Journal of Agricultural Machinery

Abstract Introduction
Planting rice seedlings in the main field followed by periodic or intermittent irrigation is often considered a form of dry farming. Research suggests that flood irrigation in rice cultivation is primarily favored by farmers for its ability to control weeds and ensure a reliable water supply, rather than necessarily enhancing rice quality or yield. Depending on the rice variety, intermittent irrigation can sometimes improve both the quality and yield per unit area. The transplanting process in this method can be carried out manually without machinery or through mechanized methods using a planter.
Materials and Methods
Conventional rice transplanters designed for use in flooded land are not suitable for transplanting in dry land farming due to technical constraints. Therefore, it is necessary to develop a specialized rice transplanter tailored for such soil condition. This transplanter encompasses essential components, including a furrow opener, coverer, seedling storage tank or tray, seedling mechanism (distributor), seedling transfer mechanism (seedling transport piston), end separator for seedlings in the soil, power transmission system, depth adjustment shoe, and main and sub chassis. To evaluate the planter's performance, various parameters were assessed, including the percentage of lost plants, the average vertical angle of plant orientation, the average spacing between plants in the crop row, and the average number of seedlings per plant. Moreover, a factorial randomized block design was employed, with three replications for each level of the independent variables. The independent variables were forward speed (X1) at three levels of 0.25, 0.5, and 1 m s^-1, planting depth (X2) at three levels of 4, 8, and 12 cm, and the size of the outlet opening of the seedling tray (X3) in three levels of 10, 15, and 20 mm.
Results and Discussion
The developed single-row planter features key specifications, including a working width of 250 mm, a power requirement of 0.57 kW, a theoretical field capacity of 0.06 ha h^-1, and a field efficiency of 66.67%. The research findings revealed that forward speed, planting depth, and outlet opening size, along with their interactions, significantly impact the percentage of lost plants at the 99% confidence level. Among the three levels of forward speed (X1), the best speed level is 0.25 m s^-1, as it results in the lowest percentage of lost seedlings. As the forward speed increases, the percentage of lost seedlings increases. The lowest percentage of lost plants (Y1) occurs at the planting depth of 8 cm and an outlet opening size of 20 mm. Furthermore, forward speed, planting depth, and their interaction have a noteworthy influence on the vertical angle of plants are established, at the 99% confidence level. With the increase of forward speed and planting depth, the average vertical angle of seedling establishment deviates from the vertical position. The forward speed of 0.25 meters per second and the planting depth of 8 cm show the best results for the establishment of seedlings. The sole factor affecting the spacing between plants in the row is the forward speed. The size of seedling tray’s outlet opening significantly affects the number of seedlings per plant at the 99% confidence level, while planting depth affects it at the 95% confidence level.
Conclusion
Given the recent water crisis, adopting the dry rice farming method and using transplanters offers a viable solution for managing and conserving water in agriculture. Implementing dry planting with a custom-made transplanter yields several benefits, including reduced water consumption, lower cultivation costs, improved soil aeration, increased efficiency, and simplified planting processes. Utilizing this transplanter is an effective strategy to decrease both the time and expenses related to transplanting, while also mechanizing rice planting in dry fields.

Abstract Introduction
Remote sensing is considered a key management tool in precision agriculture, particularly for monitoring and identifying plant coverage. Grapes are among the most valuable horticultural crops, with Hamedan province accounting for approximately 7.3 % of Iran's total vineyard area. This study evaluates the accuracy of vineyard identification in Hamedan province using machine learning algorithms including support vector machine (SVM), minimum distance (MD), and random forest (RF) models along with normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) estimated from combined optical and radar images of Sentinel (Sentinel-1 and Sentinel-2). Based on the most accurate vineyard identification map, the maximum time series of NDVI and NDWI of the MODIS satellite in vineyards was estimated between 2007 and 2020, and their correlation with the actual yield of the grape crop was examined.
