AgriEngineering, Volume 7, Issue 1 (January 2025) – 21 articles

Insect pest infestations can vary due to spatial differences in microclimates and food availability within agroecosystems. Covariates can reflect these environmental conditions. This study tested whether using environmental covariates in two-phase sample optimization improved the spatial predictions for soybean insect pests. During the 2021–2022 crop season, insect pest samples were collected at 50 georeferenced points in a commercial soybean field in Brazil, alongside data on environmental covariates such as vegetation indices, soil properties, terrain topography, and distances from riparian areas. Three covariates were selected using correlation and principal component analysis (PCA). In the 2022–2023 crop season, sample designs were optimized using the iterative algorithm optimization of sample configurations using spatial simulated annealing (SPSANN) using the selected covariates, resulting in two optimized designs that were compared to a regular grid. Data from the three sampling designs comprising 50 points were evaluated using geostatistical methods, regression analysis (pest abundance), and classification (pest presence or absence) via the random forest algorithm. The data showed no spatial dependence, making using geostatistical interpolators inappropriate. However, a multi-objective optimized sampling design, tailored to refine configurations for identifying and estimating variograms and spatial trends essential for spatial interpolation, produced the most accurate predictions. Therefore, a two-phase sample optimization with prior in situ selection of environmental covariates improves pest predictions in agricultural systems, contributing to more efficient and sustainable agricultural management. Full article

(1) Background: Human–wildlife conflict can lead to adverse consequences for both parties, particularly in areas with a high concentration of wild ungulates. Ungulates cause frequent, severe plant damage by stripping the bark or browsing on the youngest plants. In the latter case, they damage vegetative sprouts and leaves, which can cause a delay in growth or the plant’s death. Tuscany is notable for its significant population of wild boar, which cause substantial damage to vineyards and cereal crops, costing farmers millions annually. In Tuscany, given the highly cultivated landscape of olive trees, damage has also been recorded in these plants. Balancing human and wildlife needs is crucial for minimizing damage and ensuring coexistence. (2) Methods: This study tested innovative electronic playback devices using long-range radio technology (LoRa) to deter wild ungulates and prevent crop damage. These devices use sounds and lights to induce wild animals to be afraid and thus run away from the cultivated plot to be protected. The experiment was conducted on a farm in Chianti, Tuscany, involving four plots of land planted with olive trees: in two test areas, four playback devices and four camera traps were installed, and in the two control areas, only camera traps were installed. Playback devices aimed to deter wild ungulates and camera traps aimed to test their effectiveness. Data from the camera traps were analyzed statistically and behaviorally. (3) Results: Playback devices significantly reduced wild animal activity in the equipped areas. Statistical analysis revealed that the use of acoustic–luminous deterrent devices (PDs) significantly reduced wildlife visits to the olive groves. (4) Conclusion: The study’s findings, supported by heatmaps and frequency analyses, provide insights into wildlife activity patterns and guide the development of targeted, effective wildlife management strategies. Full article

The conflict between environmental conservation and agricultural production highlights the need for precise land use and land cover (LULC) mapping to support agro-environmental-related policies. Satellite image time series from the Moderate Resolution Image Spectroradiometer (MODIS) sensor are essential for current LULC mapping efforts. However, most approaches focus on pixel data, and studies exploring object-based spatiotemporal heterogeneity and correlation features in its time series are limited. The objective of this study is to mix the data cube architecture (analysis-ready data—ARD) and the geo-object-oriented time series segmentation via Geographic Object-Based Image Analysis (GEOBIA) to assess its performance in identifying natural vegetation and double-cropping practices over a crop season. The study area was the state of Mato Grosso, Brazil. Results indicate that, by combining GEOBIA and time series analysis (materialized by the multiresolution segmentation algorithm to derive spatiotemporal geo-objects of the MODIS data cube), representative training data collected after a quality control process, and the Support Vector Machine to classify the ARD, the overall accuracy was 0.95 and all users’ and producers’ accuracies were higher than 0.88. By considering the heterogeneity of Mato Grosso’s landscape, the results indicate the potential of the approach to provide accurate mapping. Full article

