Detecting changes in urban areas presents many challenges, including complex features, fast-changing rates, and human-induced interference. At present, most of the research on change detection has focused on traditional binary change detection (BCD), which becomes increasingly unsuitable for the diverse urban change detection tasks as cities grow. Previous change detection networks often rely on convolutional operations, which struggle to capture global contextual information and underutilize category semantic information. In this paper, we propose SIGNet, a Siamese graph convolutional network, to solve the above problems and improve the accuracy of urban multi-class change detection (MCD) tasks. After maximizing the fusion of change differences at different scales using joint pyramidal upsampling (JPU), SIGNet uses a graph convolution-based graph reasoning (GR) method to construct static connections of urban features in space and a graph cross-attention method to couple the dynamic connections of different types of features during the change process. Experimental results show that SIGNet achieves state-of-the-art accuracy on different MCD datasets when capturing contextual relationships between different regions and semantic correlations between different categories. There are currently few pixel-level datasets in the MCD domain. We introduce a new well-labeled dataset, CNAM-CD, which is a large MCD dataset containing 2508 pairs of high-resolution images.

Rapid and accurate mapping of the spatial distribution of cotton fields is helpful to ensure safe production of cotton fields and the rationalization of land-resource planning. As cotton is an important economic pillar in Xinjiang, accurate and efficient mapping of cotton fields helps the implementation of rural revitalization strategy in Xinjiang region. In this paper, based on the Google Earth Engine cloud computing platform, we use a random forest machine-learning algorithm to classify Landsat 5 and 8 and Sentinel 2 satellite images to obtain the spatial distribution characteristics of cotton fields in 2011, 2015 and 2020 in the Ogan-Kucha River oasis, Xinjiang. Unlike previous studies, the mulching process was considered when using cotton field phenology information as a classification feature. The results show that both Landsat 5, Landsat 8 and Sentinel 2 satellites can successfully classify cotton field information when the mulching process is considered, but Sentinel 2 satellite classification results have the best user accuracy of 0.947. Sentinel 2 images can distinguish some cotton fields from roads well because they have higher spatial resolution than Landsat 8. After the cotton fields were mulched, there was a significant increase in spectral reflectance in the visible, red-edge and near-infrared bands, and a decrease in the short-wave infrared band. The increase in the area of oasis cotton fields and the extensive use of mulched drip-irrigation water saving facilities may lead to a decrease in the groundwater level. Overall, the use of mulch as a phenological feature for classification mapping is a good indicator in cotton-growing areas covered by mulch, and mulch drip irrigation may lead to a decrease in groundwater levels in oases in arid areas.

Exploring the future trends of land use/land cover (LULC) changes is significant for the sustainable development of a region. The simulation and prediction of LULC in a large-scale basin in an arid zone can help the future land management planning and rational allocation of resources in this ecologically fragile region. Using the whole Ili-Balkhash Basin as the study area, the patch-generating land use simulation (PLUS) model and a combination of PLUS and Markov predictions (PLUS–Markov) were used to simulate and predict land use in 2020 based on the assessment of the accuracy of LULC classification in the global dataset. The accuracy of simulations and predictions using the model were measured for LULC data covering different time periods. Model settings with better simulation results were selected for simulating and predicting possible future land use conditions in the basin. The future predictions for 2025 and 2030, which are based on historical land change characteristics, indicate that the overall future spatial pattern of LULC in the basin remains relatively stable in general without the influence of other external factors. Over the time scale of the future five years, the expansion of croplands and barren areas in the basin primarily stems from the loss of grasslands. Approximately 48% of the converted grassland areas are transformed into croplands, while around 40% are converted into barren areas. In the longer time scale of the future decade, the conversion of grasslands to croplands in the basin is also evident. However, the expansion phenomenon of urban and built-up lands at the expense of croplands is more significant, with approximately 774.2 km² of croplands developing into urban and built-up lands. This work provides an effective new approach for simulating and predicting LULC in data-deficient basins at a large scale in arid regions, thereby establishing a foundation for future research on the impact of human activities on basin hydrology and related studies.

Ecological challenges resulting from soil salinization in the Tarim River Basin (TRB), exacerbated by climate change and human activities, have emphasized the need for a quick and accurate assessment of regional ecological environmental quality (EEQ) and driving mechanisms. To address this issue, this study has developed a remote-sensing ecological index with salinity adaptability (RSEI_SI) for EEQ assessment in the Tarim River Basin by integrating the comprehensive salinity index (CSI) into the remote-sensing ecological index (RSEI). The RSEI_SI enhances the sensitivity of soil salinity and characterizes the surface features of arid regions, thus expanding the applicability. Then, we used time-series analysis methods and a geodetector to quantify the spatial temporal trends and driving factors of EEQ in the TRB from 2000 to 2022. The results show that the RSEI_SI with salinity adaptation effectively monitors the EEQ of the TRB. The EEQ of the TRB displayed the situation of oasis expansion, desert deterioration, and glacier melting, and the multiyear average EEQ grades were dominated by medium and poor grades in desert and saline areas, while medium, good, and excellent grades were concentrated in oasis and mountainous areas. Looking at the trend of change in conjunction with land-use types, the EEQ of the TRB showed a mild degradation trend mainly in unused land, followed by a mild improvement trend in cropland and grassland. The Hurst index indicated that the EEQ of most areas of the TRB will improve in the future. Soil type, land use, precipitation, and temperature were considered to be key factors affecting the EEQ across the TRB, and changes in the EEQ were found to be the interaction of multiple factors. This study may provide innovative concepts and methodologies, scientific and technological support for ecological management, and green development models in the northwest arid zone.

Although understanding the carbon and water cycles of dryland ecosystems in terms of water use efficiency (WUE) is important, WUE and its driving mechanisms are less understood in Central Asia. This study calculated Central Asian WUE for 2001–2021 based on the Google Earth Engine (GEE) platform and analyzed its spatial and temporal variability using temporal information entropy. The importance of atmospheric factors, hydrological factors, and biological factors in driving WUE in Central Asia was also explored using a geographic detector. The results show the following: (1) the average WUE in Central Asia from 2001–2021 is 2.584–3.607 gCkg⁻¹H₂O, with weak inter-annual variability and significant intra-annual variability and spatial distribution changes; (2) atmospheric and hydrological factors are strong drivers, with land surface temperature (LST) being the strongest driver of WUE, explaining 54.8% of variation; (3) the interaction of the driving factors can enhance the driving effect by more than 60% for the interaction between most atmospheric factors and vegetation factors, of which the effect of the interaction of temperature (TEM) with vegetation cover (FVC) is the greatest, explaining 68.1% of the change in WUE. Furthermore, the interaction of driving factors with very low explanatory power (e.g., water pressure (VAP), aerosol optical depth over land (AOD), and groundwater (GWS)) has a significant enhancement effect. Vegetation is an important link in driving WUE, and it is important to understand the mechanisms of WUE change to guide ecological restoration projects.

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.