Highlights Development of a modular system adaptable to varying farm sizes and the architectural structure of cacao trees. Performance evaluation using realistic prototypes, achieving pickup rates between 28% and 67% across different pod orientations and surfaces, providing quantitative insights into system effectiveness under diverse operational conditions. Design considerations prioritizing scalability, user accessibility, and potential for future mechanization enhancements. Abstract. This study aimed to develop a modular, low-cost mechanical system to assist in the collection of cacao pods, particularly by addressing the labor-intensive “pickup” stage commonly found in smallholder and large-scale harvesting operations. The system was designed with three main components: a lollipop-based pickup mechanism, a pod collector with a comb-style separator, and a modular cart frame. Field testing was conducted under two surface conditions (asphalt and grass), using simulated cacao pods of various shapes and orientations to evaluate pickup effectiveness. The results demonstrated pickup rates ranging from 28% to 67%, depending on pod orientation and surface type, highlighting both the system's potential and areas for optimization. Additional factors, such as travel speed, applied downward force, pod reorientation, and ground resistance, were observed to influence system performance and offer directions for future optimization. The modular structure allowed adaptability across farm types, and multiple power source configurations (manual, bike-assisted, or tractor-towed) were demonstrated. A key limitation is that performance was tested using simulated pods, which may not fully represent real-world field conditions. Despite this, the findings provide valuable insights into the feasibility of mechanizing pod collection in diverse agricultural settings. These results indicate that the system could substantially reduce manual labor requirements, improve harvesting efficiency, and serve as a foundation for further mechanization innovations in cacao production. Keywords: Agricultural mechanization, Cacao pod pickup, Harvesting efficiency, Labor reduction, Modular system.

Highlights This article proposes ISCF, a novel method for precise soybean pod and seed counting using a segmentation followed by a classification strategy. Compared to YOLO, ISCF offers faster inference, higher accuracy, and a more efficient pipeline for real-time applications. The proposed method focuses on the practical value of the lightweight design, making it deployable on edge devices for real-world use. The proposed method applies to the automated counting of seeds or fruits of various crops in controlled indoor environments, demonstrating strong generalizability and adaptability. Abstract. Accurate counting of soybean pods and seeds is essential for yield prediction, crop management, and variety improvement. However, existing automatic methods under controlled indoor conditions often exhibit limited computational efficiency, insufficient accuracy, and limited practical deployment for reducing manual workload. To address this, we propose an Indoor Soybean Counting Framework (ISCF), a lightweight deep learning framework that decouples localization and classification into two independent stages to count soybean pods and seeds. ISCF first performs precise segmentation of soybean pods using the proposed Indoor Soybean Segmentation Network (ISSN), followed by classification of the number of seeds per pod using a MobileNetV3-based architecture. Optimized for lightweight design, ISCF is well-suited to real-time deployment on edge devices. Experimental results demonstrate the superior performance of ISCF in soybean pod and seed counting tasks, achieving an AP 50 of 99.5% for pod segmentation, a mean absolute error (MAE) of merely 0.72, and an R 2 of 0.9942 for pod counting, and an MAE of 3.79 and an R 2 of 0.9573 for seed counting. Moreover, ISCF generalizes well to datasets from four additional crop species, underscoring its potential for a broad range of indoor crop counting and phenotyping applications. Keywords: Image classification, Image recognition, Instance segmentation, Lightweight network, Plant phenotyping, Soybean counting.

