefits, this problem has recently received increasing attention in both industry and academic communities. In most preliminary works [4]- [6], the city being studied is first divided into a coarse grid map and a fine grid map on the basis of latitude and longitude coordinates, as shown in Fig. 1-(b,c).…”

“…In this case, the road network can be regarded as an instructive prior knowledge for traffic flow inference. Nevertheless, most previous methods [4]- [6] were not aware of this knowledge. Second, how to model the road network is still an open problem.…”