AgriEngineering, Volume 6, Issue 2 (June 2024) – 19 articles

The need to use environmentally friendly substances in agriculture for pest control has become increasingly urgent in recent years. This was generated by humanity’s awareness of the harmful effects of chemicals with increased persistence, which accumulated in nature and harmed living beings. Essential oils are among the most important biopesticides and could significantly contribute to the expansion of ecological agriculture, replacing traditional methods. However, for judicious use, it is necessary to have a thorough knowledge of the mechanisms by which these oils act on both harmful and useful insects. An important step in transitioning from theory to practice is adapting essential oil application technologies for open fields, overcoming the difficulties created by their high volatility and low remanence, which results in a rapid reduction in the toxic effect. The review proposes an in-depth, up-to-date analysis of the existing literature on these subjects, aiming to provide researchers with some potential future study directions and practitioners with a solid base of information regarding the interaction between insects and essential oils. Full article

Agricultural expansion and intensification worldwide has caused a reduction in ecological infrastructures for insects, herbaceous plants, and vertebrate insectivores, among other organisms. Agriculture is recognized as one of the key influences in biodiversity decline, and initiatives such as the European Green Deal highlight the need to reduce ecosystem degradation. Among fruit crops, grapes are considered one of the most intensive agricultural systems with the greatest economic relevance. This study presents a compilation of management practices to enhance biodiversity performance, which applies generally to the agricultural sector and, in particular, to viticulture, concerning the diversity of plants, semi-natural habitats, soil management, and the chemical control strategies and pesticides used in agricultural cultivation. Through a critical review, this study identifies a set of recommendations for biodiversity performance and their corresponding effects, contributing to the dissemination of management options to boost biodiversity performance. The results highlight opportunities for future investigations in determining the needed conditions to ensure both biodiversity enhancement and productive gains, and understanding the long-term effects of innovative biodiversity-friendly approaches. Full article

The proposal for a method of identifying the occurrence of desertification that has a strong association with in situ data leads to more assertive results when analysing the contribution of climate and social and economic factors to advancing the process. This study aimed to develop a methodology called the RisDes_Index to evaluate the evolution of the desertification process based on satellite data. The concept of the RisDes_Index method was based on the reflectance variables of the R, B and G bands, albedo and LAI of the Landsat 5/TM and Landsat 8/OLI satellites. Principal component analysis was used to assess the biophysical basis of the RisDes_Index by associating the results with micrometeorological data, physical and chemical properties, and vegetation cover data collected from five experimental sites in the semi-arid region of Brazil. These sites included one from a seasonally dry forest (i.e., the Caatinga), an agricultural cactus plantation, an area undergoing desertification, and two irrigated sugarcane crops (wetlands), one with and one without straw cover. The RisDes_Index was applied to all pixels of the images from 5 December 1991, 14 November 2001, 20 November 2009 and 6 October 2016 of an important desertification nucleus (DN) in the semi-arid region of Brazil, i.e., the DN of Cabrobó. The proposed RisDes_Index was able to identify areas with significant processes of desertification, which mainly occur in areas of sandy, acidic, bare soils with a high β value (Bowen ratio) and high soil temperature. The results of the RisDes_Index showed that in 5 December 1991, desertified areas comprised 38% of the total area of the DN of Cabrobó, expanding to 51% in 2016. Application of the RisDes_Index confirmed the advance of desertification in the DN of Cabrobó. This was due to a consequent increase in the water deficit and intensified deforestation to increase the areas of livestock farming. The RisDes_Index proved to be a robust method, as its estimation based on simple satellite products exhibited a strong association with biophysical variables of areas with different land uses and degradation levels. Thus, it is suggested that the RisDes_Index be applied in various regions of the world, with the idea of directing action to meet the advance of desertification. Full article

