Landslide susceptibility mapping is considered to be a prerequisite for landslide prevention and mitigation. However, delineating the spatial occurrence pattern of the landslide remains a challenge. This study investigates the potential application of the stacking ensemble learning technique for landslide susceptibility assessment. In particular, support vector machine (SVM), artificial neural network (ANN), logical regression (LR), and naive Bayes (NB) were selected as base learners for the stacking ensemble method. The resampling scheme and Pearson’s correlation analysis were jointly used to evaluate the importance level of these base learners. A total of 388 landslides and 12 conditioning factors in the Lushui area (Southwest China) were used as the dataset to develop landslide modeling. The landslides were randomly separated into two parts, with 70% used for model training and 30% used for model validation. The models’ performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) and statistical measures. The results showed that the stacking-based ensemble model achieved an improved predictive accuracy as compared to the single algorithms, while the SVM-ANN-NB-LR (SANL) model, the SVM-ANN-NB (SAN) model, and the ANN-NB-LR (ANL) models performed equally well, with AUC values of 0.931, 0.940, and 0.932, respectively, for validation stage. The correlation coefficient between the LR and SVM was the highest for all resampling rounds, with a value of 0.72 on average. This connotes that LR and SVM played an almost equal role when the ensemble of SANL was applied for landslide susceptibility analysis. Therefore, it is feasible to use the SAN model or the ANL model for the study area. The finding from this study suggests that the stacking ensemble machine learning method is promising for landslide susceptibility mapping in the Lushui area and is capable of targeting areas prone to landslides.

The impact of human activities on vegetation has been the focus of much research, but the impact on radiation energy through surface albedo associated with vegetation greenness and length of the growth season is still not well documented. Based on the land cover data for the years 2000 and 2015, this study first divided the land cover change in Beijing from 2000 to 2015 into five types according to the impact of human activities and vegetation resilience, namely, old urban areas (OU), urban expansion areas (UE), cropland (CP), mixed pixel areas (MP, which means the land covers other than urban expansion which had changed from 2000 to 2015), and the residual vegetation cover areas (pure pixels (PP), dominated by natural and seminatural vegetation, such as grassland, forest, and wetland). Then, we calculated the direct radiative forcing from the albedo change from 2000 to 2015 and analyzed the effect of vegetation on the albedo under different land cover types based on multi-resource Moderate Resolution Imaging Spectroradiometer (MODIS) products of vegetation, albedo, and solar radiation. The results showed that the most typical changes in land cover were from urban expansion. By comparing the PP with the four human-affected land cover types (OU, UE, MP, and CP), we confirmed that the radiative forcing increment between 2001–2003 and 2013–2015 in PP (0.01 W/m²) was much smaller than that in the four human-affected land cover types (the mean increment was 0.92 W/m²). This study highlights that human activities affected vegetation growth. This, in turn, brought changes in the albedo, thereby enhancing radiative forcing in Beijing during 2000–2015.

China is urbanizing rapidly, but current research into the spatiotemporal characteristics of urbanization often ignores the spatial and evolutionary associations of cities. Using the theory of spatial polarization and diffusion, together with a systematic analysis method, this study examined the spatial development process of urbanization in the Yangtze River Delta (YRD) region of China during 1995–2015. Results showed clear patterns in the scale and hierarchy of regional urbanization. Shanghai ranked first as the regional growth pole, while Nanjing, Hangzhou, and Suzhou ranked second. The spatial linkage index of urbanization showed that 10 cities (including Shanghai, Suzhou, and Hangzhou) constituted the densest spatial linkage network. The diffused area often became spatially polarized before the polarization then weakened as a new diffusion stage developed. The study also revealed that the spatial correlation urbanization differences in the YRD generally decreased. The polarization index revealed increasing spatial integration and correlation of urbanization in the YRD. This study proved that each city had a different spatial role in relation to other cities during different stages of development. Investigation of the driving mechanism of regional urbanization indicated that industrial modernization and relocation within the region provided the main endogenous driving force for the formation of spatial polarization or diffusion. Our research provides important scientific support for regional development planning. Furthermore, our analysis of the impact of spatial correlation within cities or a region could provide an important reference in relation to the regional environment and public health.

