AgriEngineering, Volume 6, Issue 4 (December 2024) – 65 articles

Ensuring the quality of medicinal herbs in the herbal market is crucial. However, the genetic and physical similarities among medicinal materials have led to issues of mixing and counterfeit distribution, posing significant challenges to quality assurance. Recent advancements in deep learning technology, widely applied in the field of computer vision, have demonstrated the potential to classify images quickly and accurately, even those that can only be distinguished by experts. This study aimed to develop a classification model based on deep learning technology to distinguish RGB images of seeds from Ziziphus jujuba Mill. var. spinosa, Ziziphus mauritiana Lam., and Hovenia dulcis Thunb. Using three advanced convolutional neural network (CNN) architectures—ResNet-50, Inception-v3, and DenseNet-121—all models demonstrated a classification performance above 98% on the test set, with classification times as low as 23 ms. These results validate that the models and methods developed in this study can effectively distinguish Z. jujuba seeds from morphologically similar species. Furthermore, the strong performance and speed of these models make them suitable for practical use in quality inspection settings. Full article

This study presents a comparative analysis of YOLO detection models for the accurate identification of bean leaf diseases caused by Coleoptera pests in natural environments. By using a manually collected dataset of healthy and infected bean leaves in natural conditions, we labeled at the leaf level and evaluated the performance of the YOLOv5, YOLOv8, YOLOv9, YOLOv10, and YOLOv11 models. Mean average precision (mAP) was used to assess the performance of the models. Among these, YOLOv9e exhibited the best performance, effectively balancing precision and recall for datasets with limited size and variability. In addition, we integrated the Sophia optimizer and PolyLoss function into YOLOv9e and enhanced it, providing even more accurate detection results. This paper highlights the potential of advanced deep learning models, optimized with second-order optimizers and custom loss functions, in improving pest detection, crop management, and overall agricultural yield. Full article

Machine learning algorithms are increasingly used to enhance agricultural productivity cost-effectively. A critical task in precision agriculture is locating a plant’s root collar. This is required for the site-specific fertilization of the plants. Though state-of-the-art machine learning models achieve stellar performance in object detection, they are often sensitive to noisy inputs and variation in environment settings. In this paper, we propose an innovative technique of smooth perturbations to improve the robustness of root collar detection tasks using the YOLOv5 neural network model. We train a YOLOv5 model on blueberry image data for root collar detection. A small amount noise is added as a smooth perturbation to the bounding box of dimensions 50× 50, and this perturbed image is fed for training. Furthermore, we introduce an additional test set that represents the out-of-distribution (O.O.D.) case by applying Gaussian blur on test images to simulate particle situation. We use three different image datasets to train our model, the (i) Estonian blueberry, (ii) Serbian blueberry image, and (iii) public dataset sourced from Roboflow datasets, of sample size 118, 2779, and 2993, respectively. We achieve an overall precision of 0.886 on perturbed blueberry images compared to 0.871 on original (unperturbed) images for the O.O.D. test set. Similarly, our smooth perturbation training has achieved an mAP of 0.828, which significantly increases against the result of normal training, which only reaches 0.794. The result proves that our proposed smooth perturbation is an effective method to increase the robustness and generalizability of the object detection task. Full article

Efficiently managing agricultural systems necessitates accurate data collection from crops to examine phenotypic characteristics and improve productivity. Traditional data collection processes for specialty horticultural crops are often subjective, labor-intensive, and may not provide accurate information for precise management decisions in phenotypic studies and crop production. Reliable and standardized techniques to record and evaluate crop features using agricultural technology are essential for improving agricultural systems. The objective of the research was to develop a methodology for accurate measurement of blackberry flowers and vegetation coverage using UAV remote sensing and image analysis. The UAV captured 20,812 images in the visible spectrum, and ImageJ software (version 1.54k) was used for segmenting floral and vegetative coverage to calculate variety-specific flower coverage. A moderately strong positive correlation (r = 0.71) was found between flower-to-vegetation ratio (FVR) and visually estimated flower area, validating UAV-derived flower coverage as a reliable method for estimating flower density in blackberries. The regression model explained 51% of the variance in flower estimates (R² = 0.51), with a root mean square error (RMSE) of 2.79 flower/cm². Additionally, distinct temporal flowering patterns were observed between primocane- and floricane fruiting blackberries. Vegetative growth also exhibited stability, with strong correlations between consecutive weeks. The temporal analysis provided insight into growth phases and flowering peaks critical for time-sensitive management practices. UAV computer vision for quantifying blackberry phenotypic features is an effective tool and a unique methodology that speeds up the data collection process at high accuracy for breeding research and farm data management. Full article