The research investigates the advantages of real-time soil quality monitoring for various land management applications. We emphasize the crucial role of soil modeling and mapping by visualizing and understanding aridity trends across different regions. The primary objective is to develop an innovative soil monitoring system utilizing Internet of Things (IoT) technology. This system, equipped with intelligent sensors, will operate autonomously, collecting real-time data to identify key trends in soil conditions. Our system employs smart soil sensors to measure macronutrient values up to a depth of 80 cm. These sensors will transmit data wirelessly. Laboratory research involved a two-month evaluation of the system’s performance across three distinct soil types collected from diverse geographical locations. Analysis of the three soil types yielded a model accuracy estimate of 0.01. A strong positive linear correlation (0.92) between moisture and macronutrients has been observed in two out of the three soil types. The results, particularly related to soil moisture, were averaged over the testing period. While precipitation values were not directly integrated into the modeling framework, they were calculated in l/m² to ensure accurate real-time estimates. The need for such advanced monitoring systems is critical for optimizing key soil macronutrients and enabling spatiotemporal mapping. This information is essential for developing effective strategies to mitigate soil aridification and prevent desertification. Full article

Sugarcane crops have a long cycle with successive harvests before re-planting, and row gaps are one of the main problems associated with the yield. The objective of this study was to establish an alternative methodology for measuring the planting and regrowth of sugarcane rows using UAV (Unmanned Aerial Vehicle) images and to compare it with manual measurements. This study was conducted in a 1 ha experimental area under mechanized harvesting. The reference methodology consists of measuring the continuous distances without regrowth between two plants along a planting row, considering distances greater than 0.50 m as gaps and the following gaps classes: >0.5–1.0 m, >1.0–1.5 m, >1.5–2.0 m, >2.0–3.5 m, and >3.5 m. Images were collected from a UAV equipped with a 12-megapixel RGB camera. The number of regrowth gaps measured through imaging for the class of gaps with a length between 0.5 and 1.0 m was eight times higher than field measurement. In the class of gaps with a length between 1.0 and 1.5 m, the result is the opposite, as the field measurement was approximately three times higher than the UAV measurement, with a significant difference in both classes. In the other length classes analyzed, the number of gaps did not show significant differences. Our results suggest that regrowth gaps can be quickly estimated with the proposed methodology for gaps greater than 1.5 m. For gaps smaller than <1 m, the methodology using a UAV is not accurate. Full article

The management of thermal environments in animal production facilities presents significant challenges, requiring continuous adjustments to meet animals’ physiological needs. This study evaluated the effects of green roofs on the thermal environment and comfort indices in small-scale poultry house prototypes, comparing facilities with and without green roof installations. The research tested various roof types (ceramic, fiber cement, and metal) combined with emerald grass (Zoysia japonica) green roof systems. Parameters measured included air temperature, relative humidity, internal roof surface temperature, Temperature and Humidity Index (THI), Black Globe Humidity Index (BGHI), Human Comfort Index (HCI), and Thermal Radiation Load (TRL) under both open and closed conditions. Results showed that green roofs reduced indoor air temperature by up to 2.4 °C in open prototypes and 10.6 °C in closed prototypes during peak heat periods. In combinations using green roofs with fiber cement tiles, internal roof surface temperature decreased by 24.0 °C in open prototypes and 27.0 °C in closed configurations. The implementation of green roofs resulted in THI reductions of 2.3 and 8.1 units in open and closed prototypes, respectively, BGHI decreases of 2.8 and 11.3 units, and TRL reductions of 21.0 W/m² and 74.0 W/m². HCI measurements confirmed improved thermal comfort conditions with green roof installations in both settings. This study concludes that green roofs effectively enhance the thermal environment by reducing bioclimatic indices during hot periods while maintaining stable conditions during cooler weather, thereby improving overall thermal comfort in animal facilities. Full article