Materials and Methods
In this research, we first extracted images of pivotal remote sensing vegetation indicators, including NDVI and NDWI, from Sentinel-2 images in Hamedan province in 2020. The approach of addressing speckle noise through median pixels allowed for the acquisition of median radar images from Sentinel-1 over the designated study area. To create high-accurate images, spectral composition was used to combine these images with the NDVI and NDWI from Sentinel-2 images. Using these images, vineyard identification maps were generated through classification algorithms, including support vector machine, random forest, and minimum distance models. Training samples were used to train these algorithms. Samples from six land coverage classes involving vineyards, were collected using a combination of field observations and Google Earth imagery. Of these, 70% were used for training and 30% for testing the classification models. In order to assess the accuracy of the vineyard identification maps, indicators including overall accuracy and kappa coefficient were examined. Subsequently, the vineyard map with the highest assessment indicator was selected. Finally, using this accurate vineyard identification map, the maximum monthly NDVI and NDWI indices estimated from MODIS sensor images in the vineyards were calculated from 2007 to 2020, and their correlation with yields of the grape crop was computed using Pearson correlation.
Results and Discussion
Based on the comparison of different classification algorithms for distinguishing vineyards, random forest model along with NDVI and NDWI indices outperformed support vector machine and minimum distance models. With regard to accuracy, however, the random forest along with the NDWI has the best overall accuracy (95%) and kappa coefficient (0.95). The superior performance of NDWI is attributed to the high moisture levels in vineyards resulting from irrigation, as NDWI is particularly sensitive to variations in vegetation water content. The lower accuracy of vineyard identification using SVM and MD models can be linked to shadow effects caused by the canopy structure of grapevines, as well as imbalanced training data used for the support vector machine model. Correlation analysis of real grape yields with NDVI and NDWI of MODIS extracted from the highest accuracy vineyards map indicates NDVI (correlation coefficient 0.81) has a stronger linear relationship with yield than NDWI (correlation coefficient 0.75). This can be explained by NDVI's sensitivity to leaf chlorophyll changes, which results in a strong correlation with yield.
Conclusion
Vineyards can be accurately identified using machine learning algorithms and remote sensing vegetation indices derived from combined radar and optical satellite images. Furthermore, the strong correlation between NDVI and grape yield enable reliable yield prediction based on NDVI time series analysis. The outcomes of this study facilitate the identification of grape cultivation areas, improved water resourse management, the development of optimized irrigation strategies, pre-harvest yield estimation, and the exploration of export options.

Abstract Introduction
The increasing demand for automation in agriculture, particularly for repetitive and labor-intensive tasks, has driven the development of robotic harvesting systems. Recent advances in computer vision, deep learning, and the availability of large image datasets have made it possible to create robust object detection models for agricultural applications. Traditional harvesting methods, such as bulk harvesting, often lead to fruit damage and loss owing to non-selective picking. Selective harvesting, particularly with the use of robotic systems, offers a promising alternative by combining the precision of human labor with the efficiency of automation. This study presents a deep learning-based model for detecting cucumber fruits on plants in a real greenhouse environment, which is an essential step towards developing autonomous harvesting robots that selectively pick ripe cucumbers.
Materials and Methods
A dedicated image dataset was curated in a commercial greenhouse, comprising 300 images of cucumber plants captured under various lighting conditions (morning, noon, and evening), to ensure robustness against real-world variability. Images were manually labeled to identify the cucumber fruits and their pedicels. To enhance the model training and prevent overfitting, data augmentation techniques were applied to the training set. Several architectures of the YOLO (You Only Look Once) object detection algorithm were evaluated, including the nano-scale versions YOLOv5n and YOLOv8n, and the small-scale YOLOv8s, in addition to the RT-DETR model.
The YOLOv8 algorithm is known as one of the state-of-the-art algorithms in computer vision because of its high speed, detection accuracy, and adaptability. The YOLOv8 architecture consists of three main parts: backbone, neck, and head, which are responsible for extracting image features, combining and enriching features, and predicting bounding boxes and object classes, respectively.