HighlightsVF agricultural radial tires can carry 40% more load at the same inflation pressure than standard radial tires.Cohesive-frictional artificial soil was penetrated by statically loaded sprayer tire to evaluate tire footprint characteristics.VF sprayer tire footprint characteristics showed significantly increased length and area at low inflation pressure on soft soil.Maximum rut depth was statistically shallower with reduced tire inflation pressure under full load conditions.Abstract. Relatively few studies on tire-penetrated soil contact properties of Very High Flexion (VF) radial tires for heavy-axle load self-propelled equipment have been done. Soil bin tire testing on cohesive-frictional artificial soil was conducted to investigate the effects of 41 and 54 kN tire load settings of a VF 710/70R42 sprayer tire, inflated to low and high tire inflation pressure settings (TIP) on 3-D contact parameters (length, width, and area) and soil rut depth. Corn yield data were compared from tire-trafficked lanes and untrafficked lanes to investigate trafficking effects on crop yield. Lowering tire inflation pressure resulted in statistically greater contact length and contact area and shallower soil rut depth (p < 0.05). Contact width was not significantly affected by TIP. Sprayer traffic resulted in a 15.8% reduction in yield compared to the yield from untrafficked lanes. The tire-to-soil contact area was 1.52 times the “gross flat plate” contact area measured on a rigid surface. The soil bin method for measuring pneumatic tire penetrated contact properties on the deformable cohesive-frictional artificial soil (COV of 1.79%, N = 36) was better than the “Gross-flat plate” method on the rigid surface for soil compaction management. Further study is needed measuring tire-penetrated contact properties for various tires and their effects on crop yield. Keywords: Artificial cohesive-frictional soil, Contact area, Contact length, Contact width, Corn yield, Soil rut depth, Tire inflation pressure, Very high flexion (VF) radial tire.

HighlightsAn improved lightweight model for cabbage maturity detection based on deep learning is proposed.A cabbage maturity detection dataset (CMDD) is established for experiments.The implementation of image slicing and counting in large scenes demonstrates the practicality of the algorithm.The performance of the proposed algorithm is effective and practical for detecting small-to-medium target plants in natural scenes.Abstract. Cabbage is a significant economic crop and an essential staple in people’s daily lives, with its closed state serving as a crucial indicator of maturity. Accurately assessing the maturity and quantity of cabbage to determine the optimal harvest time is vital for production. Due to the small-to-medium size of cabbage targets from the drone's perspective and the high similarity in maturity features, we have enhanced the YOLOv8n network by incorporating methods such as the Space-to-Depth Convolution (SPD-Conv), the Deformable Large Kernel Attention (DLKA), and the Dynamic Head (Dyhead). This has led us to propose a novel deep learning network called SDD-YOLOv8 that enhances capabilities in extracting features and performance in detection. The experimental results indicate that our enhanced model attains a mean average precision (mAP@0.5) of 87.0%, which is a 1.2% improvement compared to the baseline model. Furthermore, we have devised a technique for detecting and counting cabbages in large scenes to enhance practicality. Our method achieves an overall average counting accuracy of 95.0% compared to manual counting, with individual category accuracies reaching 93.9% and 95.0%. This method enables accurate classification and counting of cabbages in natural environments. Keywords: Attention mechanism, Deep learning, Maturity detection, Plant counting, UAV, YOLOv8.

Highlights Plasma-based nitrogen fixation offers sustainable alternatives to Haber-Bosch. Microwave induction plasma coupled torches achieve high efficiency using air and water. Biological fixation remains vital but limited in scalability and consistency. Review compares natural and artificial methods for nitrogen fixation. Abstract. Nitrogen is a vital element for life, playing a key role in biological processes such as photosynthesis and protein synthesis. Despite its abundance in the atmosphere as dinitrogen (N2), it must be converted into a usable form for most organisms. Because it is unusable in its natural state, it must be transformed into ammonia or other nitrogen compounds that plants and other organisms can absorb. This process is called nitrogen fixation. This document reviews both natural and artificial methods for fixing nitrogen. Natural processes include physical, biological, geological, and marine fixation. In contrast, artificial methods include pioneering processes such as the Frank-Caro, Birkeland-Eyde (now obsolete), and Haber-Bosch, which is currently the primary method for industrial ammonia production. However, the latter faces criticism due to its dependence on fossil fuels and the greenhouse gases it produces. Also included are plasma-based nitrogen fixation methods, such as microwave-induced plasma (MIP) torches, which offer promising alternatives by harnessing renewable energy sources and providing high efficiency. This review highlights the evolution, mechanisms, and environmental impacts of nitrogen fixation technologies, emphasizing the need for sustainable and energy-efficient solutions. Keywords: Agricultural sustainability, Ammonia synthesis, Biological nitrogen fixation, Haber-Bosch process, Microwave plasma, Nitrogen cycle, Nitrogen fixation, Plasma technology, Renewable energy, Sustainable fertilizers.

