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 advent of a range of high-precision NPP products, including MODIS NPP, MOD17 NPP, and GIMMS NPP, has sparked growing interest in the study of Earth’s ecosystems. In order to enhance comprehension of ecosystem health, in order to facilitate the development of rational resource management and environmental conservation policies, this investigation employs the MOD17A3 dataset to analyze historical variations in Net Primary Productivity (NPP) within Shanxi Province from 2001 to 2020, while also exploring future trends. The Theil–Sen median trend analysis and Mann–Kendall test are commonly used methods for analyzing time series data, employed to study the spatiotemporal trends and variations in NPP. The Grey Wolf Optimization–Support Vector Machine (GWO–SVM) model combines optimization algorithms and machine learning methods, enhancing the predictive capacity of the model for future NPP time series changes. Conversely, the Hurst exponent utilizes historical NPP trends to assess the persistence characteristics of NPP and predict future spatial variations in NPP. This study additionally investigates the natural driving factors of NPP using the Geographic Detector approach. The key findings of this study are as follows. (1) Overall, NPP in Shanxi Province exhibits a fluctuating upward trend from 2001 to 2020, with an average value of 206.278 gCm⁻²a⁻¹. Spatially, NPP exhibits a northwest–low and southeast–high pattern, with significant spatial heterogeneity and considerable variability. (2) The average Hurst exponent is 0.86, indicating a characteristic of strong persistence in growth in future NPP. Regions with strong or higher persistent growth account for 95.54% of the total area. (3) According to the CMIP6 climate scenarios, NPP is projected to gradually increase from 2025 to 2030. (4) The interactive effects between natural factors contribute more to NPP variations than individual factors, with the rainfall–elevation interaction having the highest contribution percentage.