These models were trained, and their performances were compared based on the detection accuracy and inference time metrics. Training and evaluation were conducted using a suitable computational platform.
Results and Discussion
The performances of different YOLO models and RT-DETR were rigorously evaluated. The results demonstrated that the YOLOv8n model achieved the highest detection accuracy of 87.5%, surpassing the performances of the other tested models. Importantly, the YOLOv8n model also exhibited a favorable balance between the accuracy and inference time, making it suitable for real-time applications. The analysis considered the trade-off between the number of parameters and detection speed, highlighting the efficiency of YOLOv8n.
The YOLOv8n model demonstrated superior performance in terms of pedicel detection accuracy compared to YOLOv5n, achieving a fitness score of 91.08% (calculated as a weighted average of mAP@50 and mAP@50-95). While exhibiting strong performance in fruit and pedicel detection (Figure 6), the sensitivity of the model for pedicel detection (88.0%) was comparatively lower than that for fruit detection (96.1%). The highest F1 score (0.89) was observed at a confidence level of 39.5%, indicating the effectiveness of the model in balancing the precision and recall for pedicel detection. Overall, YOLOv8n outperformed the other tested models in identifying the class and location of the fruit pedicel. The superior performance of YOLOv8n can be attributed to its architectural advancements and optimized training processes.
Conclusion
This study successfully developed a deep learning-based model for accurate and efficient cucumber fruit detection in a greenhouse environment. The YOLOv8n model demonstrated superior performance compared with the other evaluated architectures, achieving a detection accuracy of 87.5% while maintaining a good processing speed. These findings suggest that the YOLOv8n model has significant potential for integration into autonomous vegetable harvesting robots, contributing to the automation of agricultural processes and increased efficiency in greenhouse operations. Future works should explore further optimization and testing under diverse environmental conditions.

Abstract Introduction
Tillage of rainfed lands is performed using moldboard plows to a depth of 30 cm. Due to the influence of soil surface roughness and crop residues on moisture absorption and erosion reduction, investigation of the relationship between tillage implements’ performance and the aforementioned factors is essential. Therefore, considering the importance of preserving precipitation and preventing soil erosion, this study was conducted to investigate and optimize the effects of forward speed and tillage depth on soil surface roughness and the percentage of buried crop residue using response surface methodology.
Materials and Methods
This research was conducted in the Khomeyn region, Iran during the 2023-2024 growing season, utilizing a moldboard plow and an MF399 tractor. The objective was to investigate the effects of plowing depth and speed on soil surface roughness and the burial of plant residues. Soil surface roughness was measured using a pin meter, while the percentage of burial of plant residues was determined using image processing techniques and ImageJ software. Wheat straw residue with an initial moisture content of 8-9% was uniformly distributed at a rate of 100 g m^-2 along the designated paths. Images were captured before and after the tillage operation for subsequent processing and analysis.
To optimize the process, a central composite design (CCD) with three levels of speed (5, 7.5, and 10 km h^-1) and three levels of tillage depth (17.5, 22.5, and 27.5 cm) was employed. The objective was to determine the optimal factor levels for maximizing surface roughness and minimizing residue burial. Data were analyzed using a second-order model and Design Expert V11 software. The best model was selected based on statistical criteria.
Results and Discussion
Modeling soil surface roughness and crop residue incorporation revealed that the second-order regression model, with high coefficients of determination (R² = 0.983 and 0.96), was capable of accurately predicting these indices. The interaction effects of tillage speed and depth were significant (P < 0.01). In this study, the effect of tillage depth on soil surface roughness was greater than that of tractor speed. The regression model indicated that tillage depth plays a primary role in the amount of crop residue incorporation. Moldboard plowing demonstrated that increasing depth, particularly at high speeds, leads to increased roughness and residue incorporation, whereas increasing speed, especially at shallow depths, reduces roughness and increases incorporation. The maximum roughness was observed at the deepest tillage depth and lowest speed, while the shallowest depth and highest speed resulted in the minimum roughness.