HIGHLIGHTS Bio-based polymer (BBP) made of renewable materials provided promising results for soybean growth. BBP application did not negatively impact the soybean emergence, but delayed emergence and impeded weed growth. BBP conserved the soil moisture and moderated the temperature as compared with control. BBP was able to suppress the giant foxtail (S. faberi) weed growth. BBP application significantly increased the soil organic matter and nitrogen contents. ABSTRACT. The performance and impacts of the sprayable and degradable bio-based polymer (BBP), which was prepared from renewable materials such as poultry feathers and low-grade woody biomass, on soil health (quality); weed germination, growth, and pressure; soil temperature; soil-water; soil organic matter content (SOMC), nitrogen content; and soybean (Glycine max (L.) Merr.) productivity was investigated. The treatments included soybean+weed. with and without BBP applications. The weed was giant foxtail (Setaria faberi Hermm.). The soil-water content was up to 13 mm higher (p<0.05) in BBP treatments than in the control, indicating the soil-water conservation effect of BBP. The BBP application did not negatively affect soybean emergence; soybeans in both BBP and control treatments emerged on the same day. However, weed emergence was delayed by 3-5 days in the BBP treatment compared with the control. The soil temperature in the control was 3°C to 6.7°C greater than the BBP treatment’s soil temperature, indicating the temperature moderation effect of the BBP during extreme conditions, especially in hot and dry summer periods. Soybean dry matter and height with BBP application were significantly greater, and the weed count was significantly (p<0.05) lower than that without BBP. Soybean dry matter with the BBP application was 32% greater (p<0.05) than that without the BBP application (control). The BBP application reduced the variation in weed count and weed dry matter production by 78% and 67%, respectively. The average plant height for the BBP-applied plants was 821 mm, whereas it was 691 mm for the control. Average weed dry matter with BBP application was significantly (p<0.05) lower than that without BBP application. The plots with BBP application had significantly (p<0.05) lower weed numbers (18.3 weeds per plot) than those without BBP application (47.3 weeds per plot). The BBP application significantly increased soil organic matter and nitrogen content compared with the control throughout this experiment. This initial research indicated that BBP can provide beneficial conditions for plant growth and production while partially controlling S. faberi weed. Keywords: Crop productivity, Giant foxtail, Soil health, Soil temperature, Soil-water status, Sprayable and degradable biopolymers.

HighlightsPortable FPGA system for real-time AFR identification, improving food safety.Attention-based model reduces interference and enhances AFR identification accuracy.FPGA implementation with optimizations boosts inference speed by 2.51× and energy efficiency by 1.72×.Abstract. This article presents a portable FPGA-based system for real-time, on-site identification of artificially fragrant rice (AFR), which poses potential health risks. It addresses the limitations of traditional laboratory methods, which are often costly and time-consuming. An attention mechanism-based model is developed for accurate AFR identification, reducing interference from impurities and ensuring reliable results. A top-k engine and an approximate multiplier are designed to optimize the model for FPGA deployment, enhancing computational efficiency and minimizing resource consumption. The customized FPGA architecture achieves 90.5% accuracy in AFR identification, with a 2.51× increase in speed and a 1.72× improvement in energy efficiency compared to typical edge platforms. This research pioneers an efficient, on-site solution for AFR identification, contributing to rapid food safety assessment advancements. Keywords: Artificially fragrant rice (AFR), Attention mechanism, Food safety, FPGA, On-site identification.