The use of unmanned aerial spraying systems is currently being explored and applied worldwide. The objective of this study was to characterize the droplet population generated by hydraulic nozzles and centrifugal atomization nozzles used in sprayers mounted on remotely piloted aircraft (RPA). Two spray nozzle technologies were tested using a Malvern SprayTech laser particle size meter. The hydraulic nozzle evaluated was model 11001, which generates a wide-use fan spray. The centrifugal atomization nozzle, used in RPA sprayers, was manufactured by Yuenhoang, model DC12V. The experimental design was implemented in a completely randomized scheme, containing variations in the nozzles (hydraulic nozzle and centrifugal atomization nozzle) and application rate (AR) (5, 10, and 15 L ha⁻¹ in the test with the hydraulic nozzle; and 9.2, 12.8, and 15.6 L ha⁻¹ in the test with the centrifugal nozzle), with five replicates per treatment. The hydraulic nozzle test data showed a coefficient of variation of 6.8% VMD for all treatments, with droplet sizes within the fine classification ranging from 132.8 to 163.2 µm. It is noteworthy that the average relative span (span) of the droplet population generated by the hydraulic nozzle was 1.2, i.e., 20% higher than the desired reference value of 1. This value exceeds the general average reported for the centrifugal atomization nozzle, which has a span of 1.1. The relative span of the droplet size distribution for the hydraulic nozzles is greater than that observed with the centrifugal atomization nozzles. Excluding the extreme rotational speeds of the centrifugal atomization nozzle, the percentage of droplets generated with a volume smaller than 100 µm is lower compared to those produced by the hydraulic nozzle. Full article

In the realm of hydrological engineering, integrating extensive geospatial raster data from remote sensing (Big Data) with sparse field measurements offers a promising approach to improve prediction accuracy in groundwater studies. In this study, we integrated multisource data by applying the LMC to model the spatial relationships of variables and then utilized block support regularization with collocated block cokriging (CBCK) to enhance our predictions. A critical engineering challenge addressed in this study is support homogenization, where we adjusted punctual variances to block variances and ensure consistency in spatial predictions. Our case study focused on mapping groundwater table depth to improve water management and planning in a mixed land use area in Southeast Brazil that is occupied by sugarcane crops, silviculture (Eucalyptus), regenerating fields, and natural vegetation. We utilized the 90 m resolution TanDEM-X digital surface model and STEEP (Seasonal Tropical Ecosystem Energy Partitioning) data with a 500 m resolution to support the spatial interpolation of groundwater table depth measurements collected from 56 locations during the hydrological year 2015–16. Ordinary block kriging (OBK) and CBCK methods were employed. The CBCK method provided more reliable and accurate spatial predictions of groundwater depth levels (RMSE = 0.49 m), outperforming the OBK method (RMSE = 2.89 m). An OBK-based map concentrated deeper measurements near their wells and gave shallow depths for most of the points during estimation. The CBCK-based map shows more deeper predicted points due to its relationship with the covariates. Using covariates improved the groundwater table depth mapping by detecting the interconnection of varied land uses, supporting the water management for agronomic planning connected with ecosystem sustainability. Full article

Agriculture is vital for providing food and economic benefits, but crop diseases pose significant challenges, including coffee cultivation. Traditional methods for disease identification are labor-intensive and lack real-time capabilities. This study aims to address existing methods’ limitations and provide a more efficient, reliable, and cost-effective solution for coffee leaf disease identification. It presents a novel approach to the real-time identification of coffee leaf diseases using deep learning. We implemented several transfer learning (TL) models, including ResNet101, Xception, CoffNet, and VGG16, to evaluate the feasibility and reliability of our solution. The experiment results show that the proposed models achieved high accuracy rates of 97.30%, 97.60%, 97.88%, and 99.89%, respectively. CoffNet, our proposed model, showed a notable processing speed of 125.93 frames per second (fps), making it suitable for real-time applications. Using a diverse dataset of mixed images from multiple devices, our approach reduces the workload of farmers and simplifies the disease detection process. The findings lay the groundwork for the development of practical and efficient systems that can assist coffee growers in disease management, promoting sustainable farming practices, and food security. Full article

