DeepDPM: Dynamic Population Mapping via Deep Neural Network
This work addresses the challenge of obtaining fine-scaled, dynamic population data for applications like urban planning, but it is incremental as it builds on existing super-resolution and time-series methods.
The paper tackles the problem of generating dynamic, high-resolution population maps from coarse data by proposing DeepDPM, a deep neural network model that integrates spatial and temporal patterns using SRCNN and LSTM components. The results show that DeepDPM outperforms state-of-the-art methods on a real-life mobile dataset from Shanghai, enabling dynamic predictions across all-day time slots.
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 time-embedded 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.