The tomato (Solanum lycopersicum L.) is widely cultivated in yellow sand substrate-based systems in Northwest China, contributing significantly to regional agriculture. However, suboptimal water and fertilizer management hinders the balanced optimization of yield, fruit quality, and resource efficiency. In this two-year solar greenhouse experiment (2023–2024), we employed a four-factor, three-level orthogonal design [L9(3⁴)] to examine three irrigation regimes—full irrigation (FI 100% of crop evapotranspiration, [ET_c]), mild deficit irrigation (DIM 75% ET_c), and severe deficit irrigation (DIS 50% ET_c)—in combination with staged fertilizer applications at the seedling, flowering/fruit-set, and peak-fruit stages. A multi-objective decision-making framework, integrating an improved entropy weight method with a virtual-ideal-solution-based TOPSIS model, was established to address the complexity of water–fertilizer interactions. The results indicated that irrigation amount (IA) was the primary determinant of yield and water use efficiency (WUE), followed by fertilizer application in the second stage (FII). For fruit quality indices (moisture content, vitamin C (VC), lycopene (LC), soluble sugars (SSs), and soluble solids content (SSC)), IA remained the most influential factor, followed by FIII, FII, and FI; IA also had the largest impact on fruit hardness (Hd), soluble protein (SP), and titratable acidity (TA). An integrated scoring analysis revealed that treatment T5 achieved the highest yield, WUE, and partial factor productivity (PFP), whereas T7 excelled in fruit quality (VC, LC, SSC, and SP). Moreover, TOPSIS confirmed T5 as the optimal water–fertilizer strategy to achieve high yield, improved quality, and efficient resource utilization. Overall, these findings underscore a robust approach for optimizing water–fertilizer coupling in tomato cultivation under yellow sand substrate conditions, thereby enhancing resource use efficiency, promoting sustainable greenhouse agriculture in arid regions, and contributing to national water-saving and yield-increasing priorities.

This research initiative, developed in response to the need for enhanced mechanization efficiency within solar greenhouses, particularly under yellow sand cultivation conditions, introduces an integrated ditching and film-covering machine. A novel spiral staggered throw-cut combined ditching knife was specifically engineered and optimized to meet the exacting agronomic requirements of embedded substrate cultivation. Extensive analyses of soil interactions and the formulation of dynamic equations for soil particles facilitated the determination of key operational parameters: a tangent height of 650 mm for the ditching knife, a soil-throwing width of 300 mm, a piece width of 120 mm, and an inclination angle of 30°. Performance simulations of the ditching knife, conducted using the discrete element method (DEM), revealed superior soil disturbance control and improved soil return compared to conventional designs. Critical operational variables such as forward speed, knife shaft speed, and ditching depth were rigorously tested, with trench depth quality and power consumption as primary evaluation metrics. The results demonstrated that knife shaft speed profoundly influences performance, with optimal operating parameters established through detailed field testing: a speed of 0.5 m/s, a blade shaft speed of 200 rpm, and a ditching depth of 300 mm. Under these optimized conditions, the machine achieved power consumption of 0.668 kW, trench depth stability of 86.7%, a surface width of 413 mm, a bottom width of 304 mm, and an average ditching depth of 310 mm, achieving a qualification rate of 87.1%. The post-ditching soil crushing rate was 92.4%. Both simulation and field evaluations validated that the innovative ditching knife markedly enhances ditching and soil-throwing quality in sandy soil, fulfills agronomic requirements for tomato sowing, and provides an essential reference for the mechanized planting of crops in the yellow sand matrix cultivation mode of solar greenhouses.