The growing global demand for animal protein, particularly chicken meat, challenges poultry farming to adapt production systems through the adoption of digital technologies. Among the promising advances in artificial intelligence (AI), large language models (LLMs) hold potential to enhance decision-making in broiler production by supporting environmental control through the interpretation of climatic data, the generation of reports to optimize conditions, guidance on ventilation adjustments, recommendations for thermal management, assistance in air quality monitoring, and the translation of simulation results into actionable suggestions to improve bird welfare. For this purpose, the key limitations of LLMs in terms of transparency, accuracy, precision, and relevance must be effectively addressed. This study investigates the impact of retrieval-augmented generation (RAG) on improving LLM precision and relevance for environmental control in broiler production. Experiments with the OpenAI GPT-4o model and semantic similarity analysis were used to evaluate response quality with and without RAG. The results confirmed the approach’s effectiveness while identifying areas for improvement. A paired t-test revealed significantly higher similarity scores with RAG, demonstrating its impact on response quality. This study contributes to the field by advancing RAG-enhanced LLMs for environmental control, addressing market demands by demonstrating how AI improves decision-making for productivity and animal welfare, and benefits society by providing small-scale producers with cost-effective and accessible solutions for actionable insights. Full article

Aquaculture is a globally widespread practice and the world’s fastest-growing food sector and requires technological advances to both increase productivity and minimize environmental impacts. Monitoring the sector is one of the priorities of state governments, international organizations, such as the Food and Agriculture Organization of the United States (FAO), and the European Commission. Data collection in aquaculture, particularly information on the location, number, and size of production facilities, is challenging due to the time required, the extent of the area to be monitored, the frequent changes in farming infrastructures and licenses, and the lack of automated tools. Such information is usually obtained through direct communications (e.g., phone calls and e-mails) with aquaculture producers and is rarely confirmed with on-site measurements. This study describes an innovative and automated method to obtain data on the number and placement of structures for marine and freshwater finfish farming through a YOLOv4 model trained on high-resolution images. High-resolution images were extracted from Google Maps to test their use with the YOLO model for the identification and geolocation of both land (raceways used in salmonids farming) and sea-based (floating sea cages used in seabream, seabass, and meagre farming) aquaculture systems in Italy. An overall accuracy of approximately 85% of correct object recognition of the target class was achieved. Model accuracy was tested with a dataset that includes images from Tuscany (Italy), where all these farm typologies are represented. The results demonstrate that the approach proposed can identify, characterize, and geolocate sea- and land-based aquaculture structures without performing any post-processing procedure, by directly applying customized deep learning and artificial intelligence algorithms. Full article

This study assessed whether stratifying agricultural areas into macro- and micro-variability regions allows targeted sampling to better capture soil attribute variability, thus improving digital soil maps compared to regular grid sampling. Allocating more samples where soil variability is expected offers a promising alternative. We evaluated two sampling densities in two agricultural fields in Southeast Brazil: a sparse density (one sample per 2.5 hectares), typical in Precision Agriculture, and a denser grid (one sample per hectare), which usually provides reasonable mapping accuracy. For each density, we applied three designs: a regular grid and grids with 25% and 50% guided points. Apparent soil magnetic susceptibility (MSa) delimited macro-homogeneity zones, while Sentinel-2’s Enhanced Vegetation Index (EVI) identified micro-homogeneity, guiding sampling to pixels with higher Fuzzy membership. The attributes assessed included phosphorus (P), potassium (K), and clay content. Results showed that the 50% guided sample configuration improved ordinary kriging interpolation accuracy, particularly with sparse grids. In the six sparse grid scenarios, in four of them, the grid with 50% of the points in regular design and the other 50% directed by the proposed method presented better performance than the full regular grid; the higher improvement was obtained for clay content (RMSE of 54.93 g kg⁻¹ to 45.63 g kg⁻¹, a 16.93% improvement). However, prior knowledge of soil attributes and covariates is needed for this approach. We therefore recommend two-stage sampling to understand soil properties’ relationships with covariates before applying the proposed method. Full article