Oulema melanopus L., 1758 (Coleoptera: Chrysomelidae) is one of the significant pests affecting cereal crops in Europe. Its damage is evident in the destruction of leaves during the spring growing season, leading to substantial impacts on both the quantity and quality of the harvested yields. The study aimed to evaluate the extent of leaf surface damage, changes in chlorophyll content caused by this pest, and the subsequent effects on yield quality. To achieve this, two experimental parcels were established, each subjected to different pesticide treatments during the spring vegetation cycle, but notably, with the difference that one parcel did not receive insecticide applications. The phytosanitary status, yield quantity, and quality parameters of thes parcels were compared. Chlorophyll content in damaged and undamaged plants was monitored in vivo using SPAD measurements, while the extent of leaf surface damage was assessed through image analysis using GIMP software 2.10.32. Harvested grain underwent milling and baking analysis, with milling and baking-quality indicators measured using a NIR grain analyzer. The results revealed that omitting springtime insecticide treatments during the emergence of O. melanopus led to significant reductions in leaf area and yield quality. In untreated parcels, leaf decession followed linear progression, reaching 35–40% within 20 days. This damage correlated with the decline in SPAD index values, indicating a 40–50% reduction in chlorophyll content dependent photosynthetic activity. Consequently, there were substantial decreases in milling and baking qualities, including nearly 30% reductional protein-content indicators and 10% in the Hagberg falling number. In summary, our large-scale field experiments demonstrated that persistent O. melanopus damage in wheat fields significantly reduced both the quantity and quality of yields, particularly protein content. These facts underscore the economic importance of timely pest-control measures to mitigate damage and preserve crop value. Full article

This study evaluated the germination of Cinchona spp. seeds under controlled environmental conditions within a geodesic dome equipped with photovoltaic energy. The main objective was to assess how stable temperature and humidity, along with potassium nitrate (KNO₃) and specific LED light treatments, affect the germination rate and plant growth. The results indicate that Cinchona spp. seeds germinate effectively inside the dome, even under temperature and humidity conditions that differ from their natural habitat. Among the evaluated conditions, the treatment with 1000 ppm of KNO₃ and white LED light (LM 1000 ppm) showed the highest germination rate, achieving 72.5% with an average of 1.5 seeds germinated per day. Agronomic evaluations showed that this treatment also led to superior growth metrics, including an average plant height of 2.1 cm, an average leaf count of 3.6, and a dry weight of 0.0013 g. This research highlights the potential of controlled environments, such as geodesic domes, to optimize germination and early growth in endangered plant species. The combination of environmental control with KNO₃ treatments offers a valuable approach to enhancing the propagation of Cinchona spp., providing practical implications for conservation and reforestation efforts. This work provides a foundation for further studies on optimizing germination and growth conditions for other native and endangered species in controlled environments. Full article

One of the oldest techniques for preserving food is drying. Dehydrating foods reduces their moisture content and increases their shelf life by preventing microbiological activity. Food placed on the ground to dry in the sun is a common sight in rural areas of low- and middle-income countries but requires a large amount of land and can lead to food degradation by overexposure to the sun, insects, and vermin. This study designed, fabricated, and evaluated the performance of a solar dryer in comparison to direct sun drying for efficiency and product quality, utilizing bananas and potatoes as representative foods. The dryer was produced and tested within the context of Bangladesh, unlike other commercial devices. With its mild steel frame, fan, solar collector, and DC battery, the dryer achieved a drying efficiency of 49.2% by reaching a drying chamber temperature of 71 °C, which is 30 °C higher than ambient. Drying times were decreased, and samples of potatoes and bananas reached equilibrium moisture content in 6 h as opposed to 9 h for direct sun drying. The moisture content of solar-dried foods was between 12 and 13 percent, making them appropriate for long-term storage. Bioactive substances such as phenolic content and DPPH scavenging activity were reduced by 18% and 21%, respectively, in comparison to direct sun drying. Quality assessments showed that there was little loss in color and nutrients for solar-dried samples. With a one-year payback period, an economic attribute of 3.26, and a life cycle benefit of BDT 310,651 (USD 2597.68), economics show the dryer’s feasibility. The solar dryer functioned faster than direct sun drying due to its significantly higher heat generation. The solar dryer was more efficient, effective, and economic within the context of Bangladesh and other low- and middle-income countries. Full article