Tillage depth and speed influence soil surface roughness and bulk density. Higher speeds decrease furrow depth and ridge height; thus, lower speeds are recommended for creating greater roughness. The highest residue incorporation (85%) was achieved at a depth of 27.5 cm and speeds of 5 and 10 km h^-1, while the lowest (70%) occurred at a depth of 17.5 cm and a speed of 5 km h^-1. Depth was more influential than speed, and nonlinear models are necessary for more accurate modeling. The developed model, with a desirability of 81%, provides the maximum roughness (10.96 cm) and minimum residue incorporation (69.34%) for a moldboard plow at a speed of 5 km h^-1 and a tillage depth of 17.5 cm.
Conclusion
This study investigated the effects of conventional tillage methods in dry land areas on soil surface roughness and the extent of crop residue burial. The results indicate that increasing tillage depth leads to an increase in both indices, while reducing tractor speed increases roughness and decreases residue burial. The optimization model revealed that at a speed of 5 km h^-1 and a depth of 17.5 cm, minimum roughness and maximum residue incorporation can be achieved. To improve regional tillage practices, it is advised to conduct further research into the long-term effects of different tillage systems. This effort will ensure a well-informed selection and implementation of the most effective methods.
Acknowledgment
The authors gratefully acknowledge the financial support provided by the University of Lorestan.

Abstract Introduction
Global challenges threaten food security. In Iran, rice is a staple, with 770,000 ha under cultivation and an annual production of 3.75 million tonnes. The northen provinces of Guilan and Mazandaran dominant rice production, with Guilan only supplying about 50% of the nation’s demand. Advanced computational techniques such as metaheuristic algorithms and artificial intelligence offer powerful tools for problem-solving and modeling inspired by the adaptability of living organisms', and are increasingly applied to support agricultural management and sustainability. However, multi-gene genetic programming (MGP) has not yet been used for rice yield modeling in Iran. This study addresses that gap by evaluating the effectiveness of MGP and exploring its potential to enhance agricultural decision-making.
Materials and Methods
This research examines the yield performance of local rice cultivars, namely Hashemi and Ali Kazemi alongside high-yielding cultivars, including Fajr and Shiroudi in Rasht County, Iran. It utilizes library documents, face-to-face interviews, and MGP analysis. Data were collected from 385 randomly selected farmers and landowners in the region, during the 2020-2024 rice production years. Inputs from the energy sector, including fuel and electricity, water pumping equipment, agricultural machinery, fertilizers, pesticides, organic materials, and the energy output of paddy production, were examined. Energy equivalents were used to convert various types of energy into a common unit. To predict the yield of the two types of paddy cultivars using MGP, the structure of MGP trees was first designed with two objectives: maintaining the model accuracy and avoiding structural complexity. Parameter setting include population, generation and tournament sizes, gene limits, tree depth and size, and probabilities for elitism, crossover, and mutation. Additionally, various mathematical functions were utilized.
Results and Discussion
In examining total energy consumption and production in local and high-yielding cultivar farms, the results indicated a significant difference between the two varieties. In farms producing local varieties, the average energy consumption was 41,081.4 MJ, while the average energy production in these farms reached 23,771.9 MJ. In contrast, the average energy consumption in high-yielding cultivar farms was estimated at 41,118.8 MJ, whereas the average energy production in these farms was 42,220.04 MJ. The energy ratio, energy productivity, and specific energy indices for high-yielding varieties were 76.47%, 76.92%, and 77.70% higher, respectively, compared to local varieties, with the net energy gain index showing an improvement of more than 15 times. The higher energy ratio and energy productivity, along with lower specific energy and net energy gain, indicate that the high-yielding cultivar is more energy-efficient in terms of energy consumption. The MGP model converged after 100 iterations, providing the optimal solution. Changes in the best and mean fitness values indicated that as the iterations increased, the error gradually decreased and eventually stabilized, reflecting continuous improvement of the model during the training process and parameter tuning. Through cross-validation with varying training data set sizes, the findings revealed that the MGP model, when utilizing 65% of the total dataset, generated results that were remarkably similar to those achieved with 80% of the data. Hence, 65% is established as the optimal proportion for the training dataset. The coefficient of determination (R²) for the regression line in the training data set was higher than in the test phase for both varieties. In evaluating the MGP equations to assess the accuracy of the proposed model, the tree depth was increased from 4 to 12. For the local cultivar, the highest coefficient of determination (R²) at a tree depth of 4 was 0.95, while for the high-yielding cultivar, it was 0.94. The simpler structure at depth 4 resulted in a simpler mathematical equation. Finally, the effects of independent variables on the dependent variable, paddy yield, were examined. It was found that organic materials, such as compost, seed, rice straw and husks, were the most significant factors influencing the estimation of paddy yield in both varieties.
