The Long-Term Dynamic Monitoring and Ecological Stability Analysis of Dongting Lake Wetlands
Wetlands,due to their unique hydrological charac-teristics,experience drastic land cover changes. The lack of long-term,high-frequency land cover data has made it chal-lenging to dynamically monitor these changes in wetlands. This paper presents a dual-weight adaptive semantic segmen-tation model that combines feature change intensity and cate-gory balance,developed based on long-term temporal and spatially fused imagery. This model proposes a high-frequen-cy land cover classification mapping method,which effective-ly addresses the issues of continuity,high spatiotemporal reso-lution imagery,scarcity of classification samples,and high de-pendency on manual intervention in land cover mapping. It en-ables dynamic monitoring of land cover changes on a monthly scale in the Dongting Lake wetlands from 2001 to 2020.. The overall classification accuracy and Kappa coefficient of the proposed method are 86.78％ and 0.76,respectively. Based on long-term,high-frequency land cover change data,the land cover distribution in the Dongting Lake wetlands is closely related to the water level at Chenglingji station. The ecological stability shows an annual characteristic of initially decreasing then increasing,along with a seasonal characteris-tic of being higher in summer and lower in winter. The results of this study provide empirical evidence for targeted wetland conservation decision-making and flood management.
spatiotemporal fusionland cover classificationdeep learningDongting Lake wetlandsecological stability
NETL
NSTL
万方数据
