Assessing land use-based changes in ecosystem service values (ESVs) is a beneficial approach for land resource planning and ecologically sustainable development. Located in the south of China, Guilin is one of the first Sustainable Development Goals (SDGs) Innovation Demonstration Zones set up by China. It is a typical ecotourism city with an important ecological and economic status. In recent years, the time series, model fit, and spatial scale of ESV assessment in Guilin have needed to be improved in the context of rapid urbanization and natural change. In this study, an improved ESV assessment methodology was utilized to incorporate the effects of biomass, soil conservation, and precipitation and to adjust the equivalence factors based on the ratio of geographic and environmental parameters to the national average to make them heterogeneous in time and space in improving the practical fit of the assessment results. The study analyzed the evolution of land use and its contribution to ESVs in Guilin from 2000 to 2020. County and 3 km × 3 km grid scales were combined to reveal both broad and detailed spatial and temporal characteristics of ESVs in Guilin. The results show that the expansion of building land in Guilin is notable, and the amount of land use transfer continues to increase. ESVs fluctuated in a lateral S-shape, with significant differences in ESV effectiveness between counties, consistently high ESVs near waterbodies and ecological reserves, and low ESVs near commercial and industrial land and cultivated land. Despite the recovery trend in ESVs in the later years, there is still a gap between 2020 and 2000. To a certain extent, it helps Guilin optimize land allocation from different perspectives and promote ecological improvement and resource planning optimization.

Wetlands represent one of the three principal ecosystems and serve a vital function in the protection of water resources and the regulation of climate. However, wetlands are currently experiencing significant challenges, particularly in the agriculturally productive wetlands of the Heilongjiang River Basin, which have been considerably impacted by human activities. This study focuses on three representative wetlands situated within the Heilongjiang River Basin. This study analyses changes in wetland area and landscape patterns from 2002 to 2022, as well as the impact of agriculture and impervious surface expansion on the wetlands. The findings indicate that agricultural expansion is the primary driver of wetland area loss. The wetland area affected by agriculture demonstrates the most significant change, with the largest observed shift reaching 47.2%. The expansion of impervious surfaces was found to have a significant impact on wetland fragmentation, resulting in a notable decrease in wetland connectivity. This was evidenced by a reduction in the average patch size, which decreased by 14.68 ha over the decade from 2007 to 2017, a period during which impervious surfaces expanded. This paper identifies the distinctions in the influence of diverse human activities on wetland landscape patterns in the Heilongjiang Basin and employs natural samples for control, thereby attenuating the impact of the natural environment. This study offers a novel perspective on the processes of wetland change and the maintenance of wetland health, which is crucial for the realisation of clean water and sanitation (Sustainable Development Goal 6.6).

Monitoring changes in water-related ecosystems is central to SDG 6.6.1, yet most existing wetland products are produced at annual scales and therefore cannot resolve seasonal transitions in wetland extent and type composition. This limitation is particularly important in delta wetlands, where river discharge, tidal inundation, vegetation phenology, and human activities drive pronounced intra-annual wetland dynamics. Accurately characterizing these seasonal dynamics is essential for understanding wetland ecological functions, evaluating hydrological regulation capacity, and supporting adaptive conservation and management. However, seasonal-scale wetland characterization remains constrained by the lack of temporally explicit labels, frequent cloud contamination, and severe sample imbalance among rare wetland classes. To address these challenges, this study proposes STEP-Unet, a weakly supervised framework that derives seasonally resolved wetland type information from annual wetland products without additional manual annotations. Experimental results in the Yellow River Delta demonstrate that STEP-Unet consistently outperforms direct classification using annual labels across all seasons, achieving an overall accuracy of 0.905 and a mean intersection-over-union of 0.800. The model was further applied to characterize seasonal wetland class dynamics in the Yellow River Delta from 2020 to 2022, revealing clear intra-annual transitions among wetland types. These results indicate that refining annual wetland products into seasonally explicit wetland class information can provide a more detailed basis for SDG 6.6.1 monitoring and adaptive management of dynamic delta wetland ecosystems.