Highlights A novel water-powered proportional pump was developed. Novel proportional pump reduces system pressure drop by 24% versus Venturi injector. Proportional pump achieves 97.7% fertilizer distribution uniformity. Longer fertilization time with proportional pump improves mixing homogeneity. Abstract. Water and fertilizer uniformity is an important indicator of drip irrigation system performance. The fertilizer injector is key equipment in drip fertigation systems, and its performance directly affects irrigation and fertilization quality as well as energy consumption. A novel water-powered proportional pump was developed, and its hydraulic performance was investigated. In order to evaluate the effect of the Venturi injector and the novel water-powered proportional pump on fertigation characteristics, a series of experiments was conducted. The experimental scheme compared the performance of the two injectors in a single-end fed drip irrigation system. Key variables included injector type, the resulting pressure drop, fertilization time, and the spatial distribution of water and fertilizer along the laterals. The results showed that the coefficient of variation (CV) of the fertilization ratio under different pressure differentials was 2.54%. The pressure drop of the proportional pump was significantly lower than that of the Venturi injector. Using the proportional pump as the fertilizer injector can effectively reduce the working pressure of the drip fertigation system. With the same water volume (1 m 3 ) the fertilization time of the proportional pump was much longer than that of the Venturi injector. The fertilizer concentration increased slightly at the far end of the drip tape in the Venturi injector system. The fertilizer solution concentration varied less with distance when using the proportional pump. Longer fertilization time and a smaller fertilizer concentration difference improved fertilizer distribution uniformity. The type of fertilizer injector had less effect on the applied water; conversely, it had a significant effect on the applied fertilizer. The average values of Christiansen’s uniformity (CU) for applied water and fertilizer were 97.22 and 97.78 for the proportional pump, and 94.69 and 97.69 for the Venturi injector, respectively. The average distribution uniformity (DU) for applied water and fertilizer was 95.67 and 96.28 for the proportional pump, and 92.17 and 96.16 for the Venturi injector, respectively. For practical management, the proportional pump allows continuous adjustment of the fertilization ratio from 0.07% to 0.35% by simply rotating the three-way valve (0°-90°). The fertilization ratio remains highly stable under varying pressure differentials, so precise pressure regulation is not required in the field, simplifying operation and ensuring consistent fertilizer application. This study provides a reference for precision fertilization and guidance for selecting fertilizer injectors in practice. Keywords: Fertigation; Fertilizer distribution uniformity; Venturi injector; Water-powered proportional pump; Water distribution uniformity.
Highlights An adaptive leveling boom was developed for self-propelled sprinkler irrigation machinery operating in hilly terrain. The proposed boom achieves multi-degree-of-freedom posture adjustment through electric-actuator-based lifting and worm-gear-driven swing regulation. Integrated dynamic, finite element, and modal analyses supported boom optimization and achieved a 13% mass reduction while maintaining structural safety. Prototype tests confirmed improved boom stability under no-load, operating-pressure, and simulated obstacle conditions. Abstract. To improve the terrain adaptability and operational stability of self-propelled sprinkler equipment in hilly terrain, we developed an adaptive leveling boom based on electric actuator–driven lifting and a worm gear–based swing mechanism. A dynamic model of the lifting mechanism was established, and key structural parameters were optimized using a genetic algorithm to improve dynamic smoothness and stability. Based on static and modal analyses, the boom was further optimized for lightweight design and structural safety using the analytic hierarchy process. After optimization, the maximum deformation of the boom model was 0.78 mm. The maximum stress was 170.37 MPa, and the safety factor reached 1.38. Under typical operating conditions, stress and strain satisfied strength requirements. Constrained modal analysis confirmed that resonance was avoided within the primary operating frequency range. The boom weight was reduced by 13% to 165 kg, achieving lightweight design objectives while significantly improving structural strength and dynamic stability. Comparative prototype tests were conducted between the proposed boom and a conventional boom under no-load, operating-pressure, and simulated slope-obstacle disturbance conditions. The validation included eight no-load test groups, three operating-pressure levels (0.1, 0.2, and 0.3 MPa), and four simulated slope-obstacle arrangements, with five repeated trials per arrangement. A multi-index comprehensive evaluation model was established to quantify boom stability. Under the balanced no-load condition, the stability index of the proposed boom reached 0.93, representing a 22.4% improvement over the conventional boom. At operating pressures of 0.1, 0.2, and 0.3 MPa, stability improved by 16.8%, 26.4%, and 32.9%, respectively. Under simulated conditions involving combined 15° slopes and obstacles, the proposed boom rapidly recovered to a stable state with reduced displacement fluctuations. These results demonstrate that the proposed boom improves posture stability and disturbance recovery under controlled and simulated hilly-terrain conditions, providing a structural basis for further field-scale evaluation and a practical technical reference for enhancing the terrain adaptability and operational stability of mobile sprinkler irrigation equipment. Keywords: Adaptive leveling boom, Hilly tea plantation, Lightweight design, Stability analysis, Structural optimization, Self-propelled sprinkler irrigation machine.
