Population distribution data with high spatiotemporal resolution are of significant value and fundamental to many application areas, such as public health, urban planning, environmental change, and disaster management. However, such data are still not widely available due to the limited knowledge of complex human activity patterns. The emergence of location-based service big data provides additional opportunities to solve this problem. In this study, we integrated ambient population data, nighttime light data, and building volume data; innovatively proposed a spatial downscaling framework for Baidu heat map data during work time and sleep time; and mapped the population distribution with high spatiotemporal resolution (i.e., hourly, 100 m) in Beijing. Finally, we validated the generated population distribution maps with high spatiotemporal resolution using the highest-quality validation data (i.e., mobile signaling data). The relevant results indicate that our proposed spatial downscaling framework for both work time and sleep time has high accuracy, that the distribution of the population in Beijing on a regular weekday shows “centripetal centralization at daytime, centrifugal dispersion at night” spatiotemporal variation characteristics, that the interaction between the purpose of residents’ activities and the spatial functional differences leads to the spatiotemporal evolution of the population distribution, and that China’s “surgical control and dynamic zero COVID-19” epidemic policy was strongly implemented. In addition, our proposed spatial downscaling framework can be transferred to other regions, which is of value for governmental emergency measures and for studies about human risks to environmental issues.

Aquaculture plays a key role in achieving Sustainable Development Goals (SDGs), while it is difficult to accurately extract single-object aquaculture ponds (SOAPs) from medium-resolution remote sensing images (Mr-RSIs). Due to the limited spatial resolutions of Mr-RSIs, most studies have aimed to obtain aquaculture areas rather than SOAPs. This study proposed an object-oriented method for extracting SOAPs. We developed an iterative algorithm combining grayscale morphology and edge detection to segment water bodies and proposed a segmentation degree detection approach to select and edit potential SOAPs. Then a classification decision tree combining aquaculture knowledge about morphological, spectral, and spatial characteristics of SOAPs was constructed for object filter. We selected a 707.26 km² study region in Sri Lanka and realized our method on Google Earth Engine (GEE). A 25.11 ${\mathrm{km}}^2$ plot was chosen for verification, where 433 SOAPs were manually labeled from 0.5 m high-resolution RSIs. The results showed that our method could extract SOAPs with high accuracy. The relative error of total areas between extracted result and the labeled dataset was 1.13%. The MIoU of the proposed method was 0.6965, representing an improvement of between 0.1925 and 0.3268 over the comparative segmentation algorithms provided by GEE. The proposed method provides an available solution for extracting SOAPs over a large region and shows high spatiotemporal transferability and potential for identifying other objects.

Accurate spatial population distribution information, especially for metropolises, is of significant value and is fundamental to many application areas such as public health, urban development planning and disaster assessment management. Random forest is the most widely used model in population spatialization studies. However, a reliable model for accurately mapping the spatial distribution of metropolitan populations is still lacking due to the inherent limitations of the random forest model and the complexity of the population spatialization problem. In this study, we integrate gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM) and support vector regression (SVR) through ensemble learning algorithm stacking to construct a novel population spatialization model we name GXLS-Stacking. We integrate socioeconomic data that enhance the characterization of the population’s spatial distribution (e.g., point-of-interest data, building outline data with height, artificial impervious surface data, etc.) and natural environmental data with a combination of census data to train the model to generate a high-precision gridded population density map with a 100 m spatial resolution for Beijing in 2020. Finally, the generated gridded population density map is validated at the pixel level using the highest resolution validation data (i.e., community household registration data) in the current study. The results show that the GXLS-Stacking model can predict the population’s spatial distribution with high precision (R² = 0.8004, MAE = 34.67 persons/hectare, RMSE = 54.92 persons/hectare), and its overall performance is not only better than the four individual models but also better than the random forest model. Compared to the natural environmental features, a city’s socioeconomic features are more capable in characterizing the spatial distribution of the population and the intensity of human activities. In addition, the gridded population density map obtained by the GXLS-Stacking model can provide highly accurate information on the population’s spatial distribution and can be used to analyze the spatial patterns of metropolitan population density. Moreover, the GXLS-Stacking model has the ability to be generalized to metropolises with comprehensive and high-quality data, whether in China or in other countries. Furthermore, for small and medium-sized cities, our modeling process can still provide an effective reference for their population spatialization methods.

The evaluation of mortality in earthquake-stricken areas is vital for the emergency response during rescue operations. Hence, an effective and universal approach for accurately predicting the number of casualties due to an earthquake is needed. To obtain a precise casualty prediction method that can be applied to regions with different geographical environments, a spatial division method based on regional differences and a zoning casualty prediction method based on support vector regression (SVR) are proposed in this study. This study comprises three parts: (1) evaluating the importance of influential features on seismic fatality based on random forest to select indicators for the prediction model; (2) dividing the study area into different grades of risk zones with a strata fault line dataset and WorldPop population dataset; and (3) developing a zoning support vector regression model (Z-SVR) with optimal parameters that is suitable for different risk areas. We selected 30 historical earthquakes that occurred in China’s mainland from 1950 to 2017 to examine the prediction performance of Z-SVR and compared its performance with those of other widely used machine learning methods. The results show that Z-SVR outperformed the other machine learning methods and can further enhance the accuracy of casualty prediction.

Accurate knowledge of urban forest patterns contributes to well-managed urbanization, but accurate urban tree canopy mapping is still a challenging task because of the complexity of the urban structure. In this paper, a new method that combines double-branch U-NET with multi-temporal satellite images containing phenological information is introduced to accurately map urban tree canopies. Based on the constructed GF-2 image dataset, we developed a double-branch U-NET based on the feature fusion strategy using multi-temporal images to obtain an accuracy improvement with an IOU (intersection over union) of 2.3% and an F1-Score of 1.3% at the pixel level compared to the U-NET using mono-temporal images which performs best in existing studies for urban tree canopy mapping. We also found that the double-branch U-NET based on the feature fusion strategy has better accuracy than the early fusion strategy and decision fusion strategy in processing multi-temporal images for urban tree canopy mapping. We compared the impact of image combinations of different seasons on the urban tree canopy mapping task and found that the combination of summer and autumn images had the highest accuracy in the study area. Our research not only provides a high-precision urban tree canopy mapping method but also provides a direction to improve the accuracy both from the model structure and data potential when using deep learning for urban tree canopy mapping.