Identifying machine learning models that are capable of classifying soybean genotypes according to micronutrient content using only spectral data as input is relevant and useful for plant breeding programs and agricultural producers. Therefore, our objective was to classify soybean genotypes according to leaf micronutrient levels using multispectral images. In the 2019/20 crop year, a field experiment was carried out with 103 F2 soybean populations in the experimental area of the Federal University of Mato Grosso do Sul, in Chapadão do Sul, Brazil. The data were subjected to machine learning analysis using algorithms to classify genotypes according to leaf micronutrient content. The spectral data were divided into three distinct input groups to be tested in the machine learning models: spectral bands (SBs), vegetation indices (VIs), and combining VIs and SBs. The algorithms tested were: J48 Decision Tree (J48), Random Forest (RF), Support Vector Machine (SVM), Perceptron Multilayer Neural Network (ANN), Logistic Regression (LR), and REPTree (DT). All model parameters were set as the default settings in Weka 3.8.5 software. The Random Forest (RF) algorithm outperformed (>90 for CC and >0.9 for Kappa and Fscore) regardless of the input used, demonstrating that it is a robust model with good data generalization capacity. The DT and J48 algorithms performed well when using VIs or VIs+SBs inputs. The SVM algorithm performed well with VIs+SBs as input. Overall, inputs containing information about VIs provided better results for the classification of soybean genotypes. Finally, when deciding which data should serve as input in scenarios of spectral bands, vegetation indices or the combination (VIs+SBs), we suggest that the ease and speed of obtaining information are decisive, and, therefore, a better condition is achieved with band-only inputs. This allows for the identification of genetic materials that use micronutrients more efficiently and the adaptation of management practices. In addition, the decision to be made can be made quickly, without the need for chemical evaluation in the laboratory. Full article

The application of hyperspectral data in machine learning models can contribute to the rapid and accurate determination of caffeine content in coffee beans. This study aimed to identify the machine learning algorithm with the best performance for predicting caffeine content and to find input data for these models that can improve the accuracy of these algorithms. The coffee beans were harvested one year after the seedlings were planted. The fresh beans were taken to the spectroscopy laboratory (Laspec) at the Federal University of Mato Grosso do Sul, Chapadão do Sul campus, for spectral evaluation using a spectroradiometer. For the analysis, the dried coffee beans were ground and sieved for the quantification of caffeine, which was carried out using a liquid chromatograph on the Waters Acquity 1100 series UPLC system, with an automatic sample injector. The spectral data of the beans, as well as the spectral data of the roasted and ground coffee, were analyzed using machine learning (ML) algorithms to predict caffeine content. Four databases were used as input: the spectral information of the bean (CG), the spectral information of the bean with additional clone information (CG+C), the spectral information of the bean after roasting and grinding (CGRG) and the spectral information of the bean after roasting and grinding with additional clone information (CGRG+C). The caffeine content was used as an output to be predicted. Each database was subjected to different machine learning models: artificial neural networks (ANNs), decision tree (DT), linear regression (LR), M5P, and random forest (RF) algorithms. Pearson’s correlation coefficient, mean absolute error, and root mean square error were tested as model accuracy metrics. The support vector machine algorithm showed the best accuracy in predicting caffeine content when using hyperspectral data from roasted and ground coffee beans. This performance was significantly improved when clone information was included, allowing for an even more accurate analysis. Full article

The removal of plastic contamination from cotton lint is a critical issue for the U.S. cotton industry. One primary source of this contamination is the plastic wrap used on cotton modules by John Deere round module harvesters. Despite rigorous efforts by cotton ginning personnel to eliminate plastic during module unwrapping, fragments still enter the gin’s processing system. To address this, we developed a machine-vision detection and removal system using low-cost color cameras to identify and expel plastic from the gin-stand feeder apron, preventing contamination. However, the system, comprising 30–50 ARM computers running Linux, poses significant challenges in terms of calibration and tuning, requiring extensive technical knowledge. This research aims to transform the system into a plug-and-play appliance by incorporating an auto-calibration algorithm that dynamically tracks cotton colors and excludes plastic images to maintain calibration integrity. We present the image dataset that was used to validate the design, consisting of several key AI Vision-Transformer image classifiers that form the heart of the auto-calibration algorithm, which is expected to reduce setup and operational overhead significantly. The auto-calibration feature will minimize the need for skilled personnel, facilitating the broader adoption of the plastic removal system in the cotton ginning industry. Full article

In line with the concept of precision agriculture, this study aimed to validate the use of digital aerial images captured using a remotely piloted aircraft (RPA) for collecting zootechnical data on cattle feedlot systems in a tropical environment. Images were captured on 21 non-consecutive days in 110 pens with up to 150 animals each. Conventional and RPA-based methods were adopted to determine animal behavior, feed trough levels, animal counts, and pen conditions. Data analysis revealed almost perfect agreement (kappa coefficient = 0.901) between trough readings taken by conventional and RPA methods as well as substantial agreement for fecal score (kappa coefficient = 0.785) and surface conditions (kappa coefficient = 0.737). However, animal counts and water quality scores showed only fair agreement, suggesting challenges in using RPA for these specific tasks. The results indicated that RPA represents a viable alternative to conventional methods for monitoring zootechnical indices in feedlots, offering benefits in terms of accuracy, efficiency, and cost-effectiveness. The implementation of RPA-based methods holds potential for improving animal management, welfare, and yield in feedlot systems. Full article

