Accurate mapping of global urban and rural settlements is crucial for understanding their distinct expansion patterns and ecological impacts. However, existing global datasets focus mainly on urban settlements and ignore the delineation of rural settlements. Therefore, this study proposed a framework for delineating between urban and rural settlements based on dynamic thresholds defined by area and light brightness and constructed the first global 100-meter resolution urban and rural settlements dataset (GURS) spanning from 2000 to 2020, integrating GHS-BUILT-S R2023A, NPP-VIIRS-like nighttime light, and OpenStreetMap data. An accuracy assessment of 44,474 independent samples showed that GURS achieved an overall accuracy of 91.22% with a kappa coefficient of 0.85, outperforming nine multi-scale reference datasets in delineating global urban and rural settlements. GURS offers deep insights into the dynamics of global settlements, facilitating urban-rural comparative studies on socio-economic characteristics, environmental impacts, and governance modes, thereby enhancing the sustainable management of settlements.

Open public places, such as pedestrian streets, parks, and squares, are vulnerable when the pedestrians thronged into the sidewalks. The crowd count changes dynamically over time with various external factors, such as surroundings, weekends, and peak hours, so it is essential to predict the accurate and timely crowd count. To address this issue, this study introduces graph convolutional network (GCN), a network-based model, to predict the crowd flow in a walking street. Compared with other grid-based methods, the model is capable of directly processing road network graphs. Experiments show the GCN model and its extension STGCN consistently and significantly outperform other five baseline models, namely HA, ARIMA, SVM, CNN and LSTM, in terms of $RMSE$, $MAE$ and R². Considering the computation efficiency, the standard GCN model was selected to predict the crowd. The results showed that the model obtains superior performances with higher prediction precision on weekends and peak hours, of which R² are above 0.9, indicating the GCN model can capture the pedestrian features in the road network effectively, especially during the periods with massive crowds. The results will provide practical references for city managers to alleviate road congestion and help pedestrians make smarter planning and save travel time.