AgriEngineering, Volume 7, Issue 3 (March 2025) – 42 articles

Hyperspectral plant phenotyping is a method that has a wide range of applications in various fields, including agriculture, forestry, food processing, medicine and plant breeding. It can be used to obtain a large amount of spectral and spatial information about an object. However, it is important to acknowledge the inherent limitations of this approach, which include the presence of noise and the redundancy of information. The present study aims to assess a novel approach to hyperspectral data preprocessing, namely Random Reflectance (RR), for the classification of plant species. This study employs machine learning (ML) algorithms, specifically Random Forest (RF) and Gradient Boosting (GB), to analyse the performance of RR in comparison to Min–Max Normalisation (MMN) and Principal Component Analysis (PCA). The testing process was conducted on data derived from the proximal hyperspectral imaging (HSI) of leaves from three different maple species, which were sampled from trees at 7–10-day intervals between 2021 and 2024. The RF algorithm demonstrated a relative increase of 8.8% in the F1-score in 2021, 9.7% in 2022, 11.3% in 2023 and 11.8% in 2024. The GB algorithm exhibited a similar trend: 6.5% in 2021, 13.2% in 2022, 16.5% in 2023 and 17.4% in 2024. It has been demonstrated that hyperspectral data preprocessing with the MMN and PCA methods does not result in enhanced accuracy when classifying species using ML algorithms. The impact of preprocessing spectral profiles using the RR method may be associated with the observation that the synthesised set of spectral profiles exhibits a stronger reflection of the general parameters of spectral reflectance compared to the set of actual profiles. Subsequent research endeavours are anticipated to elucidate a mechanistic rationale for the RR method in conjunction with the RF and GB algorithms. Furthermore, the efficacy of this method will be evaluated through its application in deep machine learning algorithms. Full article

Agriculture, an essential driver of economic expansion, is faced by the issue of sustaining an increasing global population in the context of climatic uncertainty and limited resources. As a result, “Smart Farming”, which uses cutting-edge artificial intelligence (AI) to support autonomous decision-making, has become more popular. This article explores how the Internet of Things (IoT), AI, machine learning (ML), remote sensing, and variable-rate technology (VRT) work together to transform agriculture. Using sophisticated algorithms to predict soil conditions, improving agricultural yield projections, diagnosing water stress from sensor data, and identifying plant diseases and weeds through image recognition, crop mapping, and AI-guided crop selection are some of the main applications investigated. Furthermore, the precision with which VRT applies water, pesticides, and fertilizers optimizes resource utilization, enhancing sustainability and efficiency. To effectively meet the world’s food demands, this study forecasts a sustainable agricultural future that combines AI-driven approaches with conventional methods. Full article

In spaced crop systems, understanding the interactions between different types of vegetation in the agroecosystem and solar radiation is essential for understanding surface radiation dynamics. This study aimed to both seasonally and spatially quantify and characterize the components of the solar radiation balance in the cultivation of green dwarf coconut. The experiment was conducted in Santa Izabel do Pará, Brazil, and monitored the following meteorological parameters: rainfall, incident global radiation (R_g), and net radiation (R_n). Landsat 8 satellite images were obtained between 2021 and 2023, and the estimates for global and net radiation were subsequently calculated. The resulting data were subjected to mean tests and performance index analysis. The dry season showed higher values of R_g and R_n due to reduced cloud cover. In contrast, the rainy season exhibited lower R_g and R_n totals, with reductions of 21% and 23%, respectively. In the irrigated area, a higher R_n/R_g fraction was observed compared to the non-irrigated area, with no significant differences between the row and inter-row zones. In the non-irrigated system, there were no seasonal differences, but a spatial difference between row and inter-row was noted, with the row having higher net radiation (9.95 MJ m⁻² day⁻¹) than the inter-row (8.36 MJ m⁻² day⁻¹), which could result in distinct energy balances at a micrometeorological scale. Spatially, the eastern portion of the study area showed higher global radiation totals, with the radiation balance predominantly ranging between 400 and 700 W m⁻². Based on the performance indices obtained, satellite-based estimates proved to be a viable alternative for characterizing the components of the radiation balance in the region, provided that the images have low cloud cover. Full article