In many soil processes, including solute and gas dynamics, the architecture of intra-aggregate pores is a crucial component. Soil management practices and wetting-drying (W-D) cycles, the latter having a significant impact on pore aggregation, are two key factors that shape pore structure. This study examines the effects of W-D cycles on the architecture of intra-aggregate pores under three different soil management systems: no-tillage (NT), minimum tillage (MT), and conventional tillage (CT). The soil samples were subjected to 0 and 12 W-D cycles, and the resulting pore structures were scanned using X-ray micro-computed tomography, generating reconstructed 3D volumetric data. The data analyses were conducted in terms of multifractal spectra, normalized Shannon entropy, lacunarity, porosity, anisotropy, connectivity, and tortuosity. The multifractal parameters of capacity, correlation, and information dimensions showed mean values of approximately 2.77, 2.75, and 2.75 when considering the different management practices and W-D cycles; 3D lacunarity decreased mainly for the smallest boxes between 0 and 12 W-D cycles for CT and NT, with the opposite behavior for MT. The normalized 3D Shannon entropy showed differences of less than 2% before and after the W-D cycles for MT and NT, with differences of 5% for CT. The imaged porosity showed reductions of approximately 50% after 12 W-D cycles for CT and NT. Generally, the largest pores (>0.1 mm³) contributed the most to porosity for all management practices before and after W-D cycles. Anisotropy increased by 9% and 2% for MT and CT after the cycles and decreased by 23% for NT. Pore connectivity showed a downward trend after 12 W-D cycles for CT and NT. Regarding the pore shape, the greatest contribution to porosity and number of pores was due to triaxial-shaped pores for both 0 and 12 W-D cycles for all management practices. The results demonstrate that, within the resolution limits of the microtomography analysis, pore architecture remained resilient to changes, despite some observable trends in specific parameters. Full article

Millions of tons of cherry tomatoes are produced annually, with the harvesting process being crucial. This paper presents a deep learning-based approach to distinguish the ripeness of cherry tomatoes in real time. It specifically evaluates the performance of YOLO (You Only Look Once) v5 and YOLOv8 (with a ResNet50 backbone) models. A new dataset was created by augmenting the original 300 images to 742 images using techniques such as rotation, flipping, and brightness adjustments. Experimental results show that YOLOv8 achieved a mean average precision (mAP) of 0.757, outperforming YOLOv5, which achieved an mAP of 0.701, by 5.6%. The proposed system is expected to address labor shortages caused by population decline in rural areas and enhance productivity in cherry tomato harvesting environments. Future research will focus on integrating segmentation techniques to precisely locate cherry tomatoes and develop a robotic manipulator capable of automating the harvesting process based on ripeness. This study provides a foundation for intelligent harvesting robots applicable in real-world. Full article

The evaluation of direct energy inputs and the assessment of the carbon footprint of an agricultural tractor during the execution of an agricultural operation is a complex task. Methodological approaches such as field surveys and life cycle assessments can provide unreliable and non-repeatable results. This study exploits the use of numerical simulation to assess the fuel consumption of two agricultural tractors and their CO₂ emissions during the execution of pesticide treatment and milling. The digital models of the Landini REX 4-120 GB and the Fendt 942 Vario were developed, starting from experimental data acquired during field tests in which the power required at the power take-off (PTO) by the respective operating machine was measured. Two custom working cycles, simulating the two agricultural operations, have been defined and simulated. The estimated fuel consumption was 7.8 L∙ha⁻¹ and 23.2 L∙ha⁻¹, respectively, for the Landini REX 4-120 GB during pesticide treatment and for the Fendt 942 Vario during milling. The corresponding direct energy inputs required for the two agricultural operations were equal to 300.3 MJ∙ha⁻¹ and 893.2 MJ∙ha⁻¹, respectively. The estimated carbon footprint was 26.5 kg_CO2∙ha⁻¹ and 68.4 kg_CO2∙ha⁻¹ for pesticide treatment and for milling, respectively. Moreover, considering the operational efficiency of the systems, an analysis of the available mechanical work supplied by the fuel was conducted. Full article