Highlights Developed a computer vision system using YOLOv11x-Pose with keypoint detection to automatically detect and track corn ears in image sequences. Achieved 90% detection recall and estimated ear orientation with a mean absolute error of 15.2°, comparable to human measurement variability (12.6°). Demonstrated a scalable, time-efficient alternative to manual measurement, enabling improved monitoring of corn growth and future precision agriculture applications. Abstract. Monitoring the growth behavior of corn plants, including ear development and orientation, can provide important insights into plant health and development. Manual measurement of ear orientation is labor-intensive and subject to observer variability. This work presents an end-to-end computer vision pipeline for automated detection, tracking, and orientation estimation of corn ears in field image sequences. The pipeline combines YOLOv11x-Pose-based keypoint detection, temporal tracking, and geometric orientation estimation to enable longitudinal monitoring of ear growth behavior. A field image dataset was collected to train and evaluate the system. The proposed approach detected 90% of ears tested, while azimuth estimation achieved a mean absolute error of 15.2°, compared to a mean difference of 12.6° between two human researchers. These results demonstrate the feasibility of automated image-based monitoring of corn ear orientation and provide a foundation for future high-throughput phenotyping and crop management applications. Keywords: Computer vision, Corn morphology, Object detection, Object tracking.
Highlights Four spring tillage treatments were evaluated prior to cotton production with sprinkler irrigation in Arizona. Conventional tillage yielded 8% greater but was not statistically different than no tillage with a winter cover crop. No tillage with a winter cover crop significantly improved emergence, early season crop vigor, and crop growth. Strip tillage with a winter cover crop did not provide favorable cotton production outcomes. Abstract. Cotton (Gossypium hirsutum L.) production in central Arizona has traditionally relied on intensive tillage to break up the root-zone subsoil, laser leveling to improve surface irrigation efficiency, and cotton planting on raised beds with surface irrigation in adjacent furrows. Adoption of overhead sprinkler irrigation technology increases opportunities for reducing tillage operations; however, the effects of conservation practices on Arizona cotton production remain uncertain. The objective of this study was to compare four spring tillage management practices for sprinkler-irrigated cotton in Arizona: 1) conventional tillage with cotton planted on raised beds, 2) conventional tillage with cotton planted on flat ground, 3) no tillage with cotton planted directly into a terminated barley cover crop, and 4) strip tillage with cotton planted into tilled strips within a terminated barley cover crop. The four tillage treatments were replicated three times in a sprinkler-irrigated cotton field during the 2023 cotton season at Maricopa, Arizona. Measurements of cotton emergence, stand density, canopy height, soil water content, and fiber yield and quality were obtained. Additionally, images from a small unoccupied aircraft system (sUAS) were used to quantify fractional crop cover through canopy closure. Cotton fiber yield was 1650 kg ha -1 when planted on raised beds with conventional tillage, but this management practice demonstrated substantial spatial yield variability. Cotton planted on flat ground with conventional tillage had favorable emergence and stand density, while fiber yield was 1657 kg ha -1 and was not significantly different (p > 0.05) from yield of cotton planted on beds. No-till cotton demonstrated promising early-season vigor and crop growth, but mean fiber yield was reduced by 8% (1513 kg ha -1 ) compared to conventional tillage (p > 0.05), possibly due to no-till planter performance issues. Strip tillage did not provide favorable cotton fiber yield, with a 25% reduction (1237 kg ha -1 ) compared to conventional tillage (p < 0.05), likely due to water pooling in the tilled strips. Sprinkler-irrigated cotton in Arizona can be planted on conventionally tilled and leveled ground without a yield penalty compared to planting on raised beds, while no-till cotton should be prioritized for research as a promising conservation alternative. Keywords: Cotton, Cover Crop, Irrigation, Management, Tillage, Water.
Highlights Systematic mapping study on insect monitoring with computer vision. Review of 114 relevant research studies. State-of-the-art of multi-object detection and tracking applied to insect monitoring. Challenges and possible solutions for insect monitoring. Abstract. Insect monitoring offers several benefits to agriculture and ecology, primarily as a tool for enhancing pollination services, managing pests, promoting the rational use of pesticides, and combating insect decline to restore abundance, diversity, and biomass. Traditional monitoring requires repetitive work that depends on specialists. Intelligent insect monitoring has the potential to overcome the shortcomings of conventional monitoring and make it more efficient. We consider that monitoring should detect and track insects of interest. This article provides a comprehensive overview of the current literature, highlighting gaps, trends, and research challenges that warrant further investigation. We conducted a systematic literature review following well-established methodological guidelines. We carefully selected 38 primary and 76 derivative studies as a sample of 2077 articles from diverse databases. We analyzed and categorized the articles to address seven research questions. The results show that 103 of the studies applied insect detectors and Multiple Object Tracking, 85 utilized insect datasets, 16 proposed hardware, and a single work addressed the energy cost of the hardware. Computer vision using deep learning techniques based on Convolutional Neural Networks presents a promising approach to overcoming the challenges of intelligent insect monitoring. Ultimately, this article can serve as a starting point for future studies, offering insights from a systematic literature review. Keywords: Bees, Computer vision, Deep learning, Insects, Intelligent monitoring, Multiple Object Tracking.