Chrysanthemums, a significant genus within the Asteraceae, hold a paramount position in the global floricultural industry, second only to roses in market demand. The proliferation of diverse chrysanthemum cultivars presents a formidable challenge for accurate identification, exacerbated by the abundance of varieties, intricate floral structures, diverse floret types, and complex genetic profiles. Precise recognition of chrysanthemum phenotypes is indispensable to navigating these complexities. Traditional methods, including morphology studies, statistical analyses, and molecular markers, have fallen short due to their manual nature and time-intensive processes. This study presents an innovative solution employing deep learning techniques for image-based chrysanthemum phenotype recognition. Leveraging machine learning, our system autonomously extracts key features from chrysanthemum images, converting morphological data into accessible two-dimensional representations. We utilized Support Vector Machine (SVM) and Multilayer Perceptron (MLP) algorithms to construct frameworks for processing image data and classifying chrysanthemum cultivars based on color, shape, and texture. Experimental results, encompassing 10 cultivars, 10 flower colors, and five flower shapes, consistently demonstrated recognition accuracy ranging from 79.29% up to 97.86%. This tool promises streamlined identification of flower traits, and we anticipate its potential for real-time identification enhancements in future iterations, promising advances in chrysanthemum cultivation and exportation processes. Our approach offers a novel and efficient means to address the challenges posed by the vast diversity within chrysanthemum species, facilitating improved management, breeding, and marketing strategies in the floricultural industry. Full article

Knowledge of how certain crops respond to water stress is one of the prerequisites for choosing the best variety and best management practices to maximize crop water productivity (WP_c). The selection of a more efficient protocol for managing irrigation depths throughout the cultivation cycle and in the maturation process at the end of the growth period for each sugarcane variety can maximize bioethanol productivity and WP_c for bioethanol, sugar and biomass, in addition to the total energy captured by the sugarcane canopy in the form of dry biomass. This study aimed to evaluate the effect of four irrigation depths and four water deficit intensities on the maturation phase for eight sugarcane varieties under drip irrigation, analyzing the responses related to WP_c for bioethanol, sugar and biomass. These experiments were conducted at the University of São Paulo. The plots were positioned in three randomized blocks, and the treatments were distributed in a factorial scheme (4 × 8 × 4). The treatments involved eight commercial varieties of sugarcane and included four water replacement levels and four water deficits of increasing intensity in the final phase of the crop season. It was found that for each variety of sugarcane, there was an optimal combination of irrigation management strategies throughout the cycle and during the maturation process. The RB966928 variety resulted in the best industrial bioethanol yield (68.7 L·Mg⁻¹), WP_c for bioethanol (0.97 L·m⁻³) and WP_c for sugar (1.71 kg·m⁻³). The energy of the aerial parts partitioned as sugar had a direct positive correlation with the availability of water in the soil for all varieties. The RB931011 variety showed the greatest potential for converting water into shoots with an energy of 1.58 GJ·ha⁻¹·mm⁻¹, while the NCo376 variety had the lowest potential at 1.32 GJ·ha⁻¹·mm⁻¹. The productivity of first-generation bioethanol had the highest values per unit of planted area for the greatest water volumes applied and transpired by each variety; this justifies keeping soil moisture at field capacity until harvesting time only for WR100 water replacement level with a maximum ethanol potential of 13.27 m³·ha⁻¹. Full article

Monitoring crop height during different growth stages provides farmers with valuable information important for managing and improving expected yields. The use of synthetic aperture radar Sentinel-1 (S-1) and Optical Sentinel-2 (S-2) satellites provides useful datasets that can assist in monitoring crop development. However, studies exploring synergetic use of SAR S-1 and optical S-2 satellite data for monitoring crop biophysical parameters are limited. We utilized a time-series of monthly S-1 satellite data independently and then used S-1 and S-2 satellite data synergistically to model wheat-crop height in this study. The polarization backscatter bands, S-1 polarization indices, and S-2 spectral indices were computed from the datasets. Optimized Random Forest Regression (RFR), Support Vector Machine Regression (SVMR), Decision Tree Regression (DTR), and Neural Network Regression (NNR) machine-learning algorithms were applied. The findings show that RFR (R² = 0.56, RMSE = 21.01 cm) and SVM (R² = 0.58, RMSE = 20.41 cm) produce a low modeling accuracy for crop height estimation with S-1 SAR data. The S-1 and S-2 satellite data fusion experiment had an improvement in accuracy with the RFR (R² = 0.93 and RMSE = 8.53 cm) model outperforming the SVM (R² = 0.91 and RMSE = 9.20 cm) and other models. Normalized polarization (Pol) and the radar vegetation index (RVI_S1) were important predictor variables for crop height retrieval compared to other variables with S-1 and S-2 data fusion as input features. The SAR ratio index (SAR RI 2) had a strong positive and significant correlation (r = 0.94; p < 0.05) with crop height amongst the predictor variables. The spatial distribution maps generated in this study show the viability of data fusion to produce accurate crop height variability maps with machine-learning algorithms. These results demonstrate that both RFR and SVM can be used to quantify crop height during the growing stages. Furthermore, findings show that data fusion improves model performance significantly. The framework from this study can be used as a tool to retrieve other wheat biophysical variables and support decision making for different crops. Full article

