The eco-system in the Qinghai-Tibet Plateau (QTP) is extremely fragile, and highly vulnerable to climate change. Knowledge of the changes in the ecological conditions is vital to mitigate the impact of climate change. In this study, we investigated the trend of ecological conditions of the QTP using the remotely sensed ecological index (RSEI), which is the first PCA (principal component analysis) axis of the four indexes derived from the MODIS (Moderate resolution Imaging Spectroradiometer) images captured in the growing season of 2000–2020. The four indexes, i.e., NDVI (normalized difference vegetation index), heat (land surface temperature, LST), wetness (tasseled cap wetness index, WET) and dryness (normalized difference impervious surface index, NDBSI), were calculated on the Google Earth Engine platform. Using land use cover change (LUCC) data, long-term meteorological records and the supplementary annual livestock production, we explored the drivers of spatiotemporal changes in the RSEI. The results show the following points: (1) the ecological conditions of the QTP have remarkable spatiotemporal variations. There were two ecological degradation periods, one of them occurred in the central region during 2005–2010, mainly attributed to the rising temperatures and decreasing precipitation. The other occurred during 2015–2020, driven primarily by overgrazing in the southwest. From 2000 to 2005, it was a period of rapid ecological restoration in the ecologically fragile northeast region. (2) The contribution rate of pc1 was stable at 60%, while the contribution rate of pc2 remained below 40%, indicating that pc1 demonstrated most of the characteristics of the four indexes. The correlation coefficients between NDVI and WET with pc1 are both positive, while LST and NDBSI have negative correlation coefficients, i.e., negative effects. This is consistent with the actual situation. (3) Overgrazing caused grass degradation in the southwest area of the QTP, which might be the main reason for the poor ecological conditions (i.e., low RSEI value) during 2015–2020. (4) Temperature and precipitation showed an increasing trend during the study period. A warmer and wetter climate is expected to have profound impacts on the ecosystems in QTP and practices should be concentrated on identifying climate-sensitive ecosystem components and designating adaptative options.

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.

Climate change has become an important cause of the loss of bird habitat and changes in bird migration and reproduction. The lesser white-fronted goose (Anser erythropus) has a wide range of migratory habits and is listed as vulnerable on the IUCN (International Union for Conservation of Nature) Red List. In this study, the distribution of suitable breeding grounds for the lesser white-fronted goose was assessed in Siberia, Russia, using a combination of satellite tracking and climate change data. The characteristics of the distribution of suitable breeding sites under different climate scenarios in the future were predicted using the Maxent model, and protection gaps were assessed. The analysis showed that under the background of future climate change, temperature and precipitation will be the main climatic factors affecting the distribution of breeding grounds, and the area associated with suitable breeding habitats will present a decreasing trend. Areas listed as an optimal habitat only accounted for 3.22% of the protected distribution; however, 1,029,386.341 km² of optimal habitat was observed outside the protected area. Obtaining species distribution data is important for developing habitat protection in remote areas. The results presented here can provide a basis for developing species-specific habitat management strategies and indicate that additional attention should be focused on protecting open spaces.

The middle and lower reaches of the Yangtze River are the most important areas for geese to overwinter in the East Asian–Australasian Flyway, where about 180,000 geese fly to overwinter each year. Over the past 20 years, the region has experienced extensive and rapid land cover changes that may have exceeded the adaptability of geese, and have led to suitable goose habitat area loss, thereby, reducing the stability of the geese population. In order to identify the suitable goose habitat areas in this region, based on ensemble modeling and satellite tracking data, in this study, we simulated the spatial distribution changes in the suitable goose habitat areas over the past 20 years. The results showed that the suitable goose habitat areas had suffered varying degrees of loss, among which, the lesser white-fronted goose had the greatest suitable goose habitat area loss of over 50%. Moreover, we found that wetlands, lakes, and floodplains were the key components of suitable goose habitat areas, and the categories (land use) showed significant differences in different periods (p < 0.01). This may be one of the main reasons for the decrease in suitable goose habitat areas. The results of this study provide an important reference for the adaptive management and protection of geese in the middle and lower reaches of the Yangtze River.