Increasing concerns of animal welfare in the commercial pig industry include aggression between pigs as it affects their health and growth. Early detection of aggressive behaviors is essential for optimizing their living environment. A major challenge for detection is that these behaviors are observed occasionally in normal conditions. Under this circumstance, a limited amount of aggressive behavior data will lead to class imbalance issue, making it difficult to develop an effective classification model for the detection of aggressive behaviors. In order to address this issue, this study has been designed with the aim of developing an anomaly detection model for identifying aggressive behaviors in pigs, enabling better management of the imbalanced class distribution and effective detection of infrequent aggressive episodes. The model consists of a convolutional neural network (CNN) and a variational long short-term memory (LSTM) autoencoder. Additionally, we adopted a training method similar to weakly supervised anomaly detection and included a few aggressive behavior data in the training set for prior learning. To effectively utilize the aggressive behavior data, we introduced Reconstruction Loss Inversion, a novel objective function, to train the autoencoder-based model, which increases the reconstruction error for aggressive behaviors by inverting the loss function. This approach has improved detection accuracy in both AUC-ROC and AUC-PR, demonstrating a significant enhancement in distinguishing aggressive episodes from normal behavior. As a result, it outperforms traditional classification-based methods, effectively identifying aggressive behaviors in a natural pig-farming environment. This method offers a robust solution for detecting aggressive animal behaviors and contributes to improving their welfare. Full article

Manual weed control is becoming increasingly costly, necessitating the development of alternative methods. This work investigates the feasibility of using laser technology for autonomous weed regulation. We developed a system utilizing a laser scanner to target and eliminate weeds, which was first tested using a pilot laser for accuracy and performance. Subsequently, the system was upgraded with a high-power fiber laser. Experimental results demonstrated a high weed destruction accuracy with real-time capabilities. The system achieved efficient weed control with minimal environmental impact, providing a potential alternative for sustainable agriculture. Full article

High-resolution images captured by Unmanned Aerial Vehicles (UAVs) play a vital role in precision agriculture, particularly in evaluating crop health and detecting weeds. However, the detailed pixel information in these images makes classification a time-consuming and resource-intensive process. Despite these challenges, UAV imagery is increasingly utilized for various agricultural classification tasks. This study introduces an automatic classification method designed to streamline the process, specifically targeting cassava plants, weeds, and soil classification. The approach combines K-means unsupervised classification with spectral trend-based labeling, significantly reducing the need for manual intervention. The method ensures reliable and accurate classification results by leveraging color indices derived from RGB data and applying mean-shift filtering parameters. Key findings reveal that the combination of the blue (B) channel, Visible Atmospherically Resistant Index (VARI), and color index (CI) with filtering parameters, including a spatial radius (sp) = 5 and a color radius (sr) = 10, effectively differentiates soil from vegetation. Notably, using the green (G) channel, excess red (ExR), and excess green (ExG) with filtering parameters (sp = 10, sr = 20) successfully distinguishes cassava from weeds. The classification maps generated by this method achieved high kappa coefficients of 0.96, with accuracy levels comparable to supervised methods like Random Forest classification. This technique offers significant reductions in processing time compared to traditional methods and does not require training data, making it adaptable to different cassava fields captured by various UAV-mounted optical sensors. Ultimately, the proposed classification process minimizes manual intervention by incorporating efficient pre-processing steps into the classification workflow, making it a valuable tool for precision agriculture. Full article

In tropical regions, maintaining crop residues in the soil is challenging. Silicon (Si) may increase the persistence of these residues in the soil, as it is a precursor to lignin, providing a gradual release of nutrients for subsequent crops. Therefore, the objective of this study was to evaluate the influence of different doses of calcium silicate (Ca₂SiO₄) (0, 1, 2, and 3 Mg ha⁻¹) and limestone (0, 1, 2, and 3 Mg ha⁻¹) on the lignin content, residue decomposition, and nutrient release of four cover crops—Pennisetum glaucum, Urochloa ruziziensis, Crotalaria spectabilis, and Cajanus cajan—at various decomposition stages following cover crop management (0, 30, 60, 90, and 120 days). The experiment was conducted in the field at the experimental area of the Faculty of Engineering at Ilha Solteira-UNESP, located in the municipality of Selvíria, state of Mato Grosso do Sul, on Ferralsol. The decomposition rate of the residues was assessed using the decomposition bag method, which was installed after cover crop management. The concentrations of nitrogen (N), phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), sulfur (S), Si, lignin, and cellulose were determined. Silicate application did not affect the accumulation of nutrients by cover crops and their release into the soil. There was no relationship between the remaining Si in the dry matter of plants and more persistent residues. The most persistent plants had higher final dry matter lignin content. Using pearl millet and pigeon peas resulted in more persistent residues in the soil. Full article