Accidents and deaths at work are a persistent problem, with numbers still worrying. The agricultural and forestry sector is among the most exposed to work risks, with particular attention to noise risk from the use of agricultural machinery and operators. This study aims to analyze the exposure to noise risk during use of wheeled and tracked tractors, with or without a cab, as well as other operating machines. The analysis takes into account the parameters Lpeak (peak sound pressure values), LAeq.T (time-weighted equivalent noise exposure levels) and LAS (maximum and minimum values weighted according to the Slow time constant) in order to assess the noise impact and define strategies for improving the safety and health of workers. This study demonstrates that in multiple cases, the regulatory thresholds for the examined variables are exceeded, regardless of the presence of a cabin. Specifically, Lpeak values approach 140 dB, dangerous to human health, while LAeq.T levels are close to or, in some instances, exceed 87 dB. It is also verified that agricultural and forestry operators who mainly use crawler tractors have greater and constant exposure to noise compared to those who use tractors with a cabin. Full article

The poultry industry faces significant challenges in efficiently monitoring large populations, especially under resource constraints and limited connectivity. This paper introduces the Automated Counting and Monitoring System for Poultry Tracking (ACMSPT), an innovative solution that integrates edge computing, Artificial Intelligence (AI), and the Internet of Things (IoT). The study begins by collecting a custom dataset of 1300 high-resolution images from real broiler farm environments, encompassing diverse lighting conditions, occlusions, and growth stages. Each image was manually annotated and used to train the YOLOv10 object detection model with carefully selected hyperparameters. The trained model was then deployed on an Orange Pi 5B single-board computer equipped with a Neural Processing Unit (NPU), enabling on-site inference and real-time poultry tracking. System performance was evaluated in both small- and commercial-scale sheds, achieving a precision of 93.1% and recall of 93.0%, with an average inference time under 200 milliseconds. The results demonstrate that ACMSPT can autonomously detect anomalies in poultry movement, facilitating timely interventions while reducing manual labor. Moreover, its cost-effective, low-connectivity design supports broader adoption in remote or resource-limited environments. Future work will focus on improving adaptability to extreme conditions and extending this approach to other livestock management contexts. Full article

The increasing atmospheric CO₂ concentration due to anthropogenic activities has led to the development of low-cost, portable, and user-friendly sensing technologies. Non-Dispersive Infrared (NDIR) sensors offer reliable CO₂ detection with high sensitivity, which makes them ideal for citizen scientists. In this context, we designed two low-cost CO₂ monitoring systems: an automatic opening chamber with a lid and a portable device using NDIR sensors. These monitoring systems were calibrated (R² = 0.99) with known CO₂ concentrations. Besides its reliability and accuracy, the Automated CO₂ Monitoring System costs approximately USD 220.77 and portable CO₂ device costs USD 151.43, which makes them suitable for citizen scientists. Due to CO₂ gas monitoring system’s simplicity, structure, and operation, non-expert users can use and actively participate in environmental monitoring data collection. This promotes public engagement in climate and air quality monitoring and enables citizen scientists to have reliable data for CO₂ monitoring and environmental awareness. Full article

The powdered products industry demands certain parameters for the transport of these products, such as flowability. This has a direct impact on actions within the industry and in machinery development. For Coffea canephora, this information is absent in the relevant literature. Thus, the present study aimed to analyze alterations in the flow properties of Coffea canephora due to the degree of roasting, particle size, and storage temperature. Two degrees of roasting were used: medium light (ML) and moderately dark (MD). Later, the coffee was divided into four particle size categories: whole roasted coffee and coffee ground to fine, medium, and coarse sizes. These lots were kept at 10 °C and 30 °C and the flowability parameters were studied throughout the storage period (0, 30, 60, 120, and 180 days). The angle of internal friction presented higher values for higher degrees of roasting and lower values for larger particle sizes. The MD and fine coffee samples presented higher values for the wall friction angle. Steel provided the lowest values for the wall friction angle. Unground roasted coffee was classified as free-flowing, whilst coffee with a coarse or fine particle size was classified as having an easy flow and a cohesive flow, respectively. According to the K coefficient, coffee roasted to MD required storage containers that were more robust, such as having thicker silo walls or being constructed of a material with a higher resistance, to prevent the storage container from collapsing during transport. Full article

