AgriEngineering, Volume 7, Issue 10 (October 2025) – 7 articles

The production of electricity from photovoltaics (PV) in the agricultural sector is expanding considerably, driven by ecological concerns and continuous technological development. Additionally, growing constraints on the use of arable land for PV energy production requires increased energy production per unit area of panels. Bifacial panels are one of the highest performing PV solutions currently available. The subject of this paper is the productivity modeling of mono- and bifacial PV panels. The aim is to develop a physically based model for PV productivity without the use of commercial software. For this purpose, Durisch’s model is modified and adapted for bifacial panels and the necessary empirical parameters are determined. The developed model was validated experimentally. A comparison of the performance of the front and rear side of a bifacial panel is presented. The influence of the type of reflective surface is also investigated. The productivity and efficiency of monocrystalline monofacial and bifacial panels are also compared. The experiments were carried out in real conditions typical of a temperate continental climate for the latitude of Sofia, Bulgaria under different meteorological conditions. Full article

Mechanical damage like bruises produced during postharvest handling can lower market value, affect nutritional value, and pose food safety risks. The study evaluated bruises on apples using image processing. This research focuses on using computer vision for apple fruit damage detection. The fruits were subjected to three levels of impact using three ball weights (66, 98, and 110 g) dropped from 50 cm height and stored at 22 °C. The overall impact energies generated were 0.323 J (low), 0.480 J (medium), and 0.539 J (high). The bruise area and susceptibility of the damage, surface area of the fruit, and color were measured manually (colorimeter) and by image processing. The study found that the bruise area was significantly affected by impact force, where 110 g (0.539 J) damaged apples showed a bruise area of 4.24 cm² after 21 days of storage at 22 °C. The images showed a significant change in the RGB values (Red, Green, Blue) over 21 days of storage when impacted at 0.539 J. The study showed that the greater the impact energy effect, the higher the weight loss under constant conditions of storage. After 21 days of storage, the 110 g mechanically damaged apples recorded the highest percentage of weight loss (6.362%). The study found a significant decrease in the surface area of 110 g bruised apples, with a smaller decrease in surface area for 66 g bruised fruit. The use of computer vision to detect bruise damage and other quality attributes of Granny Smith apples can be highly recommended to detect their losses. Full article

Nitrogen fertilization is decisive for maize productivity, fertilizer use efficiency, and sustainability, which calls for fast and nondestructive nutritional diagnosis. This study evaluated the classification of maize plant nutritional status from red, green, and blue (RGB) leaf images using texture attributes. A greenhouse experiment was conducted under a completely randomized factorial design with four nitrogen doses, one maize hybrid Pioneer 30F35, and four replicates, at two sampling times corresponding to distinct phenological stages, totaling thirty-two experimental units. Images were processed with the gray-level cooccurrence matrix computed at three distances 1, 3, and 5 pixels and four orientations 0°, 45°, 90°, and 135°, yielding eight texture descriptors that served as inputs to five supervised classifiers: an artificial neural network, a support vector machine, k nearest neighbors, a decision tree, and Naive Bayes. The results indicated that texture descriptors discriminated nitrogen doses with good performance and moderate computational cost, and that homogeneity, dissimilarity, and contrast were the most informative attributes. The artificial neural network showed the most stable performance at both stages, followed by the support vector machine and k nearest neighbors, whereas the decision tree and Naive Bayes were less suitable. Confusion matrices and receiver operating characteristic curves indicated greater separability for omission and excess classes, with D1 standing out, and the patterns were consistent with the chemical analysis. Future work should include field validation, multiple seasons and genotypes, integration with spectral indices and multisensor data, application of model explainability techniques, and assessment of latency and scalability in operational scenarios. Full article