Highlights A multi-view 3D camera system was built to capture depth maps and reconstruct point clouds of complete pigs in breeding farms. Geometric and morphological features were extracted from the reconstructed point clouds for measuring phenotypic traits via 3D processing algorithms. The minimal mean absolute error of predicting liveweight was 4.19 kg. The mean absolute percentage errors of predicting chest and abdominal circumferences were 2.33% and 2.06%, respectively. Abstract. Manually measuring the phenotypic traits of pigs in breeding farms can be time- and labor-intensive and cause animal stress, and subjective manual measurement errors slow down the progress of desired traits and genetic selection across multiple breeding generations. The objectives of this study were 1) developing a multi-view 3D camera system to capture depth maps and reconstruct point clouds of complete pigs in breeding farms and 2) extracting geometric and morphological features from the reconstructed point clouds for predicting phenotypic traits. The proposed 3D scanning system was installed in a swine breeding farm, and 481 PIC Camborough® pigs in parent stocks were used with RGB-depth video acquisition. Core 3D processing algorithms merged point clouds from three camera views into one complete pig point cloud, including Iterative Closest Point, Fast Point Feature Histograms, Random Sample Consensus, and Sorting. Gaussian Mixture Clustering and point cloud slicing were implemented to extract critical features for predicting six traits: abdominal circumference, chest circumference, front body height, rear body height, ear-to-tail straight length, and ear-to-tail curve length. Three standard objects were used to test the system’s performance with mean absolute errors (MAE) of 0.04 to 0.07 m. The chest and abdominal circumference correlated highly (r = 0.74) with liveweight. After comparative studies of seven combinations of the six phenotypic traits, the best weight prediction performance (MAE = 4.19 kg) was obtained with the combination of the first four traits via the XGBoost regressor. The study highlighted the innovative applications of artificial intelligence and 3D computer vision for pig breeding and genetics selection. Keywords: Artificial intelligence, Automation, Depth sensing, Expert system, Precision livestock farming.

HighlightsSpray deposition and distribution evaluations of UAVs were conducted.Spray distributions by the ISO and the Japanese protocol showed similar trends.The Japanese test protocol is useful as an evaluation method.A great benefit is its consideration of UAV-specific downwash and crosswinds.Abstract. For this study, evaluations of spray deposition and distribution on industrial unmanned helicopters and multi-rotor UAVs were conducted, respectively, according to the Japanese convention test protocol for UAVs and the test protocol for ground boom sprayers specified in ISO 24253 part 1. Using both the Japanese conventional protocol and the ISO 24253 protocol, spraying was conducted with 8 L per hectare with commercial UAVs. The amounts of tracer captured by collectors placed on the ground surface were measured and converted to the spray application rate per area. Results found for spray distribution by the ISO protocol exhibited similar trends to those obtained using the Japanese protocol. Results obtained from comparing the spray depositions of both test protocols indicated coefficients of determination R2 of the spray deposition measured values as 0.64 and 0.85, respectively, for helicopters and multi-rotors. Under the Japanese protocol, droplets on each of the five planes of the cubic collector were examined. More than 40% of the total droplets were observed on vertical planes because of downwash from UAV rotors, despite the crosswind effect during spraying. Therefore, one reason for differences in deposition values between these test methods was that the Japanese test protocol was able to capture droplets from the lateral direction with the cubic collector, which could not be captured using the ISO test. The Japanese test protocol, which measures the amount of adhesion using cubic collectors, is a useful and promising evaluation method that takes into account the UAV-specific downwash and crosswind effects. Keywords: ISO 24253 part 1, Japanese convention test protocol for UAVs, spray deposition and distribution, UAV pesticide application.

Highlights Rigid-flexible coupling structure with silicone-coated fingers ensures compliant contact and stable grasping. Field validation confirms 91.8% harvesting success for 70-90 mm tomatoes at 5.4 s/fruit. 270° rotational detachment mechanism achieves 0% branch damage while minimizing fruit separation force to 8.36 N. First integration of retractable suction with a three-finger gripper for targeted isolation of cluster tomatoes. Abstract. Traditional tomato harvesting relies heavily on manual labor, characterized by high costs and low efficiency. With advances in agricultural intelligence, harvesting robots have emerged as a critical solution. As the core component of harvesting robots, the performance of the end-effector directly influences harvesting efficiency. To address the low success rate and high damage rate in harvesting clustered tomatoes caused by foliage occlusion and fruit overlap, this paper designs a rigid-flexible coupling three-fingered end-effector with retractable suction cups. The suction mechanism isolates the target fruit, while the three-finger gripping combined with 270° rotational traction enables low-damage harvesting. Structural parameters are optimized through multi-field coupling simulations in Ansys/Adams and field trials. Results indicate a single-fruit harvesting time of 5.4 s and a maximum success rate of 91.8%, meeting the requirements for mechanized harvesting. Keywords: End-effector, Gripping force, Kinematics, Simulation, Tomato harvesting robot.