The Qilian Mountains (QLMs), an important ecological protective barrier and major water resource connotation area in the Hexi Corridor region, have an important impact on ecological security in western China due to their ecological changes. However, most existing studies have investigated vegetation changes and their main driving forces in the QLMs on the basis of a single scale. Thus, the interactions among multiple environmental factors in the QLMs are still unclear. This study was based on normalised difference vegetation index (NDVI) data from 2000 to 2019. We systematically analysed the spatial and temporal characteristics of the QLMs at multiple time scales using trend analysis, ensemble empirical mode decomposition, Geodetector, and correlation analysis methods. At different time scales under single-factor and multi-factor interactions, we examined the mechanisms of the vegetation changes and their drivers. Our results showed that the vegetation in the QLMs showed a trend of overall improvement in 2000–2019, at a rate of 0.88 × 10⁻³, mainly in the central western regions. The NDVI in the QLMs showed a short change cycle of 3 and 5 years and a long-term trend. Sunshine time and wind speed were the main drivers of the vegetation variation in the QLMs, followed by temperature. Precipitation affected the vegetation spatial variation within a certain altitude range. However, temperature and precipitation had stronger explanatory powers for the vegetation variation in the western QLMs than in the eastern part. Their interaction was the dominant factor in the regional differences in vegetation. The responses of the NDVI to temperature and precipitation were stronger in the long time series. The main drivers of vegetation variation were land surface temperature and precipitation in the east and temperature and evapotranspiration in the west. Precipitation was the main driver of vegetation growth in the northern and southwestern QLMs on both the short- and long-term scales. Vegetation changes were more significantly influenced by short-term temperature changes in the east but by a combination of temperature and precipitation in most parts of the QLMs on a 5-year time scale.

Interferogram filtering is an essential step in processing data from interferometric synthetic aperture radar (InSAR), which greatly improves the accuracy of terrain reconstruction and deformation monitoring. Most traditional interferogram filtering methods achieve noise suppression and detail preservation through morphological estimation based on the statistical properties of the interferogram in the spatial or frequency domain. However, as the interferogram’s spatial distribution is diverse and complex, traditional filtering methods struggle to adapt to different distribution and noise conditions and cannot handle detail preservation and noise suppression simultaneously. The study proposes a convolutional neural network (CNN)-based multi-level feature fusion model for interferogram filtering that differs from the traditional feedforward neural network (FNN). Adopting a multi-depth multi-path convolution strategy, the method preserves phase details and suppresses noise during interferogram filtering. In filtering experiments based on simulated data, qualitative and quantitative evaluations were used to validate the performance and generalization capabilities of the proposed method. The method’s applicability was evaluated by visual observation during filtering and unwrapping experiments on real data, and the time-series deformation acquired by time series (TS)-InSAR technique is used to evaluate the effect of interferogram filters on deformation monitoring accuracy. Compared to commonly used interferogram filtering methods, the proposed method has significant advantages in terms of performance and efficiency. The study findings suggest new directions for research on high-precision InSAR data processing and provide technical support for practical applications of InSAR.

The anomalous movements of glaciers cause disasters, such as debris flows and landslides. It is very important to assess the glacier movements and their future trends. Glacier velocity refers to movement process. The current research aims to analyse past and current spatiotemporal changes in glacier velocity. No study has used neural network model to conduct a spatiotemporal prediction for glacier velocity. Therefore, this paper selected typical mountain glaciers G2 and G5 along the Sichuan-Tibet Railway as research objects and constructed the Convolutional Gate Recurrent Unit (ConvGRU) spatiotemporal prediction model based on 1988–2018 Landsat data to predict velocities in 2019–2028, and analysed the future trends of G2 and G5. The evaluation indexes met the model requirements to a large extent, quantitatively showing that the model has high accuracy and can successfully capture the fluctuation changes in time series data of glacier velocity. The mean deviations of G2 and G5 were 0.09 and −0.47 m/yr, respectively, reflecting the high reliability of the model applied to extraction of glacier velocity. The velocities of G2 and G5 showed a slow downtrend with fluctuations; that is, they will not cause damage to the construction and operation of the Sichuan-Tibet Railway in the short term.

The landslide susceptibility assessment is an essential part of landslide disaster risk identification and prevention. However, the binarization of the hidden layer limits the parameterization ability of the conditional probability of visible layer, making the training process of restricted Boltzmann machine more difficult and further limiting the accuracy and efficiency of deep belief network (DBN) model in landslide susceptibility assessment. Therefore, this study proposed a landslide susceptibility assessment method based on Auto-Encoder (AE)-modified DBN. Zhouqu County, Gansu Province in the People’s Republic of China, was selected as the study area. Historical landslides in Zhouqu County were identified using small baseline subset interferometric synthetic aperture radar technology and optical image. Landslide factors were screened based on a geographical detector and stepwise regression method. The Logcosh loss function and determinant coefficient R ² index were used to evaluate the training process of the AE model, and the balanced cross entropy loss function was used to evaluate the entire network training process. In addition, the area under the curve (AUC) of the synthetical index model (SIM), support vector machine (SVM), and multilayer perceptron (MLP) were compared and evaluated. The results indicated that the proposed model could significantly improve the accuracy of landslide susceptibility assessment. The AUC value of the proposed model was 0.31, 0.12, and 0.11 higher than that of SIM, SVM, and MLP, respectively. Therefore, the improved DBN model based on AE proposed is reliable for early landslide identification and prediction.