The degradation of world‐wide estuarine ecosystems as a result of accelerated human population growth accompanied by agricultural, industrial and urban development justifies a strong need to find efficient ways to manage and protect these sensitive environments. Starting from 2001, the authors have been involved in an interdisciplinary research project aiming to develop environmental indicators for integrated estuarine ecosystem assessment in the Gulf of Mexico. As part of this project, a study was conducted to characterize land‐use and land‐cover changes with the Pensacola estuarine drainage area as a case. The Pensacola bay was targeted because it is one of few exemplary large river‐driven estuarine systems across the northern Gulf of Mexico. The study had two major sections. The first part was dedicated to the development of an improved method for coastal land‐use and land‐cover mapping, which was built upon hierarchical classification and spatial reclassification. An image scene was separated into urban and rural regions early in the classification, with a ‘mask’ defined by road intersection density slices combined with road buffers. Each part was classified independently in its most effective context and, later, both were merged to form a complete map. In spatial reclassification, image interpretation procedures, auxiliary vector data and a variety of Geographical Information System (GIS) functions were synthesized to resolve spectral confusion and improve mapping accuracy. This method was used to map land use and land cover from Landsat Thematic Mapper/Enhanced Thematic Mapper Plus (TM/ETM+) imagery for 1989, 1996 and 2002, respectively. The accuracy assessment shows that the overall classification errors were less than 10%. The second part focused on the analysis of the spatio‐temporal dynamics of estuarine land‐use and land‐cover changes by using post‐classification comparison and GIS overlay techniques. The project has revealed that a substantial growth of low‐density urban land occurred in the lower drainage basin in connection with population and housing growth, as well as a significant increase of mixed forest land in the upper watershed as a result of active logging and harvesting operations. These growths were achieved at the cost of evergreen forest and wetlands, thus compromising safeguards for water quality, biodiversity of aquatic systems, habitat structure and watershed health in the Pensacola estuarine drainage area.

Guangzhou has experienced a rapid urbanization since 1978 when China initiated the economic reform, resulting in significant land use/cover changes (LUC). To produce a time series of accurate LUC dataset that can be used to study urbanization and its impacts, Landsat imagery was used to map LUC changes in Guangzhou from 1987 to 2015 at a three-year interval using a multiple classifier system (MCS). The system was based on a weighted vector to combine base classifiers of different classification algorithms, and was improved using the AdaBoost technique. The new classification method used support vector machines (SVM), C4.5 decision tree, and neural networks (ANN) as the training algorithms of the base classifiers, and produced higher overall classification accuracy (88.12%) and Kappa coefficient (0.87) than each base classifier did. The results of the experiment showed that, based on the accuracy improvement of each class, the overall accuracy was improved effectively, which combined advantages from each base classifier. The new method is of high robustness and low risk of overfitting, and is reliable and accurate, and could be used for analyzing urbanization processes and its impacts.

Context: Habitat connectivity is essential for the long-term persistence of species, but is commonly disregarded in climate change impact studies. The Tibetan Plateau contains a biome rich in endemic ungulates, which are highly sensitive to climatic variations and deserve particular attention in conservation planning against climate change. Objectives: We evaluated the response and vulnerability of habitat connectivity to climate change for four ungulate species endemic to the Tibetan Plateau, and examined the robustness of protected areas (PAs) for the conservation of these species under climate change. Methods: For each focal species, we developed ecological niche models to predict the spatial variations in habitat under climate change and conducted a network-theoretical analysis to estimate the consequent changes in habitat connectivity. Moreover, we used the circuit theory to characterize dispersal patterns of these species and conducted gap analyses to estimate the contribution of existing PAs to the conservation of these species. Results: The four focal species will experience a remarkable connectivity loss that outpaced their habitat loss in response to climate change. Currently, 53.39 and 46.64% of the areas that could contribute to the habitat suitability and connectivity, respectively, of these species are unprotected. These values could further increase under future climate conditions. Conclusions: Climate-driven habitat variations may lead to the loss of key connectivity areas between the habitats of ungulates, causing disproportionate decrease in habitat connectivity. The existing PAs on the Tibetan Plateau are not robust for the conservation of the four ungulates. Adjustment of certain key PAs may help to address the conservation gaps.