Surface runoff poses a significant threat to crop production and the environment. However, most studies on soil properties have not quantified soil nutrient loss as a consequence of soil erosion. This study measures the magnitude of nutrient loss through the development of a novel electrochemical sensor designed for direct and selective detection of nitrates and phosphates in soil runoff. The sensor fabrication process utilizes molecularly imprinted polymer techniques which involve the electrodeposition of polypyrrole with the analyte onto a carbon electrode. Cyclic voltammetry (CV) analysis was performed to evaluate the sensor performance in quantifying nitrates and phosphates across three distinct sets of soil samples collected for analysis. The sensor response was linear to the nitrate concentration in the range of 0.01 M to 100 μM (R² = 0.9906). The phosphate MIP sensor also displayed a linear response for concentrations ranging from 10 µM to 200 µM (R² = 0.9901). The sensor exhibited high sensitivity towards nitrates and phosphates and effectively detected nutrient levels in the soil solution with a detection limit of 25 μM and 53 μM, respectively. The sensor was then evaluated for degradation and repeatability, which produced a relative standard deviation of 13.5% and 8.2% for nitrate and phosphate, respectively. Further, the loss of nutrients in different soil types indicated the need for soil characterization before the application of fertilizer to reduce the nutrient loss in the event of surface runoff. Full article

Smart greenhouses offer crucial solutions for reducing our atmospheric impact and resource waste. However, two fundamental challenges persist in their implementation, massive energy consumption and a high level of human intervention, particularly for sensor battery replacement or recharging. Unfortunately, sensors are indispensable in greenhouses and agriculture, such as for monitoring environmental parameters for air quality assessment. Therefore, while sensors cannot be eliminated, it is essential to optimize their energy consumption. This work introduces an energy-efficient monitoring system for smart greenhouses, aiming to reduce the energy consumption of individual sensors and enhance system sustainability. This study focuses on optimizing the sampling intervals of commonly monitored environmental parameters to minimize sensor energy usage while maintaining data acquisition accuracy adequate for the intended purpose. Additionally, to further reduce battery energy draw, an energy harvesting system using solar panels was implemented. In conclusion, adopting an optimal sampling strategy for each parameter significantly reduces energy consumption compared to fixed, inefficient sampling intervals commonly used in commercial weather stations. Furthermore, by employing an energy harvesting system for each sensor, leveraging the light emitted by greenhouse lamps and external sources ensures the autonomy of sensors within the greenhouse, thereby minimizing the need for human intervention for battery replacement and recharging. Full article

Typically, developing new digital agriculture technologies requires substantial on-site resources and data. However, the crop’s growth cycle provides only limited time windows for experiments and equipment validation. This study presents a photorealistic digital twin of a commercial-scale strawberry farm, coupled with a simulated ground vehicle, to address these constraints by generating high-fidelity synthetic RGB and LiDAR data. These data enable the rapid development and evaluation of a deep learning-based machine vision pipeline for fruit detection and sizing without continuously relying on real-field access. Traditional simulators often lack visual realism, leading many studies to mix real images or adopt domain adaptation methods to address the reality gap. In contrast, this work relies solely on photorealistic simulation outputs for training, eliminating the need for real images or specialized adaptation approaches. After training exclusively on images captured in the virtual environment, the model was tested on a commercial-scale strawberry farm using a physical ground vehicle. Two separate trials with field images resulted in F1-scores of 0.92 and 0.81 for detection and a sizing error of 1.4 mm (R² = 0.92) when comparing image-derived diameters against caliper measurements. These findings indicate that a digital twin-driven sim2real transfer can offer substantial time and cost savings by refining crucial tasks such as stereo sensor calibration and machine learning model development before extensive real-field deployments. In addition, the study examined geometric accuracy and visual fidelity through systematic comparisons of LiDAR and RGB sensor outputs from the virtual and real farms. Results demonstrated close alignment in both topography and textural details, validating the digital twin’s ability to replicate intricate field characteristics, including raised bed geometry and strawberry plant distribution. The techniques developed and validated in this strawberry project have broad applicability across agricultural commodities, particularly for fruit and vegetable production systems. This study demonstrates that integrating digital twins with simulation tools can significantly reduce the need for resource-intensive field data collection while accelerating the development and refinement of agricultural robotics algorithms and hardware. Full article

