Construct social-behavioral association network to study management impact on waterbirds community ecology using digital video recording cameras

Home Range and Habitat Use of the Swan Goose (Anser cygnoides L. 1758) during Wintering in the Seocheon Tidal Flat, South Korea, Using GPS-Based Telemetry

The Seocheon Tidal Flat is an important staging and wintering site for the Far East Russian population of Swan Goose (Anser cygnoides) in the East Asian–Australasian Flyway. However, rapid environmental changes for tourism in this area can threaten the survival of this vulnerable population by hindering sufficient rest and wintering; therefore, establishing protection strategies based on Swan Goose behavioral characteristics is necessary. Here, we estimated Swan Goose core home ranges and habitat use based on GPS tracking data collected at the Seocheon Tidal Flat in South Korea from 2017–2018. The home range of Swan Geese was estimated to be an area from Yubu Island in the south to Janggu Bay in the north; however, the core home range and habitat use characteristics differed significantly between daytime and nighttime (Day: 59.9 km2, Night: 40.3 km2, on average, 100% MCP). During the day (08:00–18:00), Swan Geese mostly spent time resting or feeding on tidal flats, especially those around tidal channels or paddy fields near Janggu Bay, whereas they mostly rested on sand dunes near Yubu Island along with the mudflats at Janggu Bay at night. Our results provide practical information on the habitat use of wintering Swan Geese population over time and indicate that Yubu Island is an important resting place. Hence, these results can contribute to evaluating threats to Swan Geese and establishing management and protection strategies for the Seocheon Tidal Flat, a major wintering site for the Far East Russian population of Swan Geese.

Unlocking the Potential of Deep Learning for Migratory Waterbirds Monitoring Using Surveillance Video

Estimates of migratory waterbirds population provide the essential scientific basis to guide the conservation of coastal wetlands, which are heavily modified and threatened by economic development. New equipment and technology have been increasingly introduced in protected areas to expand the monitoring efforts, among which video surveillance and other unmanned devices are widely used in coastal wetlands. However, the massive amount of video records brings the dual challenge of storage and analysis. Manual analysis methods are time-consuming and error-prone, representing a significant bottleneck to rapid data processing and dissemination and application of results. Recently, video processing with deep learning has emerged as a solution, but its ability to accurately identify and count waterbirds across habitat types (e.g., mudflat, saltmarsh, and open water) is untested in coastal environments. In this study, we developed a two-step automatic waterbird monitoring framework. The first step involves automatic video segmentation, selection, processing, and mosaicking video footages into panorama images covering the entire monitoring area, which are subjected to the second step of counting and density estimation using a depth density estimation network (DDE). We tested the effectiveness and performance of the framework in Tiaozini, Jiangsu Province, China, which is a restored wetland, providing key high-tide roosting ground for migratory waterbirds in the East Asian–Australasian flyway. The results showed that our approach achieved an accuracy of 85.59%, outperforming many other popular deep learning algorithms. Furthermore, the standard error of our model was very small (se = 0.0004), suggesting the high stability of the method. The framework is computing effective—it takes about one minute to process a theme covering the entire site using a high-performance desktop computer. These results demonstrate that our framework can extract ecologically meaningful data and information from video surveillance footages accurately to assist biodiversity monitoring, fulfilling the gap in the efficient use of existing monitoring equipment deployed in protected areas.

Habitat Quality and Social Behavioral Association Network in a Wintering Waterbirds Community

Migratory waterbirds concentrated in freshwater ecosystems in mosaic environments rely on quality habitats for overwintering. At West Dongting Lake National Nature Reserve (WDLNNR), China, land-use change and hydrology alternation are compounding factors that have affected important wintering areas for migratory waterbirds. Presently, changes in the hydrology and landscape have reshaped natural wintering habitats and their availability, though the impact of hydrological management on habitat selection of wintering waterbirds is largely unknown. In this study, we classified differentially managed habitats and calculated their area using the normalized difference vegetation index (NDVI) to evaluate suitable habitat availability over the study period (2016–2017 and 2017–2018 wintering periods). We then used social behavioral association network (SBAN) model to compare habitat quality through species-species social interactions and species-habitat associations in lakes with different hydrological management. The results indicated that social interactions between and within species structured wintering waterbirds communities, which could be dominated by one or more species, while dominant species control the activities of other co-existing species. Analysis of variance (ANOVA) tests indicated significant differences in SBAN metrics between lakes (p = 0.0237) and habitat (p < 0.0001) levels. Specifically, lakes with managed hydrology were preferred by more species. The managed lakes had better habitat quality in terms of significantly higher habitat areas (p < 0.0001) and lower habitat transitions (p = 0.0113). Collectively, our findings suggest that proper hydrological management can provide continuous availability of quality habitats, especially mudflats and shallow waters, for a stable SBAN to ensure a wintering waterbirds community with more sympatric species in a dynamic environment.