This study addresses the critical challenge of the limited understanding of environmental factors influencing cocoa cultivation in Colombia, a region with significant production potential but diverse agroecological conditions. The fragmented nature of the existing agricultural data and the lack of targeted research hinder efforts to optimize productivity and sustainability. To bridge this gap, this research employs a data-driven approach, using advanced machine learning techniques such as supervised, unsupervised, and ensemble models, to analyze environmental datasets and provide actionable recommendations. By integrating data from official Colombian sources, as well as the NASA POWER database, and geographical APIs, the present study proposes a methodology to systematically assess environmental conditions and classify regions for optimal cocoa cultivation. The use of an assembled model, combining clustering with targeted machine learning for each cluster, offers a more precise and scalable understanding of cocoa establishment under diverse conditions. Despite challenges such as limited dataset resolution and localized climate variability, this research provides valuable insights for a more comprehensive understanding of the environmental conditions impacting cocoa plantation establishment in a given location. The key findings reveal that temperature, humidity, and wind speed are crucial determinants of cocoa growth, with complex interactions affecting regional suitability. The results offer valuable guidance for the implementation of adaptive agricultural practices and resilience strategies, enabling sustainable cocoa production systems. By implementing better practices, countries such as Colombia can achieve higher market shares under growing global cocoa demand conditions. Full article

This study aims to evaluate the behavior of seed longevity in soybean, maize, and tomato stored under controlled conditions using Logistic and Boltzmann sigmoidal models. Additionally, it seeks to determine the performance of these models in predicting $P_{50}$, $P_{85}$, and $P_{25}$. The models were fitted to the experimental longevity data, and their performance in predicting the percentiles was evaluated. The Logistic model showed better performance in predicting $P_{50}$ (time for viability to drop to 50%), $P_{85}$ (time for viability to drop to 85%), and $P_{25}$ (time for viability to drop to 25%), estimating the parameters more frequently within the experimental range (obtained from the initial viability data). The results of this study suggest that some cultivars exhibited different patterns in deterioration rates, with some showing abrupt declines in viability, highlighting differences in the speed and nature of seed deterioration. The Logistic model proved to be superior, with an accuracy of 83% in estimating the $P_{85}$ and $P_{25}$ percentiles, while the Boltzmann model achieved an accuracy of 54%. The tomato cultivar Gaucho showed the greatest loss in germination, reaching $P_{25}$ quickly, while the soybean cultivar M 7119 IPRO and maize cultivar MAM06 maintained high germination for a longer period. These findings emphasize the importance of using viability percentiles to optimize storage practices, minimize economic losses, and prevent genetic erosion in conservation programs. Modeling seed longevity using sigmoidal models can significantly contribute to determining various viability percentiles, supporting storage practices and providing valuable insights for strategic decision-making in seed management, proving useful in both commercial and species conservation contexts. Full article

The soybean and corn strip cropping pattern is widely promoted globally, but at present, the degree of mechanization of this planting mode is insufficient, and the development of machinery is slow. In this regard, through a review of the literature and a field sowing test, we briefly describe the current situation of soybean and corn strip sowing machinery in the Yellow River basin, analyze the existing problems in mechanized planting, and give suggestions for improvement, aiming to provide a reference for the research and development of machinery. Full article