In breeding programs, the demand for high-throughput phenotyping is substantial as it serves as a crucial tool for enhancing technological sophistication and efficiency. This advanced approach to phenotyping enables the rapid and precise measurement of complex traits. Therefore, the objective of this study was to estimate the correlation between vegetation indices (VIs) and grain yield and to identify the optimal timing for accurately estimating yield. Furthermore, this study aims to employ photographic quantification to measure the characteristics of corn ears and establish their correlation with corn grain yield. Ten corn hybrids were evaluated in a Complete Randomized Block (CRB) design with three replications across three locations. Vegetation and green leaf area indices were estimated throughout the growing cycle using an unmanned aerial vehicle (UAV) and were subsequently correlated with grain yield. The experiments consistently exhibited high levels of experimental quality across different locations, characterized by both high accuracy and low coefficients of variation. The experimental quality was consistently significant across all sites, with accuracy ranging from 79.07% to 95.94%. UAV flights conducted at the beginning of the crop cycle revealed a positive correlation between grain yield and the evaluated vegetation indices. However, a positive correlation with yield was observed at the V5 vegetative growth stage in Lavras and Ijaci, as well as at the V8 stage in Nazareno. In terms of corn ear phenotyping, the regression coefficients for ear width, length, and total number of grains (TNG) were 0.92, 0.88, and 0.62, respectively, demonstrating a strong association with manual measurements. The use of imaging for ear phenotyping is promising as a method for measuring corn components. It also enables the identification of the optimal timing to accurately estimate corn grain yield, leading to advancements in the agricultural imaging sector by streamlining the process of estimating corn production. Full article

A floating greenhouse for growing oyster mushrooms can be operated remotely via a mobile phone. This innovative system can enhance mushroom production and quality while saving time. By using the Android OS operating system on a mobile phone (Internet Mobile Device with Android OS, MGT Model: T10), users can adjust the humidity and temperature within the greenhouse. This approach is particularly beneficial for older adults. Create a smart floating greenhouse that can be controlled remotely to cultivate oyster mushrooms. It would help to enhance the quality of the mushrooms, reduce the time required for cultivation, and increase the yield per planting area. We carefully examined the specifications and proceeded to create a greenhouse that could float. In addition, we have developed a unit that could control temperature and humidity, a solar cell unit, and a rack for growing mushrooms. Our greenhouses were operated remotely. To determine the best conditions for growing plants in a floating greenhouse, we conducted a test to measure temperature and humidity. We then compared our findings to those of a traditional greenhouse test and determined the optimal parameters for floating greenhouse growth. These parameters include growth time, temperature, humidity, and weight. A mushroom nursery that can be controlled remotely and floats on water consists of four main components: a structure to regulate temperature and humidity, solar cells, and mushroom racks. Research shows that mushrooms grown under this automated control system grow better than those grown through traditional methods. The harvest period is shorter, and the yield is higher than the typical yield of 1.81–1.22. When considering the construction and use of remote-controlled floating mushroom nurseries, the daily weight of mushrooms accounted for 20.22%. The company’s investment return rates were found to be 3.47 years, or 580.21 h per year, which is higher than the yield of traditional methods. This mobile phone remote control system, created by Arduino, is tailor-made for cutting-edge floating greenhouses that grow grey oyster mushrooms. It can be operated with ease via mobile devices and is especially user-friendly for elderly individuals. This system enables farmers to produce a high volume of quality breeds. Furthermore, those with fish ponds can utilize the system to increase their profits. Full article