The combination of multispectral data and machine learning provides effective and flexible monitoring of the soil nutrient content, which consequently positively impacts plant productivity and food security, and ultimately promotes sustainable agricultural development overall. The aim of this study was to investigate the associations between spectral variables and soil physicochemical attributes, as well as to predict these attributes using spectral variables as inputs in machine learning models. One thousand soil samples were selected from agricultural areas 0–20 cm deep and collected from Northeast Mato Grosso do Sul state of Brazil. A total of 20 g of the dried and homogenized soil sample was added to the Petri dish to perform spectral measurements. Reflectance spectra were obtained by CROP CIRCLE ACS-470 using three spectral bands: green (532–550 nm), red (670–700 nm), and red-edge (730–760 nm). The models were developed with the aid of the Weka environment to predict the soil chemical attributes via the obtained dataset. The models tested were linear regression, random forest (RF), reptree M5P, multilayer preference neural network, and decision tree algorithms, with the correlation coefficient (r) and mean absolute error (MAE) used as accuracy parameters. According to our findings, sulfur exhibited a correlation greater than 0.6 and a reduced mean absolute error, with better performance for the M5P and RF algorithms. On the other hand, the macronutrients S, Ca, Mg, and K presented modest r values (approximately 0.3), indicating a moderate correlation with actual observations, which are not recommended for use in soil analysis. This soil analysis technique requires more refined correlation models for accurate prediction. Full article

The tomato (Solanum lycopersicum) is the second most produced vegetable globally, playing a significant role in national and international economies. This crop is highly sensitive to water deficit and thermal stress, which directly affect yield and fruit quality. Foliar application of calcium carbonate (CaCO₃) may be a possible strategy to minimize the effects of these abiotic stresses. This research aimed to determine: (a) the effects of different water replacement levels (WRLs) and photoprotector strategies (Ps) applied to the canopy on production and harvest quality of tomato fruit, (b) thermal responses—Crop Water Stress Index (CWSI) and soil temperature and (c) crop water productivity (WP_c). The research was conducted at the University of São Paulo (USP/ESALQ), Piracicaba, State of São Paulo, Brazil. The experimental design adopted was randomized blocks, with four blocks and nine treatments, totaling 36 plots. The treatments were arranged in a 3 × 3 factorial scheme, with three WRLs (70, 100 and 130% of the required irrigation depth) and three photoprotector strategies (without photoprotector, with photoprotector and with photoprotector + adjuvant). Biometric and thermal responses, productivity, harvest quality and WP_c were determined. The highest plant height and stalk diameter values were found in the treatment with photoprotector and adjuvant, with an average of 0.98 m and 0.0130 m, respectively. For the variables soil temperature, CWSI and tomato productivity, no significant differences were observed. The general average productivity obtained was 77.9 Mg ha⁻¹. The highest WP_c values were found in the WRL 70 treatments, with an average of 23.6 kg m⁻³. No significant differences were observed for pulp firmness. The highest average value of soluble solids was observed in the treatments with photoprotector (4.8 °Brix) and the highest average value of titratable acidity was observed in the WRL 130 treatments (0.36%). Therefore, deficit irrigation resulted in water savings without compromising tomato productivity and the application of photoprotector and adjuvant increased tomato quality. Full article

Magnaporthe oryzae, the source of the rice blast, is a serious threat to the world’s rice supply, particularly in areas like Tamil Nadu, India. In this study, weather-based models were developed based on count time series and machine learning techniques like INGARCHX, Artificial Neural Networks (ANNs), and Support Vector Regression (SVR), to forecast the incidence of rice blast disease. Between 2015 and 2023, information on rice blast occurrence was gathered weekly from three locations (Thanjavur, Tirunelveli, and Coimbatore), together with relevant meteorological data like temperature, humidity, rainfall, sunshine, evaporation, and sun radiation. The associations between the occurrence of rice blast and environmental factors were investigated using stepwise regression analysis, descriptive statistics, and correlation. Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) were used to assess the model’s prediction ability. The best prediction accuracy was given by the ANN, which outperformed SVR and INGARCHX in every location, according to the results. The complicated and non-linear relationships between meteorological variables and disease incidence were well-represented by the ANN model. The Diebold–Mariano test further demonstrated that ANNs are more predictive than other models. This work shows how machine learning algorithms can improve the prediction of rice blast, offering vital information for early disease management. The application of these models can help farmers make timely decisions to minimize crop losses. The findings suggest that machine learning models offer promising potential for accurate disease forecasting and improved rice management. Full article