Ready-to-drink herbal teas are increasingly popular due to their pleasant aroma and taste, with plants cultivated organically showing improved quality properties. Vis/NIR absorbance and multivariate analysis were used for classifying infused herbal teas cultivated under organic systems, in addition to testing various spectral pretreatments to assess the identification accuracy improvement. A total of 150 herbal tea infusions (boldo, carqueja, chamomile, fennel, and lemon grass) were evaluated, and six spectral pretreatments (centering, standard normal variation, object-wise standardization, first derivative, second derivative, and detrending) were applied to the spectra. Principal component analysis (PCA) and the partial least squares discriminant analysis (PLS-DA) were used to distinguish the infused herbal teas. Clustering patterns were affected by the pretreatments, and the PCA was capable of separating the infused herbal teas. The PLS-DA was efficient in identifying the infusions, reaching kappa values from 0.97 to 1.00 with optimal latent variable numbers from two to five. Detrending and object-wise standardization pretreatments led to better results and required fewer latent variables. The proposed methodology presents the potential to be used in a fast, safe, environmentally friendly (without chemical reagents), and nondestructive way, appearing as essential for meeting the technological development of the agrifood industry. Full article

Citriculture has worldwide importance, and monitoring the nutritional status of plants through leaf analysis is essential. Recently, proximal sensing has supported this process, although there is a lack of studies conducted specifically for citrus. The objective of this study was to evaluate the application of portable X-ray fluorescence spectrometry (pXRF) combined with machine learning algorithms to predict the nutrient content (B, Ca, Cu, Fe, K, Mg, Mn, P, S, and Zn) of citrus leaves, using inductively coupled plasma optical emission spectrometry (ICP-OES) results as a reference. Additionally, the study aimed to differentiate 15 citrus scion/rootstock combinations via pXRF results and investigate the effect of the sample condition (fresh or dried leaves) on the accuracy of pXRF predictions. The samples were analyzed with pXRF both fresh and after drying and grinding. Subsequently, the samples underwent acid digestion and analysis via ICP-OES. Predictions using dried leaves yielded better results (R² from 0.71 to 0.96) than those using fresh leaves (R² from 0.35 to 0.87) for all analyzed elements. Predictions of scion/rootstock combinations were also more accurate with dry leaves (Overall accuracy = 0.64, kappa index = 0.62). The pXRF accurately predicted nutrient contents in citrus leaves and differentiated leaves from 15 scion/rootstock combinations. This can significantly reduce costs and time in the nutritional assessment of citrus crops. Full article

This review aims to study the applications of sensors for monitoring and controlling the physicochemical parameters of water in aquaculture systems such as Biofloc Technology (BFT), Recirculating Aquaculture Systems (RASs), and aquaponic systems using IoT technology, as well as identify potential knowledge gaps. A bibliometric analysis and systematic review were conducted using the Scopus database between 2020 and 2024. A total of 217 articles were reviewed and analyzed. Our findings indicated a significant increase (74.79%) in research between 2020 and 2024. pH was the most studied physicochemical parameter in aquaculture, analyzed in 98.2% of cases (sensors: SEN0169, HI-98107, pH-4502C, Grove-pH), followed by temperature (92.9%, sensor DS18B20) and dissolved oxygen (62.5%, sensors: SEN0237, MAX30102, OxyGuard DO model 420, ZTWL-SZO2-485, Lutron DO-5509). Overall, water monitoring through the implementation of IoT sensors improved growth rates, reduced culture mortality rates, and enabled the rapid prediction and detection of atypical Total Ammonia Nitrogen (TAN) levels. IoT sensors for water quality monitoring in aquaponics also facilitate the evaluation and prediction of seed and vegetable growth and germination. In conclusion, despite recent advancements, challenges remain in automating parameter control, ensuring effective sensor maintenance, and improving operability in rural areas, which need to be addressed. Full article