The use of artificial lighting in a total or supplementary way is a current trend, with growing interest due to the increase in the global population and climate change, which require high-yield, quality, and fast-growing crops with less water and a smaller carbon footprint. This experiment aimed to evaluate the effect of light-emitting diode (LED) lighting on the production of basil, mustard, and red cabbage seedlings under controlled artificial conditions and in a greenhouse as a supplementary lighting regime. Under controlled conditions, the experiment was conducted with basil seedlings, comparing LED light with two wavelengths (purple and white light). In a greenhouse, mustard and red cabbage seedlings were evaluated under natural light (regular photoperiod) and with supplementary purple lighting of 3 h added to the photoperiod. The variables assessed were aerial fresh mass (AFM), aerial dry mass (ADM), root dry mass (RDM), plant length (PL), and leaf area (LA). Basil seedlings grown under purple light showed greater length and AFM than those grown under white light, with no effect on the production of secondary metabolites. In the greenhouse experiment, red cabbage seedlings showed an increase in AFM, ADM, and DRM with light supplementation, with no effect on LA. AFM showed no statistical difference in mustard seedlings, but the productive parameters LA, ADM, and DRM were higher with supplementation. None of the evaluated treatments influenced the production of phenolic compounds and flavonoids in the three species evaluated. Light supplementation affected red cabbage and mustard seedlings differently, promoting better development in some production parameters without affecting the production of phenolic compounds and flavonoids in either plant. Thus, light supplementation or artificial lighting can be considered a tool to enhance and accelerate the growth of seedlings, increasing productivity and maintaining the quality of the secondary metabolites evaluated. Thus, this technology can reduce operational costs, enable cultivation in periods of low natural light and photoperiod, and cultivate tropical species in temperate environments in completely artificial (indoor) conditions. Full article

The effects of phytopathogenic fungi on fruits and vegetables are a significant global concern, impacting various sectors including social, economic, environmental, and consumer health. This issue results in diminished product quality, affecting a high percentage of globally important fruits. Over the last 20 years, the use of chemical products in the agri-food sector has increased by 30%, leading to environmental problems such as harm to main pollinators, high levels of chemical residue levels, development of resistance in various phytopathogens, and health issues. As a response, various organizations worldwide have proposed programs aimed at reducing the concentration of active compounds in these products. Priority is given to alternative treatments that can mitigate environmental impact, control phytopathogens, and ensure low residuality and toxicity in fruits and vegetables. This review article presents the mechanisms of action of three alternative treatments: chitosan, citral, and hexanal. These treatments have the potential to affect the development of various pathogenic fungi found in tropical and subtropical fruits. It is important to note that further studies to verify the effects of these treatments, particularly when used in combination, are needed. Integrating the mechanisms of action of each treatment and exploring the possibility of generating a broad-spectrum effect on the development of pathogenic microorganisms in fruits is essential for a comprehensive understanding and effective management. Full article

The production of Explorer roses has historically been attractive due to the acceptance of the product around the world. This species of roses presents high sensitivity to physical contact and manipulation, creating a challenge to keep the final product quality after cultivation. In this work, we present a system that combines the capabilities of intelligent computer vision and unmanned aerial vehicles (UAVs) to identify the state of roses ready for cultivation. The system uses a deep learning-based approach to estimate Explorer rose crop yields by identifying open and closed rosebuds in the field using videos captured by UAVs. The methodology employs YOLO version 5, along with DeepSORT algorithms and a Kalman filter, to enhance counting precision. The evaluation of the system gave a mean average precision (mAP) of 94.1% on the test dataset, and the rosebud counting results obtained through this technique exhibited a strong correlation (R² = 0.998) with manual counting. This high accuracy allows one to minimize the manipulation and times used for the tracking and cultivation process. Full article

The paper presents research on measuring and the possibility of prediction of noise levels on the left and right sides of the operator within the cabin of an agricultural tractor when moving across various agrotechnical surfaces, considering movement velocity and tire pressures while employing machine learning techniques. Noise level measurements were conducted on a LANDINI POWERFARM 100 type tractor, and aligned with standards (HRN ISO 5008, HRN ISO 6396 and HRN ISO 5131). The obtained noise values were divided into two data sets (left and right set) and processed using multiple linear regression (mlr) and three machine learning methods (gradient boosting machine (gbm); support vector machine using radial basis function kernel (svmRadial); monotone multi-layer perceptron neural network (monmlp)). The most accurate method, considering surfaces, from the left side data set—(R² 0.515–0.955); (RMSE 0.302–0.704); (MAE 0.225–0.488)—and the right side—(R² 0.555–0.955); (RMSE 0.180–0.969); (MAE 0.139–0.644)—was monmlp predominantly, and to a lesser extent svmRadial. On analyzing the total data sets from the left and right sides regarding surfaces, gbm emerged as the most accurate method. The application of machine learning methods demonstrated data accuracy, yet in future research, measurements on certain surfaces may need to be repeated multiple times potentially to improve accuracy further. Full article