The greenhouse gases sequestrated by ecosystems are of great relevance to global carbon cycle and climate regulation. However, it is time-consuming and laborious to conduct sampling analysis, and it is also difficult to analyze the variation of potential sequestration of various ecosystems for greenhouse gases in China. This study used six 5-year periods of land use data for China between 1990 and 2015 to analyze the changes of three natural ecosystems (forest, grassland, and wetland). Correspondingly, the potential sequestration of the three ecosystems for three major greenhouse gases (carbon dioxide CO₂, methane, and nitrous oxide) during the 25 years were simulated through a greenhouse gas value (GHGV) model. The GHGV model was found to be a reliable alternative to calculating the carbon sequestration of natural ecosystems in China. The total greenhouse gas sequestration of China’s natural ecosystems remained at around 267 Pg CO₂-equivalent; however, the greenhouse gas sequestration had decreased by 3.3 Pg CO₂-equivalent between 1990 and 2015. Comparison of the simulation results of the GHGV model based on the localized parameters and the model default parameters revealed that the simulated potential sequestration of the greenhouse gases for forest and wetland ecosystems (but not the grassland ecosystem) were smaller when run with localized parameters than the model default parameters. Moreover, the carbon sequestration of natural ecosystems was greater than the amount of anthropogenic carbon emissions, but the potential sequestration of natural ecosystems for greenhouse gas has become increasingly limited. Our study reveals the model can act as an important supplement for assessing the potential sequestration of the greenhouse gases for ecosystems at a regional scale.

Image analysis of the Yellow River beach area since 1987 provided land use and water body patterns to support effective agricultural and environmental management. Landsat and Sentinel-2A/B images, and data from the Third National Land Survey, were used to examine the water body and land use patterns. The continuous beach land since 1987 was calculated from annual vegetation and water body indexes while that of cultivated land was extracted from the Third National Land Survey. Object-Oriented Feature Extraction was used to extract staple crops. The results showed that 58.26% of the beach area was cultivated land. Continuous beach land covered an area of 1630.98 km² and was consisted of scattered patches that were unevenly distributed between the north and south banks of the Yellow River. The staple crop types in the beach area, winter wheat and summer corn accounted for 72.37% and 68.03% of the total cultivated land. Affected by the strategy on the Yellow River basin in China, as the ecological space and protection continue to increase, this study provides basic scientific references for the correct use of cultivated land resources and protection of the balance of soil and water resources dynamic utilization and balance of cultivated land protection and ecological protection.

The South-to-North Water Diversion (SNWD) provides significant benefits in facilitating water security and improving ecology in northern China. However, few studies have estimated the water value of the SNWD and the corresponding subsequent subsidies of the ecological migrants in Xichuan County displaced by the project. Based on the Google Earth Engine (GEE), this study analyzed the water ecosystem changes in Xichuan County in 2000–2020 and valued the water transfer of the SNWD. We calculated the water cost, the water value of the trunk line project, and the four provinces (Hebei, Henan, Beijing, and Tianjin) of CNY 4.04, 39.64, and 120.93 billion, respectively, and the proportion of the three was 1:10:30 during 2014–2020. The water ecosystem area showed a rapid increase when the SNWD became operational since the end of 2014. The subsequent annual subsidy gap of ecological migrants was CNY 0.84 billion, which only accounted for 4.31% of the gross profit of SNWD. Our results imply that relevant water sectors have sufficient profits to support corresponding subsequent subsidies for ecological migrants. Ecological migrants are a major challenge for water transfer projects. Overall, this study fills a gap of interactions between subsequent policies and ecological migrants and provides a typical case for managing the migration problem caused by sustainable water management worldwide.