Conclusion
Since modeling focuses on predicting crop yield and making data-driven scientific and practical decisions, the results of this study represent an important step toward advancing sustainable agriculture. It is recommended that farmers seek up to date insights from consultants and participate in workshops to increase their sustainable yields.

Abstract Introduction
One of the most important parts of agricultural operations is tillage, which accounts for about 60% of the total energy consumed. Therefore, reducing tillage energy demand by lowering the number of passes through the development of cost-effective machinery is highly essential in modern farming. One of the main implements that helps farmers achieve this is the disc harrow. As the most important secondary tillage tool, the disc harrow improves soil structure, breaks up clods, and increases the penetration of water and air into the soil. However, its optimal performance is influenced by parameters such as disc diameter, disc edge type (toothed or plain), disc gang angle, and tractor forward speed. Soil bins, as controlled environments for testing tillage tools, serve as an ideal alternative to agricultural lands. They allow accurate simulation of field conditions while minimizing the effects of climate change and variable soil properties.
Materials and Methods
The present study was conducted with the aim of designing, constructing, and evaluating a disc harrow carrier chassis in the controlled environment of a laboratory soil bin. First, the design phase was carried out using SolidWorks 2020 software, followed by an analysis of the design performance under maximum load using the von Mises method. The next step was the construction of the design. After construction, the evaluation phase was performed by examining the effects of four independent input variables: forward speed (6.43 and 13.15 m min⁻¹), soil moisture content (2.37 and 13.25 percent on a wet basis), disc edge type (plain or toothed), and disc gang angle (0, 15, and 30 degrees), on the dependent output variable, draft force. Each test was replicated three times, resulting in a total of 72 tests.
Results and Discussion
The results showed that the engineered chassis exhibited sufficient strength during the initial evaluation tests, with all components performing well. The findings indicated that increasing forward speed and disc gang angle led to higher draft force, while higher soil moisture levels reduced draft force. Under low moisture conditions, plain discs generated greater draft force; however, this trend reversed as moisture increased. The highest draft requirement (3.588 N) was observed for plain discs at 2.37% moisture, while the lowest (1.724 N) occurred at 13.25% moisture. At a forward speed of 6.43 m min⁻¹, plain and toothed discs required equal draft, but at 13.15 m min⁻¹, the toothed discs required substantially more draft.
Conclusion
The experiments showed that there was no significant difference in draft force between disc gang angles of 0 and 15 degrees. However, increasing the angle from 15 to 30 degrees caused a significant rise in draft force. This indicates that the initial increase in gang angle has a smaller effect, but beyond 15 degrees the impact becomes more pronounced. Therefore, selecting an appropriate disc gang angle can help reduce fuel consumption and improve the productivity of agricultural machinery. Both increasing disc gang angle and forward speed raise draft force because soil resistance to disc movement increases. At higher speeds, the disc must exert more force to cut and move the soil, leading to higher energy consumption and greater equipment wear. Conversely, at lower speeds, draft force decreases, but tillage efficiency may be reduced and plowing uniformity may be affected.