Potential soil production is closely related to the physical and mechanical properties. The aim of this paper was to evaluate the effect of different levels of soil compaction created by tractor chassis. The total area of the experimental plot was 13.22 ha. Up until 2019, a conventional tillage system had been used. The measurements were carried out with an innovative measuring device that allows for the continuous measurement of the horizontal penetrometry for comparative measurements while driving, which was designed at the Slovak University of Agriculture in Nitra. The measuring device measured the soil resistance in the tire track (On-track) and out of track (Off-track) as well as in three (50 s) sequences within one tractor pass. Three lines were chosen, where in each a pair of combinations was made. The results were subjected, in addition to graphical evaluation, to single factor ANOVA analysis. When comparing individual passes (PH1 to PH6), the statistical analysis showed that the results of the horizontal resistance measurements proved to be statistically significant (p < 0.05) with respect to the weight, number of passes, and tire underinflation. The highest compaction was caused by the first pass, while the higher weight of the tractor during the next pass had a smaller effect. Underinflating the tires ensured a reduction in compaction. Reducing the tractor tire pressure to 0.15 MPa resulted in a reduction in soil compaction of up to 16%. Full article

A lightweight strawberry detection and localization algorithm plays a crucial role in enabling the harvesting robot to effectively harvest strawberries. The YOLO model has often been used in strawberry fruit detection for its high accuracy, speed, and robustness. However, some challenges exist, such as the requirement for large model sizes, high computation operation, and undesirable detection. Therefore, the lightweight improved YOLOv5s-CGhostnet was proposed to enhance strawberry detection. In this study, YOLOv5s underwent comprehensive model compression with Ghost modules GCBS and GC3, replacing modules CBS and C3 in the backbone and neck. Furthermore, the default GIOU bounding box regressor loss function was replaced by SIOU for improved localization. Similarly, CBAM attention modules were added before SPPF and between the up-sampling and down-sampling feature fusion FPN–PAN network in the neck section. The improved model exhibited higher mAP@0.5 of 91.7% with a significant decrement in model size by 85.09% and a reduction in GFLOPS by 88.5% compared to the baseline model of YOLOv5. The model demonstrated an increment in mean average precision, a decrement in model size, and reduced computation overhead compared to the standard lightweight YOLO models. Full article

Satellite remote sensing data expedite crop yield estimation, offering valuable insights for farmers’ decision making. Recent forecasting methods, particularly those utilizing machine learning algorithms like Random Forest and Artificial Neural Networks, show promise. However, challenges such as validation performances, large volume of data, and the inherent complexity and inexplicability of these models hinder their widespread adoption. This paper presents a simpler approach, employing linear regression models fitted from vegetation indices (VIs) extracted from MODIS sensor data on the Terra and Aqua satellites. The aim is to forecast cotton yields in key areas of the Brazilian Cerrado. Using data from 281 commercial production plots, models were trained (167 plots) and tested (114 plots), relating seed cotton yield to nine commonly used VIs averaged over 15-day intervals. Among the evaluated VIs, Enhanced Vegetation Index (EVI) and Triangular Vegetation Index (TVI) exhibited the lowest root mean square errors (RMSE) and the highest determination coefficients (R²). Optimal periods for in-season yield prediction fell between 90 and 105 to 135 and 150 days after sowing (DAS), corresponding to key phenological phases such as boll development, open boll, and fiber maturation, with the lowest RMSE of about 750 kg ha⁻¹ and R² of 0.70. The best forecasts for early crop stages were provided by models at the peaks (maximum value of the VI time series) for EVI and TVI, which occurred around 80–90 DAS. The proposed approach makes the yield predictability more inferable along the crop time series just by providing sowing dates, contour maps, and their respective VIs. Full article