In addition to being an important instrument in the search for increasingly greater productivity, agricultural production with adequate use of irrigation systems significantly minimizes the impact on water resources. To meet high productivity and yield, as well as industrial quality, a series of studies on sugarcane cultivation are necessary. Despite being able to adapt to drought, sugarcane is still a crop highly dependent on irrigation to guarantee the best quality standards. Our study aimed to analyze the agronomic performance and technological attributes of two sugarcane cultivars, evaluating the vegetative and productive pattern, as well as the industrial quality of the cultivars RB92579 and SP80–1816, which were cultivated under split-irrigation management in the Sugarcane Research Unit of IF Goiano—Campus Ceres, located in the state of Goiás in the Central-West region of Brazil. A self-propelled sprinkler irrigation system (IrrigaBrasil) was used, duly equipped with Twin 120 Komet sprinklers (Fremon, USA). The cultivars were propagated vegetatively and planted in 0.25 m deep furrows with 1.5 m between rows. The experiment was conducted in a completely randomized design (CRD), with a bifactorial split-plot scheme (5 × 2), with four replications, where the experimental plots were subjected to one of the following five split-irrigation management systems: 00 mm + 00 mm; 20 mm + 40 mm; 30 mm + 30 mm; 40 mm + 20 mm; or 60 mm + 00 mm. At 60 and 150 days after planting (DAP), the following respective irrigation management systems were applied: 00 mm + 00 mm and 20 mm + 40 mm. Biometric and technological attributes, such as plant height (PH) and stem diameter (SD), were evaluated in this case at 30-day intervals, starting at 180 DAP and ending at 420 DAP. Measurements of soluble solids content (°Brix), apparent sucrose content (POL), fiber content (Fiber), juice purity (PZA), broth POL (BP), reducing sugars (RS), and total recoverable sugars (TRS) were made by sampling stems at harvest at 420 DAP. RB92579 showed total recoverable sugar contents 11.89% and 8.86% higher than those recorded for SP80–1816 under split-irrigation with 40 mm + 20 mm and 60 mm + 00 mm, respectively. Shoot productivity of RB92579 reached 187.15 t ha⁻¹ under split-irrigation with 60 mm + 00 mm, which was 42.16% higher than the shoot productivity observed for SP80–1816. Both cultivars showed higher qualitative and quantitative indices in treatments that applied higher volumes of water in the initial phase of the culture, coinciding with the dry season. Sugarcane cultivar RB92579 showed a better adaptation to the prevailing conditions in the study than the SP80–1816 cultivar. Full article

Carbon dioxide flux emissions (CFE) from agricultural areas exhibit spatial and temporal variability, and the best time of collar fixation to the soil prior to the collection of CO₂ flux, or even its existence as a factor, is unclear. The objective of this study was to evaluate the effect of the fixation time of collars that support the soil-gas flux chamber based on the influence of CFE on different pasture management practices: control (traditional pasture management practice) (CON), chisel (CHI), fertilized (FER), burned (BUR), integrated crop-livestock (iCL), and plowing and harrowing (PH). A field study was conducted on the clayey soil of Udults. The evaluations were performed monthly by fixing the PVC collars 30 d and 30 min prior to each CFE measurement. Although a linear trend in CFE was observed within each pasture management practice between the two collar-fixation times, collar fixation performed 30 min prior led to an overestimation of CFE by approximately 32.7% compared with 30 d of collar fixation. Thus, CFE were higher (p ≤ 0.10) in the MC, when compared to the FC, when the CON, BUR, and iCL managements were evaluated. Overall, fixing the collar 30 d prior to field data collection can improve the quality of the data, making the results more representative of actual field conditions. Full article

Citrus yield estimation using deep learning and unmanned aerial vehicles (UAVs) is an effective method that can potentially achieve high accuracy and labor savings. However, many citrus varieties with different fruit shapes and colors require varietal-specific fruit detection models, making it challenging to acquire a substantial number of images for each variety. Understanding the performance of models on constrained or biased image datasets is crucial for determining methods for improving model performance. In this study, we evaluated the accuracy of the You Only Look Once (YOLO) v8m, YOLOv9c, and YOLOv5mu models using constrained or biased image datasets to obtain fundamental knowledge for estimating the yield from UAV images of yellow maturing citrus (Citrus junos) trees. Our results demonstrate that the YOLOv5mu model performed better than the others based on the constrained 25-image datasets, achieving a higher average precision at an intersection over union of 0.50 (AP@50) (85.1%) than the YOLOv8m (80.3%) and YOLOv9c (81.6%) models in the training dataset. On the other hand, it was revealed that the performance improvement due to data augmentation was high for the YOLOv8m and YOLOv9c models. Moreover, the impact of the bias in the training dataset, such as the light condition and the coloring of the fruit, on the performance of the fruit detection model is demonstrated. These findings provide critical insights for selecting models based on the quantity and quality of the image data collected under actual field conditions. Full article

