Climate change forecasts indicate that the frequency and intensity of extreme climate events will increase in the future; these changes will have important effects on ecosystem stability and function. An important arid region of the world, Central Asia has ecosystems that are extremely vulnerable to extreme weather events. However, few studies have investigated the resistance and resilience of this region’s ecosystems to extreme weather events. In this study, first, the extreme drought/wet threshold was calculated based on the 113-year (1901–2013) standardized precipitation–evapotranspiration index (SPEI); second, moderate resolution imaging spectroradiometer (MODIS) remote sensing data were applied to calculate ecosystem water use efficiency (WUE) and quantify ecosystem resistance and resilience after different extreme climate events; and finally, differences in the changes of various ecosystem types before and after climate events were assessed. The results showed the following: (1) The average SPEI was 0.073, and the thresholds of extreme wetness and drought were 0.91 and −0.67, respectively. Central Asia experienced extreme wet periods in 2002 and 2003 and a drought period in 2008. (2) Suitable wetness levels can increase the resistance of an ecosystem; however, continuous wetness reduces ecosystem resistance, as does drought. Wet areas had strong resilience after wet events, and arid areas had strong resilience after drought events. (3) During both wet and drought years, the transition between shrubland and grassland caused changes in ecosystem resistance and resilience. These findings are important for understanding the impact of future climate change on ecosystem stability.

Automatic road extraction from remote sensing images has an important impact on road maintenance and land management. While significant deep-learning-based approaches have been developed in recent years, achieving a suitable trade-off between extraction accuracy, inference speed and model size remains a fundamental and challenging issue for real-time road extraction applications, especially for rural roads. For this purpose, we developed a lightweight dynamic addition network (LDANet) to exploit rural road extraction. Specifically, considering the narrow, complex and diverse nature of rural roads, we introduce an improved Asymmetric Convolution Block (ACB)-based Inception structure to extend the low-level features in the feature extraction layer. In the deep feature association module, the depth-wise separable convolution (DSC) is introduced to reduce the computational complexity of the model, and an adaptation-weighted overlay is designed to capture the salient features. Moreover, we utilize a dynamic weighted combined loss, which can better solve the sample imbalance and boosts segmentation accuracy. In addition, we constructed a typical remote sensing dataset of rural roads based on the Deep Globe Land Cover Classification Challenge dataset. Our experiments demonstrate that LDANet performs well in road extraction with fewer model parameters (<1 MB) and that the accuracy and the mean Intersection over Union reach 98.74% and 76.21% on the test dataset, respectively. Therefore, LDANet has potential to rapidly extract and monitor rural roads from remote sensing images.