Over the years, agricultural management practices are being improved as they integrate Information and Communication Technologies (ICT) and Precision Agriculture tools. Regarding sugarcane crop production, this integration aims to reduce production cost, enhance input applications, and allow communication among different hardware and datasets, improving system sustainability. Sugarcane mechanization has some particularities that mandate the development of custom solutions based on digital tools, which are being applied globally in different crops. Digital mechanization can be conceived as the application of digital tools on mechanical operation. This review paper addresses different digital solutions that have contributed towards the mechanization of sugarcane crop production. The process of digitalization and transformation in agriculture and its related operations to sugarcane are presented, highlighting important ICT applications such as real-time mechanical operations monitoring and integration among operations, demonstrating their contributions and limitations regarding management efficiency. In addition, this article presents the major challenges to overcome and possible guidance on research to address these issues, i.e., poor communication technologies available, need for more focus on field and crop data, and lack of data interoperability among mechanized systems. Full article

A novel biomass production system, integrating the co-harvesting and co-storage of moist corn grain and stover, promises a reduction in delivered feedstock costs. In this innovative method, the dry grain traditionally utilized for feed or biofuel production will now be processed at a considerably greater moisture content. The adoption of this approach may necessitate a substantial redesign of existing material handling infrastructure to effectively accommodate the handling and storage of moist grain after processing by milling or grinding. A comprehensive study was conducted to quantify the physical properties of this grain after processing with a knife processor or a hammermill. The geometric mean particle size, bulk and tapped density, sliding angle, material coefficient of friction, and discharged angle of repose were quantified. Five grain treatments, either fermented or unfermented, and having different moisture contents, were used. After processing, the moist, fermented ground grain exhibited a significantly smaller particle size compared to the dry grain. Additionally, both moist processed grains resulted in a decreased bulk density and increased material sliding angle, friction coefficient, and angle of repose. The examined metrics collectively suggest that handling, mixing, and storing moist ground grain will pose significant challenges compared to conventional dry ground grain. This increased difficulty may lead to substantially higher costs, a crucial factor that must be carefully considered when evaluating the overall economics of implementing this new biomass production system using combined harvesting and storage of corn grain and stover. Full article

Most of the northeastern region of Brazil (NEB) has a maize production system based on family farming, with no technological advances and totally dependent on the natural rainfall regime, which is concentrated in 4 to 5 months in most parts of the region. This means that the productivity of this crop is low in the NEB. In the northern mesoregions of the NEB, rainfall is concentrated between January and June, in the east of the NEB from April to September, and in the west of the NEB from October to March. The growing season takes place during these semesters. With this in mind, our objective was to develop a model based on canonical correlation analysis (CCA) to predict corn production in the mesoregions of the NEB between 1981 and 2010, using accumulated precipitation per semester as the predictor variable and predicting the observed production in kg/ha. Our results showed that the CCA model presented higher correlations between observed and simulated production than that obtained simply from the direct relationship between accumulated rainfall and production. The other two metrics used, RMSE and NRMSE, showed that, on average, in most mesoregions, the simulation error was around 200 kg/ha, but the accuracy was predominantly moderate, around 29% in most mesoregions, with values below 20% in six mesoregions, indicative of better model accuracy, and above 50% in two mesoregions, indicative of low accuracy. In addition, we investigated how the different combinations between two modes of climate variability with a direct influence on precipitation in the NEB impacted production in these 30 years, with the combination of El Niño and a positive Atlantic dipole being the most damaging to harvests, while years when La Niña and a negative Atlantic dipole acted together were the most favorable. Despite the satisfactory results and the practical applicability of the model developed, it should be noted that the use of only one predictor, rainfall, is a limiting factor for better model simulations since other meteorological variables and non-climatic factors have a significant impact on crops. However, the simplicity of the model and the promising results could help agricultural managers make decisions in all the states that make up the NEB. Full article

Seed quality significantly affects how well crops grow. Traditional methods for checking seed quality, like seeing how many seeds sprout or using a chemical test called tetrazolium testing, require people to look at the seeds closely, which takes a lot of time and effort. Nowadays, computer vision, a technology that helps computers see and understand images, is being used more in farming. Here, we use computer vision with X-ray imaging to assist experts in rapidly and accurately assessing seed quality. We looked at three different sets of seeds using X-ray images and used YOLOv8 to analyze them. YOLOv8 software measures different aspects about seeds, like their size and the area taken up by the part inside, called the endosperm. Based on this information, we put the seeds into four groups depending on how much endosperm they have. Our results show that the YOLOv8 program works well in identifying and separating the endosperm, even with a small amount of data. Our method was able to accurately identify the endosperm about 95.6% of the time. This means that our approach can help determine how effective the seeds are to plant crops. Full article