Accurate landslide extraction is significant for landslide disaster prevention and control. Remote sensing images have been widely used in landslide investigation, and landslide extraction methods based on deep learning combined with remote sensing images (such as U-Net) have received a lot of attention. However, because of the variable shape and texture features of landslides in remote sensing images, the rich spectral features, and the complexity of their surrounding features, landslide extraction using U-Net can lead to problems such as false detection and missed detection. Therefore, this study introduces the channel attention mechanism called the squeeze-and-excitation network (SENet) in the feature fusion part of U-Net; the study also constructs an attention U-Net landside extraction model combining SENet and U-Net, and uses Sentinel-2A remote sensing images for model training and validation. The extraction results are evaluated through different evaluation metrics and compared with those of two models: U-Net and U-Net Backbone (U-Net Without Skip Connection). The results show that proposed the model can effectively extract landslides based on Sentinel-2A remote sensing images with an F1 value of 87.94%, which is about 2% and 3% higher than U-Net and U-Net Backbone, respectively, with less false detection and more accurate extraction results.

The prediction of land subsidence is a crucial step for early warning of urban infrastructure damage and timely remedy. However, the performance of most mathematical and empirical prediction models is often compromised by their large number of parameters, complex operational processes and sparsely measured values. Currently, the traditional neural network models are popular and effective, but they cannot accurately discover the characteristic changes of time series data. In this paper, a long short-term memory (LSTM) neural network was proposed to predict the land subsidence of time series Interferometric Synthetic Aperture Radar (InSAR). First, the Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) technique was utilized to monitor the time series land subsidence at Beijing Capital International Airport (BCIA) from 2005 to 2010 based on ENVISAT ASAR images with a descending orbit. The results were compared with the existing results to verify the reliability and then used to analyse the temporal and spatial characteristics of the time series land subsidence of the BCIA. Based on the time series InSAR deformation data, the LSTM neural network was used to establish the prediction model of time series InSAR, and the results were compared with those of the Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). The comparison results showed that the LSTM neural network was more accurate than the MLP and RNN on the point scale (the root mean square error was 4.60 mm and the mean absolute error was 3.18 mm), the correlation coefficients between the prediction results of the LSTM neural network and the real InSAR measurement results in 2007 and 2008 were 0.93 mm and 0.96 mm, respectively, indicating that LSTM neural network had better prediction performance. Eventually, based on the land subsidence data of time series InSAR from 2006 to 2010, the LSTM neural network was applied to predict the BCIA time series land subsidence in 2011. The results predicted that cumulative subsidence in September 2011 would reach a maximum of 350 mm. Therefore, the LSTM neural network is a potentially effective prediction method, which can replace numerical or empirical models in the absence of detailed hydrogeological data. Moreover, its prediction results can be used to assist decision-making, early warning and hazard relief.

Net ecosystem productivity (NEP) quantifies magnitude of the terrestrial vegetation carbon sinks. Drought is one of the most important stressors affecting vegetation NEP. At present, the spatiotemporal dynamics of vegetation NEP in drought-prone of Northwest China (NWC) lack discussion under different climatic zones and land cover types, and the response of vegetation NEP to drought remains unclear. Hence, we estimated the vegetation NEP in NWC using ground and remote sensing data and quantified the spatiotemporal differentiation of NEP under different climatic zones and land cover types. The drought fluorescence monitoring index (DFMI) was developed to examine the relationship between vegetation NEP and drought response based on the solar-induced chlorophyll fluorescence (SIF) data. Our results suggested that vegetation carbon sinks increased significantly at 7.09 g C m⁻² yr⁻¹ in NWC during 2000–2019, mainly in northern Shaanxi, eastern and southern Gansu, and southern Ningxia. NEP showed increasing trends under different climatic zones and land cover types, but there were differences in carbon sink capacity. The strongest carbon sink capacity was in humid regions and forests, while the weakest was in arid regions and grasslands. The vegetation carbon sinks showed a non-linear relationship with the drought degree reflecting multiple trend differences, especially in forests and grasslands. The response to drought was faster and more significant in semi-arid and semi-humid transition zones and extreme humid regions when vegetation carbon sinks decreased. DFMI was a good indicator to monitor drought conditions in NWC. NEP and DFMI were an 8–20-month periodic positive correlation and showed a high correlation with high–high and low–low clustering spatially. Drought significantly weakened vegetation carbon sinks in NWC. This study emphasizes the demand to rapidly identify climatic conditions that lead to decrease significantly in vegetation carbon sinks and to formulate adaptation strategies aimed at reducing drought risk under global warming.