Groundwater is crucial for economic and agricultural development, particularly in arid areas where surface water resources are extremely scarce. The prediction of groundwater levels is essential for understanding groundwater dynamics and providing scientific guidance for the rational utilization of groundwater resources. A back propagation (BP) neural network based on the artificial bee colony (ABC) optimization algorithm was established in this study to accurately predict groundwater levels in the overexploited arid areas of Northwest China. Recharge, exploitation, rainfall, and evaporation were used as input factors, whereas groundwater level was used as the output factor. Results showed that the fitting accuracy, convergence rate, and stabilization of the ABC-BP model are better than those of the particle swarm optimization (PSO-BP), genetic algorithm (GA-BP), and BP models, thereby proving that the ABC-BP model can be a new method for predicting groundwater levels. The ABC-BP model with double hidden layers and a topology structure of 4-7-3-1, which overcame the overfitting problem, was developed to predict groundwater levels in Yaoba Oasis from 2019 to 2030. The prediction results of different mining regimes showed that the groundwater level in the study area will gradually decrease as exploitation quantity increases and then undergo a decline stage given the existing mining condition of 40 million m³/year. According to the simulation results under different scenarios, the most appropriate amount of groundwater exploitation should be maintained at 31 million m³/year to promote the sustainable development of groundwater resources in Yaoba Oasis.

Precipitation is scarce and evaporation is intense in desert areas. Groundwater is used as the main water source to develop agriculture in the oases. However, the effects of using groundwater on the ecological environment elicit widespread public concern. This study investigated the relationship between soil salinity and groundwater characteristics in Yaoba Oasis through in situ experiments. The relationship of the mineral content, pH, and main ion content of groundwater with soil salt was quantitatively evaluated through a gray relational analysis. Four main results were obtained. First, the fresh water area with low total dissolved solid (TDS) was usually HCO₃⁻ or SO₄²⁻ type water, and salt water was mostly Cl⁻ and SO₄²⁻. The spatial distribution of main ions in groundwater during winter irrigation in November was basically consistent with that during spring irrigation in June. However, the spatial distribution of TDS differed in the two seasons. Second, soil salinization in the study area was severe, and the salinization rate reached 72.7%. In this work, the spatial variability of soil salinization had a relatively large value, and the values in spring were greater than those in autumn. Third, the soil in the irrigated area had a high salt content, and the salt ion content of surface soil was higher than that of subsoil. A piper trilinear diagram revealed that Ca²⁺ and K⁺ + Na⁺ were the main cations. SO₄²⁻, Cl⁻, and HCO₃⁻ were the main anions, and salinization soil mainly contained SO₄²⁻. Fourth, the changes in soil salt and ion contents in the 0–10 cm soil layer were approximately similar to those of irrigation water quality, both of which showed an increasing trend. The correlation of surface soil salinity with the salinity of groundwater and its chemical components was high. In summary, this study identified the progress of irrigation water quality in soil salinization and provided a scientific basis for improving the oasis ecosystem, maintaining the healthy development of agriculture, managing oasis water resources, and policy development. Our findings can serve as a reference for other, similar oasis research.

Climate change and human activities have profound effects on the characteristics of groundwater in arid oases. Analyzing the change of groundwater level and quantifying the contributions of influencing factors are essential for mastering the groundwater dynamic variation and providing scientific guidance for the rational utilization and management of groundwater resources. In this study, the characteristics and causes of groundwater level in an arid oasis of Northwest China were explored using the Mann–Kendall trend test, Morlet wavelet analysis, and principal component analysis. Results showed that the groundwater level every year exhibited tremendous regular characteristics with the seasonal exploitation. Meanwhile, the inter-annual groundwater level dropped continuously from 1982 to 2018, with a cumulative decline depth that exceeded 12 m, thereby causing the cone of depression. In addition, the monthly groundwater level had an evident cyclical variation on the two time scales of 17–35 and 7–15 months, and the main periodicity of monthly level was 12 months. Analysis results of the climatic factors from 1954 to 2018 observed a significant warming trend in temperature, an indistinctive increase in rainfall, an inconspicuous decrease in evaporation, and an insignificant reduction in relative humidity. The human factors such as exploitation amount, irrigated area, and population quantity rose substantially since the development of the oasis in the 1970s. In accordance with the quantitative calculation, human activities were decisive factors on groundwater level reduction, accounting for 87.79%. However, climate change, including rainfall and evaporation, which contributed to 12.21%, still had the driving force to change the groundwater level in the study area. The groundwater level of Yaoba Oasis has been greatly diminished and the ecological environment has deteriorated further due to the combined effect of climate change and human activities.

Land cover classification that uses very high resolution (VHR) remote sensing images is a topic of considerable interest. Although many classification methods have been developed, the accuracy and usability of classification systems can still be improved. In this paper, a novel post-processing approach based on a dual-adaptive majority voting strategy (D-AMVS) is proposed to improve the performance of initial classification maps. D-AMVS defines a strategy for refining each label of a classified map that is obtained by different classification methods from the same original image, and fusing the different refined classification maps to generate a final classification result. The proposed D-AMVS contains three main blocks. (1) An adaptive region is generated by gradually extending the region around a central pixel based on two predefined parameters (T₁ and T₂) to utilize the spatial feature of ground targets in a VHR image. (2) For each classified map, the label of the central pixel is refined according to the majority voting rule within the adaptive region. This is defined as adaptive majority voting. Each initial classified map is refined in this manner pixel by pixel. (3) Finally, the refined classified maps are used to generate a final classification map, and the label of the central pixel in the final classification map is determined by applying AMV again. Each entire classified map is scanned and refined pixel by pixel based on the proposed D-AMVS. The accuracies of the proposed D-AMVS approach are investigated with two remote sensing images with high spatial resolutions of 1.0 m and 1.3 m. Compared with the classical majority voting method and a relatively new post-processing method called the general post-classification framework, the proposed D-AMVS can achieve a land cover classification map with less noise and higher classification accuracies.