A protocol for detecting the potential occurrence of spontaneous combustion (SC) in stored cottonseeds and peanuts using a micro-incubator is described. The protocol indicates how to quantify CO₂ production rates and final CO₂ levels in wet versus dry cottonseed and peanut samples, which can provide crucial data for the early detection of SC risk in storage facilities. The experimental design utilizes a micro-incubator to simulate conditions found in large bulk crop storage. Parameters monitored include CO₂ concentration, temperature, and relative humidity. The protocol includes preparation methods, experimental procedures for both control (dry) and wet seed tests, and test termination criteria that allow for safe experimentation of likely pathogenic fungi. The protocol has three replicates for wet and dry conditions. The protocol is intended to facilitate future experimental studies and ultimately contribute to the development of a consistently reliable early warning fire detection system for SC in cottonseed and peanut warehouse facilities. A consistently reliable fire detection system would address a critical need in the cotton and peanut industry for improved fire risk management and insurability of storage facilities. Full article

Soil loss compromises ecosystem services essential for sustainable development, necessitating effective strategies to identify priority areas for conservation practices aimed at reducing soil erosion. Current methods often rely on literature-based classification, which can be subjective. This study explores the use of artificial intelligence techniques to enhance the objectivity and efficiency of qualitative classifications for soil erosion risk. Accordingly, the aims were to apply Machine Learning methods, specifically cluster analysis, to categorize soil erosion risk in the Peixe Angical Basin, in addition to using a discriminant analysis to propose a discriminant classifier vectors for current and future predictions of soil loss risks. Our database consisted of pixel-based data on the R, K, LS, and C factors. These input data were linked to soil losses (output data), which had been classified based on findings from studies conducted in a different basin. Following this, machine learning techniques were applied to analyze the data. The cluster analysis identified seven distinct erosion risk groups: slight, slight to moderate, moderate, moderate to severe, severe, very severe, and extremely severe. Additionally, discriminant analysis facilitated the development of seven predictive models for current and future soil erosion risk, streamlining the need of new soil erosion modeling and enhancing decision-making processes. We anticipate that this methodology can be applied to other basins, providing a more robust framework for assessing soil erosion risk without relying on arbitrary qualitative classification. Full article

Various cultivars of citrus fruits have unique constructions, such as thick outer skin. These constructions generate gas diffusion resistance between the atmosphere and the fruit, which can limit the gas exchange of O₂ and CO₂.This has not been sufficiently investigated. This study on seven cultivars of citrus fruit firstly aimed to investigate gas diffusion resistance utilizing the ethane efflux method; secondly, this study aimed to investigate the internal gas concentration of O₂ and CO₂. As a result, a cultivar of citrus fruit with slimmer outer skin thickness had lower resistance. For the internal gas, a high CO₂ concentration in comparison with the atmosphere was observed even in the fruits with the minimum resistance, and no considerable difference was observed among all cultivars, regardless of the gas diffusion resistance value. However, when the fruits were stored at 25 °C for 2 weeks, CO₂ gas concentration tended to increase and O₂ gas concentration tended to decrease, with an increase in the resistance value. Therefore, when the respiration of citrus fruits is activated at ambient temperature, the self-control system of internal gas concentration can be driven to suppress the respiration which was induced by gas diffusion resistance generated from their construction. Full article

In this study, the agricultural work stress induced by the noise and vibration of some agricultural machinery was analyzed through electroencephalogram (EEG) measurements. The values of spectral edge frequency (SEF) 95%, relative gamma power (RGP), and EEG-based working index (EWI), utilized as stress indicators, were derived by analyzing the EEG data collected. The EEG analysis revealed that agricultural work stress manifested when participants engaged in agricultural tasks following a period of rest. Additionally, the right prefrontal cortex was identified where the values of SEF95% and RGP increased concurrently with the rise in noise (61.42–88.39 dBA) and vibration (0.332–1.598 m/s²). This study’s results are expected to be utilized as foundational data to determine the agricultural work stress felt by farmers during work through EEG analysis in response to changes in noise and vibration. Full article

