Given global climate change and rapid land cover changes due to human activities, accurately identifying, extracting, and monitoring the long-term evolution of wetland resources is profoundly significant, particularly in areas with fragile ecological conditions. Gansu Province, located in northwest China, contains all wetland types except coastal wetlands. The complexity of its wetland types has resulted in a lack of accurate and comprehensive information on wetland changes. Using Gansu Province as a case study, we employed the GEE platform and Landsat time-series satellite data, combining high-quality sample datasets with feature-optimized multi-source feature sets. The random forest algorithm was utilized to create wetland classification maps for Gansu Province across eight periods from 1987 to 2020 at a 30 m resolution and to quantify changes in wetland area and type. The results showed that the wetland mapping method achieved robust classification results, with an average overall accuracy (OA) of 96.0% and a kappa coefficient of 0.954 across all years. The marsh type exhibited the highest average user accuracy (UA) and producer accuracy (PA), at 96.4% and 95.2%, respectively. Multi-source feature aggregation and feature optimization effectively improve classification accuracy. Topographic and seasonal features were identified as the most important for wetland extraction, while textural features were the least important. By 2020, the total wetland area in Gansu Province was 10,575.49 km², a decrease of 4536.86 km² compared to 1987. The area of marshes decreased the most, primarily converting into grasslands and forests. River, lake, and constructed wetland types generally exhibited an increasing trend with fluctuations. This study provides technical support for wetland ecological protection in Gansu Province and offers a reference for wetland mapping, monitoring, and sustainable development in arid and semi-arid regions.

New urbanization often leads to land-use and land-cover change (LUCC), which inevitably affects ecosystem services (ESs). Although it is traditionally believed that urbanization reduces ecosystem services, some studies have shown that reasonable urban development facilitates ecosystem conservation. Previous studies have focused on the impacts of urbanization on either LUCC or ESs, with fewer dynamic assessments of the coordination of the three. Taking China’s contiguous poor areas (CPAs) as an example, this study applied coupling coordination, path analysis, and a multiscale geographically weighted regression (MGWR) model to identify the dynamic relationship among urbanization, land use, and the environment and then predicted their coupling coordination under shared socioeconomic pathways (SSP-RCP) in 2035 using the Patch Generation Land Use Simulation (PLUS) and a random forest model. The results of the study show that (1) urbanization, land-use change, and environmental loads in China’s CPAs showed an inconsistent upward trend. There was a slight overall decrease in ESs before 2013, which was consistent with the early stage of the Environmental Kuznets Curve (EKC); after that time, they showed different characteristics. (2) From 2000 to 2018, the coupling coordination degree of CPAs decreased slightly due to urbanization, geographic factors, and grassland and unused land. LUCC was essential to maintaining the system balance. The SN (southern contiguous poverty area) was at a basic level of coordination, while the other regions showed a moderate imbalance. (3) According to scenario projections, the degree of coupling coordination in all regions will increase by 2035. Environmental prioritization and sustainable routes are the best options for CPAs’ development. The SN is more stable, while the WN (western contiguous poverty area) has the lowest coupling coordination. (4) Environmentally friendly urbanization should be carried out with land management tailored to local conditions. Measures that could be recommended include establishing ecological pilot zones in SN areas, prioritizing the protection of grassland ecosystems in WN areas, and promoting intensive land use in the NN (northern contiguous poverty area). The present study offers a novel perspective on the interplay between the economy and the environment at the county level and achieves predictive coupling coordination through the integration of PLUS and random forest models. This investigation into coordinated urbanization–LUCC–ES development in CPAs yields valuable insights for enhancing environmental and economic well-being in similar regions within China, as well as globally.

Arid and semiarid wetlands, the core geographical unit of desert oases, significantly benefit and improve the ecological environment. In this study, we systematically compared the spatiotemporal dynamics and driving forces of natural and constructed wetlands in arid and semiarid regions of northern China from 1995 to 2019. For these comparisons, we utilized a land-use transition matrix, partial least-squares–structural equation model (PLS-SEM), and geographically weighted regression (GWR) model. The results showed that (1) the area of wetlands as a whole showed an upward trend, with natural and constructed wetlands increasing by 4.16% and 11.86%, respectively. The increases mainly resulted from conversions of grassland and other lands (shrub, sparse vegetation, and bare land). (2) The direct dominant factors that drove natural wetland changes were soil and terrain, while those that drove constructed wetlands were human disturbances. Human disturbance, by affecting soil, had a higher significant indirect effect on natural wetlands. Heat, by affecting moisture, had the greatest indirect effect on constructed wetlands. (3) The sensitivity of natural and constructed wetlands to the responses of different drivers showed significant spatial heterogeneity. This study explores the interaction and driving mechanisms of human and natural attributes on natural and constructed wetlands and provides a scientific foundation for the restoration and sustainable development of wetlands in arid and semiarid areas.