Results were disseminated via an academic paper in Ocean-Land-Atmosphere Research (a Science Partten Journal) and shared in AAASScience WeChat Public (Official Media of American Association for the Advancement of Science in China). The findings were also included as a case study in the Yangtze River Delta Pilot Site and included in the support of major research projects on oceanography by the National Natural Science Foundation (NSFC).

By systematically integrating remote sensing data, deep learning, and ecological analysis, the project has significantly advanced wetland conservation methodologies, offering scalable solutions for biodiversity preservation,  biological invasion control,  and ecosystem management globally.

Exploring and analysing the key drivers of vegetation spatial and temporal distribution is of practical significance for monitoring the expansion of coastal wetland vegetation, species diversity conservation and sustainable management of coastal wetlands.

• Spartina alterniflora was influenced by marine factors (e.g., salinity and wave height).
• Phragmites australis and Suaeda salsa were driven by rainfall, anthropogenic activities, and interspecific competition.

Understanding these factors supports better management of invasive species and promotes biodiversity conservation.

Using spatial-temporal data, the long-term distribution characteristics of wetland vegetation were analyzed. Tools such as the landscape pattern index, migration modeling, and expansion/decline dynamics identified distinct trends:

• Spartina alterniflora patches showed high aggregation and a decreasing trend.
• Phragmites australis and Suaeda salsa patches displayed lower aggregation, higher fragmentation, and increasing trends.
• Vegetation migration patterns revealed significant spatial and temporal heterogeneity, with vegetation distributed in bands along the terrestrial gradient.

A comprehensive database was created, integrating remote sensing-derived vegetation cover with key environmental, climate, and human activity data. This includes metrics such as soil salinity, sea surface temperature, seawater salinity, and aquaculture pond locations, forming a robust foundation for further analyses.

A Gaussian function was applied to vegetation index time series to extract candidate features, while a deep learning algorithm identified three major vegetation types (Spartina alterniflora, Phragmites australis, and Suaeda salsa). Field validation confirmed the model's accuracy, enabling precise vegetation classification from 1990 to 2022.

Using the Google Earth Engine (GEE) platform, Landsat TM/OLI series remote sensing data from 1990 to 2022 were collected, covering TM5, ETM+7, OLI8, and OLI9. Key spectral bands (near-infrared, red, and green light) were fused to ensure high-quality data for subsequent analysis.

Based on results from monitoring data and facilitated feedback discussions with the village grazing committees, rangeland restoration activities are identified as appropriate. This often requires the existing village grazing plan to be adapted and evolve with the changing state of the rangelands. For example, in Ngoley village, data collected over two years indicated one particularly problematic species (Sphaeranthus - locally called “Masida”) that proliferated significantly during a prolonged dry season and limited the regrowth of palatable species after the rains. To prevent further proliferation, an uprooting plan was designed and implemented based on the best practices for removing this particular species. Immediately after the first round of uprooting, the data show a drop in the species frequency and subsequent months of monitoring provide further evidence to suggest that native, palatable grasses are recovering in the treated plots. These targeted interventions directly contribute to GBF Target 1 by integrating biodiversity considerations into local planning and land use, and Target 2 by restoring degraded ecosystems. Furthermore, by improving ecological function and resilience, these efforts enhance the rangeland’s capacity to withstand climate variability, supporting both biodiversity and the well-being of local communities.

The village grazing committee and interested community members then come together at a Conservation Technology Center (CTC) for Rangeland Data Feedback Meetings facilitated jointly by an APW team member and the habitat monitors. While the dashboards are available on any mobile device, the CTCs allow for the community to convene for information sharing and participatory decision-making based on the data visually displayed on large screens. Oftentimes, the village grazing committee will review existing land use plans and verify their effectiveness with the data collected each month, adjusting pasture resource allocation accordingly. Finally, where the dashboards show rangeland degradation or proliferation of invasive species, the committee can use the data as justification to apply for financial support from APW for rangeland restoration interventions such as invasive species removal, reseeding, or soil erosion control projects. Through these data-informed, participatory mechanisms, community members play an active role in the stewardship and sustainable use of their natural resources. This model contributes to GBF Target 2 and 22 by empowering Indigenous Peoples and local communities to take leadership in habitat restoration, ensuring that their knowledge, rights, and participation are integral to conservation planning and implementation.