Cotton is the most important cash crop in Xinjiang but low utilization rate of water and fertilizer is restricting healthy development of this industry. At present, there is a lack of water and nitrogen management optimization methods based on multi-objectives of cotton water use efficiency (WUE), nitrogen use efficiency (NUE), yield, and income. A continuous field experiment was conducted during 2017–2018 to study the effects of water–nitrogen coupling on cotton growth, WUE, NUE, nitrogen partial factor productivity, yield, quality, and economic benefits under drip irrigation in northern Xinjiang. Using multiple regression and spatial analyses, the water and nitrogen management strategy for multi-objective optimization was determined. Three irrigation levels were used—low (I₁), medium (I₂), and full (I₃)—Representing 75%, 87.5%, and 100% of cotton water demand, respectively. The three nitrogen application levels were low (N₁, 210 kg/ha), medium (N₂, 280 kg/ha), and high (N₃, 350 kg/ha), representing 75%, 100%, and 125% of the local nitrogen application, respectively. Among all treatments, the leaf area index, boll weight, dry matter quantity and yield reached respective maxima of 4.43 m²/m², 4.73 g, 16,623 kg/ha, and 6333 kg/ha for the I₃N₂ treatment. Cotton fiber quality was the best for I₃ irrigation, but too little or too much nitrogen reduced fiber quality. The economic benefit under I₃ irrigation was 1.93–4.81 times that for I₁. For a single optimization objective, WUE reached a maximum of 1.78 kg/ha·mm for irrigation of 415.80 mm and nitrogen application of 295.71 kg/ha; corresponding single maxima follow: NUE of 37.65% for 418.27 mm and 278.57 kg/ha; yield of 6416.42 kg/ha for 470.12 mm and 304.29 kg/ha; and economic benefit of 15,338.55 RMB/ha for 470.12 mm and 307.14 kg/ha. Multiple regression and spatial analysis showed that for irrigation of 430.71–440.12 mm and nitrogen application of 270.95–318.45 kg/ha, the WUE, NUE, yield, and economic benefits of cotton simultaneously exceeded 90% of their maxima, which was an efficient and reasonable water and nitrogen management mode in this location. The results provide a scientific basis for effective integrated management of water and fertilizer in drip irrigation cotton fields in northern Xinjiang.

Hami, Xinjiang, is located in an extremely arid region and jujube is the main economic crop. It is important to adopt dwarf and close-planting technology under drip irrigation and to optimize water and fertilizer management to improve jujube yield and quality. Local 12-year-old jujube trees were treated using two factors of irrigation and fertilization. Three irrigation amounts (520, 700, and 880 mm) and three fertilization levels (248, 318, and 388 kg/hm²) were set up in plot experiments. The root system, yield, and quality of jujube were monitored under different irrigation and nitrogen application combinations. The effects on water use efficiency (WUE), nitrogen partial factor productivity (PNP), and economic benefit were analyzed. The water and fertilizer coupling effect of dwarf closely planted jujube was studied by combining multiple regression and spatial analyses. The yield, quality, economic benefits, WUE, and PNP of jujube were significantly affected by irrigation and fertilization. Multiple regression and spatial analyses showed that the highest yield was for irrigation of 700 mm and a nitrogen rate of 340 kg/hm². For the maximum net benefit, irrigation was 806 mm and nitrogen was 388 kg/hm²; correspondingly, for the highest total sugar, values were 688 mm and 362 kg/hm²; for vitamin C, they were 622 mm and 376 kg/hm²; for PNP, they were 880 mm and 256.57 kg/hm²; and for WUE, they were 520 mm and 388 kg/hm². A comprehensive evaluation of each index showed that the acceptable irrigation amount for yield, quality, WUE, and net benefit of ≥85% of the maximum value was 600–628 mm, and the nitrogen application rate was 360–372 kg/hm². This study provides guidance for the scientific management of water and fertilizer in the drip irrigation and fertilization process of local jujube trees.

The timely identification of key rice growth stages supports water management, crop monitoring, and yield estimation. This study evaluated whether single-date unmanned aerial vehicle (UAV) RGB imagery can identify early tillering, booting, heading, and milk-ripe rice without a continuous image time series. UAV imagery and synchronous field observations were collected from 64 fields in the Zhanghe Irrigation District, China, during 2022–2023. Four visible-light indices and 12 gray-level co-occurrence matrix (GLCM) texture features were used with k-nearest neighbors (KNN), a support vector machine (SVM), random forest (RF), a gradient boosting decision tree (GBDT), and corresponding stacking ensembles. Stacking-RF achieved the highest test performance, with 91.7% accuracy and a macro-F1 of 0.917, exceeding KNN, the best individual model, by 6.8 percentage points and 0.067, respectively. Early tillering and milk-ripe were identified more accurately than booting and heading. Visible-light indices supplied most of the discriminative information, while texture features contributed complementary canopy-structure information. The results show that an RGB-only, single-date input can support a rapid within-site growth-stage assessment. However, the sample-level split, single study area, and absence of radiometric calibration limit inference to new fields, years, and regions.