Seed analysis is a cornerstone in advancing agriculture, with vigor tests playing a critical role in evaluating the physiological quality of seeds. However, monitoring seed vigor over time poses a significant challenge for the seed industry, as traditional methods are time-consuming and heavily reliant on subjective human judgment. Concerning these limitations, optical-based techniques have emerged as promising alternatives. Among them, the biological laser speckle phenomenon, rooted in optical interferometry, has proven effective in sensitively detecting and monitoring activity levels in living tissues. Known as the biospeckle laser (BSL) technique, this approach offers reliable results in assessing seed vigor. The BSL technique stands out due to its simplicity, rapid analysis, objectivity, and potential for automation, making it a valuable tool for seed analysis. This paper explores the state-of-the-art application of the BSL technique for evaluating seed vigor, highlighting successful approaches, identifying current challenges, and outlining areas for future research. It delves into the experimental setup for seed illumination and discusses the associated image processing methods. Furthermore, the paper examines the numerical and graphical outcomes, underscoring the BSL technique’s ability to carry out seed analysis by addressing the limitations of traditional methods and enhancing efficiency in the agricultural sector. Full article

In plasticulture production systems, the conventional practice involves broadcasting pre-emergent herbicides over the entire surface of raised beds before laying plastic mulch. However, weed emergence predominantly occurs through the transplant punch-holes in the mulch, leaving most of the applied herbicide beneath the plastic, where weeds cannot grow. To address this issue, we developed and evaluated a precision spraying system designed to target herbicide application to the transplant punch-holes. A dataset of 3378 images was manually collected and annotated during a tomato experimental trial at the University of Florida. A YOLOv8x model with a p2 output layer was trained, converted to TensorRT^® to improve the inference time, and deployed on a custom-built computer. A Python-based graphical user interface (GUI) was developed to facilitate user interaction and the control of the smart sprayer system. The sprayer utilized a global shutter camera to capture real-time video input for the YOLOv8x model, which activates or disactivates a TeeJet solenoid for precise herbicide application upon detecting a punch-hole. The model demonstrated excellent performance, achieving precision, recall, mean average precision (mAP), and F1score exceeding 0.90. Field tests showed that the smart sprayer reduced herbicide use by up to 69% compared to conventional broadcast methods. The system achieved an 86% punch-hole recognition rate, with a 14% miss rate due to challenges such as plant occlusion and variable lighting conditions, indicating that the dataset needs to be improved. Despite these limitations, the smart sprayer effectively minimized off-target herbicide application without causing crop damage. This precision approach reduces chemical inputs and minimizes the potential environmental impact, representing a significant advancement in sustainable plasticulture weed management. Full article

Cannabis sativa, often called hemp, is a medicinal plant belonging to the Cannabaceae family and is widely recognized for its therapeutic applications. After the industrial supercritical CO₂ extraction method, hemp residue biomass was recovered, and a significant quantity of bioactive compounds was identified. Therefore, it is of paramount importance to study whether they can be further exploited using green techniques. In the present work, hemp leaf residues were treated using two extraction techniques: one conventional stirring extraction (STE) and one green pressurized liquid extraction (PLE). The latter technique is a promising and swift method for the efficient extraction of valuable molecules from natural sources. The two techniques were optimized through Response Surface Methodology, and the optimized parameters were the appropriate solvent, temperature, and extraction duration. The aim was to maximize the yield of bioactive compounds (polyphenols, flavonoids, and ascorbic acid) from hemp leaf residue and evaluate their antioxidant activity using the most appropriate technique. The results showed that after three 5 min PLE cycles, the recovered individual polyphenols were comparable (p > 0.05) to a 45 min STE (19.34 and 20.84 mg/g, respectively), as well as in antioxidant capacity assays and other bioactive compounds. These findings emphasize the efficacy of the rapid PLE approach as an effective extraction technique to enhance the value of hemp leaf residues while maximizing the concentration of high-added value molecules. Full article