In the field of building extraction, many convolutional neural network (CNN)-based methods have been developed to solve the problem of the irregular boundaries in their predictions. The prevailing approach is to build an additional edge segmentation branch or obtain accurate vector components of buildings. However, pixel-based methods still cannot obtain an accurate location of the boundary, while vector extraction will bring the problem of sample imbalance and missing detection. In this work, we utilize the complementarity of the two types of methods and propose the line segment collaborate segmentation (LCS) framework. In the proposed LCS framework, semantic segmentation provides location guidance for vector extraction, while vector extraction provides precise positioning for semantic segmentation. In this way, the two tasks can leverage their respective strengths. The results on three datasets show that the performance of vector extraction and semantic segmentation is improved simultaneously using the LCS framework, which proves the effectiveness of our method. At the same time, our framework is flexible and can be embedded in other vector extraction methods to improve performance.

The accessibility provided by the transportation system plays an essential role in driving urban growth and urban functional land use changes. Conventional studies on land use simulation usually simplified the accessibility as proximities and adopted the grid-based simulation strategy, leading to the insufficiencies of characterizing spatial geometry of land parcels and simulating subtle land use changes among urban functional types. To overcome these limitations, an Accessibility-interacted Vector-based Cellular Automata (A-VCA) model was proposed for the better simulation of realistic land use change among different urban functional types. The accessibility at both local and zonal scales derived from actual travel time data was considered as a key driver of fine-scale urban land use changes and was integrated into the vector-based CA simulation process. The proposed A-VCA model was tested through the simulation of urban land use changes in the City of Toronto, Canada, during 2012–2016. A vector-based CA without considering the driving factor of accessibility (VCA) and a popular grid-based CA model (Future Land Use Simulation, FLUS) were also implemented for comparisons. The simulation results reveal that the proposed A-VCA model is capable of simulating fine-scale urban land use changes with satisfactory accuracy and good morphological feature (kappa = 0.907, figure of merit = 0.283, and cumulative producer’s accuracy = 72.83% ± 1.535%). The comparison also shows significant outperformance of the A-VCA model against the VCA and FLUS models, suggesting the effectiveness of the accessibility-interactive mechanism and vector-based simulation strategy. The proposed model provides new tools for a better simulation of fine-scale land use changes and can be used in assisting the formulation of urban and transportation planning.

Fine knowledge of the spatiotemporal distribution of the population is fundamental in a wide range of fields, including resource management, disaster response, public health, and urban planning. The United Nations’ Sustainable Development Goals also require the accurate and timely assessment of where people live to formulate, implement, and monitor sustainable development policies. However, due to the lack of appropriate auxiliary datasets and effective methodological frameworks, there are rarely continuous multi-temporal gridded population data over a long historical period to aid in our understanding of the spatiotemporal evolution of the population. In this study, we developed a framework integrating a ResNet-N deep learning architecture, considering neighborhood effects with a vast number of Landsat-5 images from Google Earth Engine for population mapping, to overcome both the data and methodology obstacles associated with rapid multi-temporal population mapping over a long historical period at a large scale. Using this proposed framework in China, we mapped fine-scale multi-temporal gridded population data (1 km × 1 km) of China for the 1985–2010 period with a 5-year interval. The produced multi-temporal population data were validated with available census data and achieved comparable performance. By analyzing the multi-temporal population grids, we revealed the spatiotemporal evolution of population distribution from 1985 to 2010 in China with the characteristic of concentration of the population in big cities and the contraction of small- and medium-sized cities. The framework proposed in this study demonstrates the feasibility of mapping multi-temporal gridded population distribution at a large scale over a long period in a timely and low-cost manner, which is particularly useful in low-income and data-poor areas.