Tomato fungal diseases can cause significant economic losses to farmers. Advanced disease detection methods based on symptom recognition in images face challenges when identifying fungal diseases in tomatoes, especially with limited training images. This study utilized novel techniques designed for limited data scenarios, such as one-shot and few-shot learning, to identify three tomato fungal diseases, i.e., Alternaria solani, Alternaria alternata, and Botrytis cinerea. Automated feature extraction was performed using the ResNet-12 deep model, and a cosine similarity approach was employed during shot learning. The accuracy of diagnosing the three diseases and healthy leaves using the 4-way 1-shot learning method was 91.64, 92.37, 92.93, and 100%. For the 4-way 3-shot learning method, the accuracy improved to 92.75, 95.07, 96.63, and 100%, respectively. These results demonstrate that the proposed method effectively reduces the dependence on experts labeling images, working well with small datasets and enhancing plant disease identification. Full article

Mastitis is a disease that is considered an obstacle in dairy farming. Some methods of diagnosing mastitis have been used effectively over the years, but with an associated relative cost that reduces the producer’s profit. In this context, this sector needs tools that offer an early, safe, and non-invasive diagnosis and that direct the producer to apply resources to confirm the clinical picture, minimizing the cost of monitoring the herd. The objective of this study was to develop a predictive methodology based on sequential knowledge transfer for the automatic detection of bovine subclinical mastitis using computer vision. The image bank used in this research consisted of 165 images, each with a resolution of 360 × 360 pixels, sourced from a database of 55 animals diagnosed with subclinical mastitis, all of which were not exhibiting clinical symptoms at the time of imaging. The images utilized in the sequential learning transfer were those of MammoTherm, which is used for the detection of breast cancer in women. The optimized model demonstrated the most optimal network performance, achieving 92.1% accuracy, in comparison to the model with manual search (86.1%). The proposed predictive methodologies, based on knowledge transfer, were effective in accurately classifying the images. This significantly enhanced the automatic detection of both healthy animals and those diagnosed with subclinical mastitis using thermal images of the udders of dairy cows. Full article

In Japan, the aging and decreasing number of agricultural workers is a significant problem. For wine grape harvesting, especially for large farming areas, there is physical strain to farmers. In order to solve this problem, this study focuses on developing an automated harvesting robot for wine grapes. The harvesting robot needs high dust, water, and mud resistance because grapevines are grown in hard conditions. Therefore, a three-axis linear robot was developed using a rack and pinion mechanism in this study, which can be used in outdoor conditions with low cost. Three brushless DC motors were utilized to drive the three-axis linear robot. The motors were controlled using a control area network (CAN) bus to simplify the hardware system. The accuracy of the robot positioning was evaluated at the automated harvesting condition. The experiment results show that the accuracy is approximately 5 mm, 9 mm, and 9 mm in the x-axis (horizontal), y-axis (vertical), and z-axis (depth), respectively. In order to improve the accuracy, we constructed an error model of the robot and conducted a calibration of the robot. The accuracy was improved to around 2 mm of all three axes after calibration. The experimental results show that the accuracy of the robot is high enough for automated harvesting of the wine grapes. Full article

Aiming to address the problems of poor separation of peanuts and soil and severe damage of pods during peanut harvesting in saline soil, a peanut digging and harvesting machine was designed using extrusion shaking vibration and roller extrusion. Theoretical calculations determined the structural parameters of critical components. The law of motion of the seedling soil assemblage at the stage of separation and transportation was derived by analyzing the kinematic properties. The soil extrusion vibration crushing dispersion and sieving process was analyzed, and the factors affecting soil crushing and separation were determined by establishing the extrusion collision model. One-way and orthogonal tests used soil content, breakage, and loss rates as test indicators. The orthogonal test showed that the working parameters were as follows: working speed was 0.889 m/s, the inclination angle was 21.5°, the working line speed of the sieve surface was 2.00 m/s and the roller gap of the roller squeezing device was 37 mm, the peanut harvesting rate of soil content was 1.36%, the breakage rate was 0.78%, and the loss rate was 1.15%. The paper references developing a peanut harvester for clay-heavy soil with soil separation performance improvement. Full article

Soil monitoring is essential for promoting sustainability in agriculture, as it helps prevent degradation and optimize the use of natural resources. The introduction of innovative technologies, such as low-cost sensors and intelligent systems, enables the acquisition of real-time data on soil health, increasing productivity and product quality while reducing waste and environmental impact. This study examines various agricultural monitoring technologies, focusing on soil moisture sensors and nutrient detection, along with examples of IoT-based systems. The main characteristics of these technologies are analyzed, providing an overview of their effectiveness and the key differences among various tools for optimizing agricultural management. The aim of the review is to support an informed choice of the most appropriate sensors and technologies, thus contributing to the promotion of sustainable agricultural practices. Full article