Conventional ridging and mulching machines struggle to perform effectively in yellow sand substrates due to their loose texture, high collapsibility, and strong fluidity, which compromise ridge stability and operational quality. To address these challenges, this study proposes the development of an integrated rotary tillage, ridging, and film-mulching machine specifically designed to meet the agronomic requirements of tomato cultivation in greenhouse environments with yellow sand substrate. Based on theoretical analysis and parameter calculations, a soil transportation model was established, and the key structural parameters—such as blade arrangement and helical shaft geometry—were determined. A discrete element method (DEM) simulation was employed to construct a contact model for the yellow sand–slag mixed substrate. A combination of single-factor experiments and Box–Behnken response surface methodology was used to investigate the effects of forward speed, shaft rotational speed, and tillage depth on ridge stability and operational performance. The simulation results indicated that a forward speed of 0.82 m·s⁻¹, shaft speed of 260 rpm, and tillage depth of 150 mm yielded the highest ridge stability, with an average of 95.7%. Field trials demonstrated that the ridge top width, base width, height, and spacing were 598.6 mm, 802.3 mm, 202.4 mm, and 1002.8 mm, respectively, with an average ridge stability of 94.3%, differing by only 1.4 percentage points from the simulated results. However, a quantitative traction/energy comparison with conventional equipment was not collected in this study, and we report this as a limitation. The energy consumption is estimated based on power usage and effective field capacity (EFC) under similar operating conditions. Soil firmness reached 152.1 kPa, fully satisfying the agronomic requirements for tomato cultivation. The proposed machine significantly improves operational adaptability and ridge stability in yellow sand substrate conditions, providing robust equipment support for efficient greenhouse farming.

Carbon dioxide (CO₂) enrichment is an important means of increasing crop productivity in protected cultivation. However, local canopy CO₂ concentration in Chinese solar greenhouses is jointly affected by gas release, pipeline transport, and ventilation disturbances, making fixed-parameter proportional–integral–derivative (PID) control unable to simultaneously achieve rapid tracking, low overshoot, and fast disturbance recovery. This study developed a CO₂ enrichment system comprising controlled thermal decomposition of ammonium bicarbonate, condensation and water scrubbing, near-canopy delivery, and programmable logic controller (PLC)-based closed-loop control, and proposed a dynamic-target fuzzy PID (DT-FPID) strategy. Step-response tests were used to establish a first-order-plus-dead-time model linking heater duty cycle to local canopy CO₂ concentration, followed by fixed-target tracking, rule-based dynamic-target execution, and short-term ventilation-disturbance recovery tests in a local validation zone of a Chinese solar greenhouse. Relative to fixed-parameter PID, DT-FPID showed approximately 68–79% lower maximum overshoot and approximately 35–70% shorter ±20 ppm precision settling time (T₂₀) in simulation. At 600 ppm, the ±5% settling time was approximately 71% shorter, whereas at 800 and 1000 ppm it was broadly comparable to PID. In the greenhouse experiments, each controller–target combination included three independent runs. Based on descriptive comparisons of group means, DT-FPID showed approximately 47–49% lower mean maximum overshoot, approximately 36–40% shorter mean settling time, and approximately 77–80% shorter mean ventilation-disturbance recovery time; its mean maximum overshoot and settling time were also lower than those of conventional fuzzy PID. All three dynamic-target field runs completed the prescribed switches among the 600, 800, and 1000 ppm target levels. These results support control performance only under the short-term local validation conditions of this study; they are not used to determine physiologically or economically optimal CO₂ concentrations or to extrapolate whole-greenhouse uniformity or long-term production effects.

Mulch-film covering technology has been widely adopted in cotton production in arid regions; however, the associated problem of residual-film pollution has become increasingly prominent, creating an urgent demand for efficient and accurate monitoring approaches. Owing to the small target scale, irregular morphology, blurred boundaries, and complex soil backgrounds of residual-film fragments, residual-film detection based on close-range UAV imagery remains a challenging task. To address these issues, this study proposes an improved algorithm, termed YOLO-EGASF, for residual-film detection in arid-region cotton fields, built upon the lightweight YOLOv11n framework. To enhance the detection of small targets with weak boundary characteristics, the baseline model is improved from three aspects. First, a boundary-enhanced multi-branch small-target extraction module (EMSE) is designed to reinforce shallow-layer details and gradient information through multi-scale convolution and explicit edge enhancement. Second, a GLoCA attention module that integrates global coordinate information with local geometric features is constructed to improve the discriminative capability of the model for residual-film targets under complex background conditions. Third, an ASF-layer multi-scale feature fusion structure is introduced, together with an additional small-target detection layer, to strengthen the participation of high-resolution features in cross-scale fusion and prediction. Experimental results on a self-constructed UAV-based residual-film dataset from cotton fields demonstrate that YOLO-EGASF outperforms several mainstream detection models in terms of Precision, Recall, mAP@0.5, and mAP@0.5:0.95, achieving mAP@0.5 and mAP@0.5:0.95 values of 71.9% and 26.8%, respectively. These results indicate a significant improvement in detection accuracy and robustness, confirming that the proposed method can effectively meet the practical requirements of fine-grained residual-film monitoring in arid-region cotton fields.