Coriander is a significant crop, playing an essential role in daily life for various purposes, including flavouring curries and medicinal uses, among others. Despite its importance, coriander is still harvested manually. To address this, developed a self-propelled battery-operated coriander harvester, designed with ergonomics, environmental sustainability and affordability for small and marginal farmers in mind. The harvester is equipped with a main frame, a lead-acid battery, a BLDC motor, a reciprocating cutter bar, a PU conveyor belt, a collection bag, a handle, and transport wheels. The harvester was tested on the coriander crop, and the results were analyzed using Design Expert software to optimize various operational parameters. The harvester’s performance was evaluated at three forward speeds: 1.5 km/h, 2 km/h, and 2.5 km/h, resulting in covered areas of 0.114 ha, 0.164 ha, and 0.22 ha, with field efficiency values of 76%, 82%, and 88%, respectively. Optimal harvesting conditions were identified by design expert software at a forward speed of 1.64 km/h, with a conveyor driving pulley at level 3 (50.8 mm) and a cutting height at level 2 (75 mm). Under these conditions, the harvester achieved a harvesting efficiency of 97.24% and a cutting efficiency of 98.2%, with minimal conveying loss of 0.96%. The theoretical field capacity was 0.16 ha/h, the actual field capacity was 0.131 ha/h, and the overall field efficiency was 81.8%. Full article

Digital twins, defined as virtual counterparts of physical systems that evolve with sensor data have potential applications in controlled-environment agriculture. This study previews the integration of adaptive Microclimate Monitoring within a Unity-based digital twin of a strawberry greenhouse to support dynamic sensor selection and reallocation. Using data collected from 56 distributed temperature–relative humidity sensors, a Thompson Sampling algorithm was deployed to assign monthly importance rankings and identify season-specific subsets of sensors. To evaluate how well these subsets represented the whole sensor network, we used the Z-index, which measures distributional consistency. Across all observed months, Z-index values remained close to zero, with values of 0.037 in February, 0.012 in April, −0.002 in June, and 0.025 in October for relative humidity. These results indicate that the digital twin framework sustains the overall climate trend while reducing sensing redundancy, pointing to its potential role in future climate monitoring strategies within greenhouse systems. Full article

The efficient degradation of lignin from agricultural by-products is a critical step in the development of sustainable bioprocessing technologies for waste valorisation. Enzymatic degradation of kraft lignin performed with lignin peroxidase (LiP), manganese peroxidase (MnP), and laccase (Lac) was investigated. A response surface methodology (RSM) based on a Box–Behnken Design (BBD) was employed in order to optimise key process parameters including enzyme concentration, lignin concentration, pH, incubation temperature, and activator concentration. The surface plots were used to determine the best conditions for each enzyme in order to better degrade kraft lignin. Therefore, LiP needed a stronger acidic environment and moderate temperature, MnP needed an almost neutral pH and moderate temperature, and Lac needed a neutral pH and higher temperature. This work contributes to the development of smart agricultural waste management practices by combining enzymatic treatments with statistical modelling for process optimisation. This study provides a framework for lignin degradation that can be used as a starting point for diverse lignocellulosic by-product fragmentation, thus supporting a circular bioeconomy initiative in accordance with today’s trends. The optimised enzymatic parameters could help enhance efficiency, enable process standardisation across feedstocks, and support economically and environmentally sustainable industrial-scale lignin valorisation in integrated biorefineries. Full article

Weed detection is critical for precision agriculture, enabling targeted herbicide application to reduce costs and enhance crop health. This study utilized UAV-acquired RGB imagery from cotton fields to develop and evaluate deep learning models for weed detection. As sustainable resource management gains importance in rainfed agricultural systems, precise weed identification is essential to optimize yields and minimize herbicide use. However, distinguishing weeds from crops in complex field environments remains challenging due to their visual similarity. This research employed YOLOv7, YOLOv7-w6, and YOLOv7-x models to detect and classify weeds in cotton fields, using a dataset of 9249 images collected under real field conditions. To improve model performance, we enhanced the annotation process using LabelImg and Roboflow, ensuring accurate separation of weeds and cotton plants. Additionally, we fine-tuned key hyperparameters, including batch size, epochs, and input resolution, to optimize detection performance. YOLOv7, achieving the highest estimated accuracy at 83%, demonstrated superior weed detection sensitivity, particularly in cluttered field conditions, while YOLOv7-x with accuracy at 77% offered balanced performance across both cotton and weed classes. YOLOv7-w6 with accuracy at 63% faced difficulties in distinguishing features in shaded or cluttered soil regions. These findings highlight the potential of UAV-based deep learning approaches to support site-specific weed management in cotton fields, providing an efficient, environmentally friendly approach to weed management. Full article