Studying the relationship between agricultural irrigation water requirements (IWR) and water supply is significant for optimizing the sustainable management of water resources in Tarim River Basin (TRB). However, the related studies have not quantified the total IWR and the imbalance of irrigation water supply and requirements in the TRB. The study analyzed the spatial-temporal variations of IWR by a modified Penman–Monteith (PM) method during 1990–2015. Five major crops—rice, wheat, maize, cotton, and fruit trees—are chosen for calculating the IWR. It was found that the IWR increased significantly, from 193.14 × 10⁸ m³ in 1990 to 471.89 × 10⁸ m³ in 2015, for a total increase of 278.74 × 10⁸ m³. For the first period (1990–2002), the total IWR remained stable at 200 × 10⁸ m³ but started to increase from 2003 onwards. Significantly more irrigation water was consumed in the oasis regions of the Tienshan Mountains (southern slope) and the Yarkand River (plains). Furthermore, there was an intensified conflict between IWR and water supply in the major sub-basins. The ratios of IWR to river discharge (IWR/Q) for the Weigan-Kuqa River Basin (WKRB), Aksu River Basin (ARB), Kaxgar River Basin (KGRB), and Yarkand River Basin (YRB) were 0.93, 0.68, 1.05, and 0.79, respectively. The IWR/Q experienced serious annual imbalances, as high flows occurred in July and August, whereas critical high IWR occurred in May and June. Seasonal water shortages further aggravate the water stress in the arid region.

Estimating Terrestrial Water Storage (TWS) not only helps to provide a comprehensive insight into water resource variability and the hydrological cycle but also for better water resource management. In the current research, Gravity Recovery And Climate Experiment (GRACE) data are combined with the available hydrological data to reconstruct a longer record of Terrestrial Water Storage Anomalies (TWSA) prior to 2003 of the Tarim River Basin (TRB), based on a Long Short-Term Memory (LSTM) model. We found that the TWSA generated by LSTM using soil moisture, evapotranspiration, precipitation, and temperature best matches the GRACE-derived TWSA, with a high correlation coefficient (r) of 0.922 and a Normalized Root Mean Square Error (NRMSE) of 0.107 during the period 2003–2012. These results show that the LSTM model is an available and feasible method to generate TWSA. Further, the TWSA reveals a significant fluctuating downward trend (p < 0.001), with an average decline rate of 0.03 mm/month during the period 1982–2016 in the TRB. Moreover, the TWSA amount in the north of the TRB was less than that in the south of the basin. Overall, our findings unveiled that the LSTM model and GRACE data can be combined effectively to analyze the long-term TWSA in large-scale basins with limited hydrological data.

Levees are critical for flood defence, but their integrity is threatened by hazards such as piping and seepage, especially during high-water-level periods. Traditional manual inspections for these hazards and associated emergency response elements, such as personnel and assets, are inefficient and often impractical. While UAV-based remote sensing offers a promising alternative, the effective fusion of multi-modal data and the scarcity of labelled data for supervised model training remain significant challenges. To overcome these limitations, this paper reframes levee monitoring as an unsupervised anomaly detection task. We propose a novel, fully automated framework that unifies geophysical hazards and emergency response elements into a single analytical category of “abnormal targets” for comprehensive situational awareness. The framework consists of three key modules: (1) a state-of-the-art registration algorithm to precisely align infrared and visible images; (2) a generative adversarial network to fuse the thermal information from IR images with the textural details from visible images; and (3) an adaptive, unsupervised segmentation module where a mean-shift clustering algorithm, with its hyperparameters automatically tuned by Bayesian optimization, delineates the targets. We validated our framework on a real-world dataset collected from a levee on the Pajiang River, China. The proposed method demonstrates superior performance over all baselines, achieving an Intersection over Union of 0.348 and a macro F1-Score of 0.479. This work provides a practical, training-free solution for comprehensive levee monitoring and demonstrates the synergistic potential of multi-modal fusion and automated machine learning for disaster management.

Analyzing the impervious surface area (ISA) of China’s three major urban agglomerations and expansion pattern of representative cities is of great significance for formulating context-specific urban planning policies and enhancing the resilience of urban development. This research employs impervious surface expansion indicators to reveal the spatiotemporal dynamics of impervious surface area, and further applies the location centrality index (LCI) to investigate the expansion structures and patterns of five megacities. The results indicate that the ISA of China’s three major urban agglomerations expanded from 22,544.10 km² to 69,348.59 km² from 1985 to 2024; both the expansion rate and intensity have exhibited a distinct decelerating trend. However, significant regional variation exists in the peak expansion phases: the Guangdong–Hong Kong–Macao Greater Bay Area Urban Agglomeration (GBA) peaked during the Initial Exploratory Phase (1985–1995), whereas the Yangtze River Delta Urban Agglomeration (YRD) and Beijing–Tianjin–Hebei Urban Agglomeration (BTH) reached their peaks during the High-speed Development Phase (2005–2015). At the urban scale, LCI-based analysis of urban expansion across five megacities reveals that adjacency expansion type has become the predominant form of growth, exceeding 50% in most cities. These findings enhance our understanding of evolutionary trajectories of ISA within urban agglomerations and the expansion patterns of five megacities, providing a scientific basis for sustainable urban planning and urban resilience.

Xinjiang experiences frequent dust storms, posing significant challenges to regional ecological security and public health. Based on the China High-resolution and High-quality Near-surface Air Pollutants (CHAP) dataset and ground monitoring data, this paper adopts the Potential Source Contribution Function (PSCF) to analyze the spatiotemporal characteristics of atmospheric particulate matter across Xinjiang and typical cities and to identify potential source regions and contribution intensities. The results show that (1) PM_2.5 and PM₁₀ concentrations are elevated in southern Xinjiang but reduced in the north, and particulate pollution in most areas has generally decreased. (2) Northern Xinjiang cities have high PM_2.5 in winter, while southern Xinjiang cities keep persistently high PM₁₀ levels. (3) The PM_2.5/PM₁₀ ratio is above 0.35 in northern cities, where pollution is dominated by fine particles affected mainly by human activities; southern Xinjiang is dominated by coarse particles from natural sources. (4) Particulate matter in Urumqi mainly comes from the northern Tianshan Mountains, with winter WPSCF over 0.9. Pollutants in Kashgar originate from both long-distance cross-border dust transmission and local emissions. These findings are of great significance for the sustainable development of Xinjiang and urban agglomerations along the Belt and Road.