Cultivated land resilience is often required for the regional food security in sustainable agriculture, particularly under the global climate change and ecological risks in arid and semi-arid regions of Western China. Among them, Xinjiang's oasis cultivated land has been a major production base for high-quality cotton and grain in China. However, an important ecological barrier can be found from multiple disturbances, such as drought, wind-blown sand, and urbanization, thus resulting in significant systemic vulnerability. This study aims to investigate the resilience pattern and driving mechanisms of cultivated land using ecosystem resilience theory. The cultivated land resilience was deconstructed into three capacities: resistance, adaptation, and recovery. A differentiated evaluation was constructed with 14 indicators suitable for the unique characteristics of Xinjiang’s oasis cultivated land, including irrigation dependence, ecological sensitivity, and economic underdevelopment. Resistance capacity was measured by the indicators, such as the proportion of effective irrigated area, soil thickness, soil pH, and soil moisture content. Adaptation capacity was represented by crop planting diversity index, multiple cropping index, agricultural machinery use per land area, and rural electricity consumption. Recovery capacity was assessed by per capita grain security rate, grain output rate of cultivated land, landscape fragmentation index, and per capita agricultural productive investment. Eight control variables were introduced to avoid estimation bias, including elevation, annual average rainfall, annual average temperature, pesticide use per land area, agricultural film use intensity, grain crop sowing area ratio, rural per capita disposable income, and per capita GDP. The XGBoost-SHAP model was employed to combine with kernel density estimation and spatial autocorrelation analysis. The spatiotemporal patterns of cultivated land resilience were examined at the county level in Xinjiang from 2000 to 2023. The strong predictive performance was achieved with the training set R² values over 0.92 for all resilience dimensions and test set R² values ranging from 0.785 to 0.919. SHAP analysis was conducted to quantify the contribution of each driving factor to the nonlinear marginal effects. The results indicate that: (1) The overall resilience of cultivated land showed a fluctuating upward trend during the study period. The peak of the kernel density curve was shifted to the right and the width narrowed, indicating a significant reduction in regional disparities. (2) Spatially, a “high in the north, low in the south” pattern was observed, with the high-value areas in the eastern oases (e.g., Yizhou District, Qitai County) and gradually clustering, while the extent of low-value areas shrank. The global Moran’s I index ranged between 0.182 and 0.310, indicating significant spatial aggregation. (3) Rainfall, per capita GDP, and elevation were identified as the drivers influencing cultivated land resilience, with contribution shares of 36.5%, 16.7%, and 13.9%, respectively. Increasing rainfall weakened the land resilience, due to waterlogging or soil nutrient loss, while the mid-elevation areas exhibited higher resilience. Reasonable investment in per capita GDP enhanced the cultivated land resilience, although excessive investment diminished the returns. The findings can provide scientific support to formulate the differentiated cultivated land protection in Xinjiang and similar arid and semi-arid regions worldwide. The interpretable machine learning models can also offer important theoretical and practical value in the nonlinear driving mechanisms of cultivated land resilience.

Cotton is an important cash crop in Xinjiang, accounting for 90.2% of China's total production in 2022. However, natural factors such as drought, high soil salinity, and the constraints of perennial shallow tillage soil management practices limit the yield and efficiency of cotton production and sustainable agricultural development. Deep vertical rotary tillage facilitates the breaking up of soil solidification and promotes the salt leached by irrigation water. In order to investigate the improvement effect of deep vertical rotary tillage on heavily saline cotton fields in Southern Xinjiang of China, this study conducted a 2 a (2021-2022) field experiment with three deep vertical rotary tillage depths (DT20: deep vertical rotary tillage 20 cm, DT40: deep vertical rotary tillage 40 cm, DT60: deep vertical rotary tillage 60 cm), and alternate with conventional tillage (five-share plowing 20 cm CT20), and CT20 was set to be the two consecutive years of conventional tillage. Original soil samples from 0-60 cm were collected to determine the water-stable aggregates. Soil moisture, salinity, organic carbon, total nitrogen, total phosphorus and total potassium were defermined by samples under the drip irrigation tapes, wide rows and narrow rows of each treatment on the 3rd day after each irrigation. Cotton root samples were collected at 105 days after sowing in 2021 and at 103 days in 2022. The effects of different depths of deep vertical rotary tillage on soil physical properties, soil nutrient content, cotton root length density, boll weight, dry matter mass accumulation and seed cotton yield were investigated, and the effect of crop yield was quantified by structural equation modeling. The results showed that: 1) deep vertical rotary tillage was able to loosen the soil in the tillage layer to optimize the soil structure. DT60 treatment was able to significantly reduce the soil bulk density, the content of coarse aggregates (>2 mm), and silt and clay particle (<0.053 mm) in the tillage depth layer compared with DT20 and CT20 treatment, which led to a significant reduction in mean weight diameter and mean geometric diameter, and increased total soil porosity and the content of micro-aggregates (<0.25～0.053 mm), while DT60 treatment was unable to further improve the soil structure in the deep soil layer compared with DT40 treatment. 2) DT40 and DT60 treatments were able to significantly increase soil moisture from 0-40 cm soil layer and reduce soil salinity and pH value, whereas DT20 treatment was only able to reduce soil salinity from 0-20 cm soil layer, whereas DT60 treatment was able to significantly reduce soil salinity and pH value from 0-60 cm soil layer compared with DT40 treatment. The reduction of soil salinity promoted the accumulation of soil organic carbon in the 0-40 cm soil layer and soil total nitrogen in the 0-60 cm soil layer, but DT60 treatment was unable to significantly increase soil organic carbon and soil total nitrogen in the 0-20 cm soil layer compared with the DT40 treatment. 3) The analysis of the structural equation modeling showed that soil salinity was an indirect factor affecting the seed cotton yield, and the accumulation of cotton’s dry matter and the weight of cotton bolls were the direct factored. The reduction of soil salinity favors soil nutrient accumulation and cotton root growth, promoted nutrient transport and accumulation to the plant organ, and increased cotton dry matter accumulation and seed cotton yield. Therefore, DT60 treatment had the best effect of soil salinity reduction, and thus the effect of yield increase. Comprehensive analysis showed that the depth of 60 cm on deep vertical rotary tillage with conventional tillage alternating can realize the synergy of improving and increasing the yield and efficiency of the severe saline cotton fields in the Southern Xinjiang of China.