The poultry industry plays a pivotal role in global agriculture, with poultry serving as a major source of protein and contributing significantly to economic growth. However, the sector faces challenges associated with labor-intensive tasks that are repetitive and physically demanding. Automation has emerged as a critical solution to enhance operational efficiency and improve working conditions. Specifically, robotic manipulation and handling of objects is becoming ubiquitous in factories. However, challenges exist to precisely identify and guide a robot to handle a pile of objects with similar textures and colors. This paper focuses on the development of a vision system for a robotic solution aimed at automating the chicken rehanging process, a fundamental yet physically strenuous activity in poultry processing. To address the limitation of the generic instance segmentation model in identifying overlapped objects, a cost-effective, dual-active laser scanning system was developed to generate precise depth data on objects. The well-registered depth data generated were integrated with the RGB images and sent to the instance segmentation model for individual chicken detection and identification. This enhanced approach significantly improved the model’s performance in handling complex scenarios involving overlapping chickens. Specifically, the integration of RGB-D data increased the model’s mean average precision (mAP) detection accuracy by 4.9% and significantly improved the center offset—a customized metric introduced in this study to quantify the distance between the ground truth mask center and the predicted mask center. Precise center detection is crucial for the development of future robotic control solutions, as it ensures accurate grasping during the chicken rehanging process. The center offset was reduced from 22.09 pixels (7.30 mm) to 8.09 pixels (2.65 mm), demonstrating the approach’s effectiveness in mitigating occlusion challenges and enhancing the reliability of the vision system. Full article

Achieving global sustainable agriculture requires farmers worldwide to adopt smart agricultural technologies, such as autonomous ground robots. However, most ground robots are either task- or crop-specific and expensive for small-scale farmers and smallholders. Therefore, there is a need for cost-effective robotic platforms that are modular by design and can be easily adapted to varying tasks and crops. This paper describes the hardware design of a unique, low-cost multiaxial modular agricultural robot (ModagRobot), and its field evaluation for soybean phenotyping. The ModagRobot’s chassis was designed without any welded components, making it easy to adjust trackwidth, height, ground clearance, and length. For this experiment, the ModagRobot was equipped with an RGB-Depth (RGB-D) sensor and adapted to safely navigate over soybean rows to collect RGB-D images for estimating soybean phenotypic traits. RGB images were processed using the Excess Green Index to estimate the percent canopy ground coverage area. 3D point clouds generated from RGB-D images were used to estimate canopy height (CH) and the 3D Profile Index of sample plots using linear regression. Aboveground biomass (AGB) was estimated using extracted phenotypic traits. Results showed an R², RMSE, and RRMSE of 0.786, 0.0181 m, and 2.47%, respectively, between estimated CH and measured CH. AGB estimated using all extracted traits showed an R², RMSE, and RRMSE of 0.59, 0.0742 kg/m², and 8.05%, respectively, compared to the measured AGB. The results demonstrate the effectiveness of the ModagRobot for in-row crop phenotyping. Full article

Enhancing agricultural machinery field efficiency offers substantial benefits for farm management by optimizing the available resources, thereby reducing cost, maximizing productivity, and supporting sustainability. Field efficiency is influenced by several unpredictable and stochastic factors that are difficult to determine due to the inherent variability in field configurations and operational conditions. This study aimed to simplify field efficiency estimation by training machine learning regression algorithms on data generated from a farm management information system covering a combination of different field areas and shapes, working patterns, and machine-related parameters. The gradient-boosting regression-based model was the most effective, achieving a high mean $R^2$ value of 0.931 in predicting field efficiency, by taking into account only basic geometric field indices. The developed model showed also strong predictive performance for indicative agricultural fields located in Europe and North America, reducing considerably the computational time by an average of 73.4% compared to the corresponding analytical approach. Overall, the results of this study highlight the potential of machine learning for simplifying field efficiency prediction without requiring detailed knowledge of a plethora of variables associated with agricultural operations. This can be particularly valuable for farmers who need to make informed decisions about resource allocation and operational planning. Full article

The use of non-invasive methods can contribute to the development of predictive models for measuring carcass yield (CY) and hot carcass weight (HCW) in domestic ruminants. In this study, in vivo measurements of subcutaneous fat thickness (SFT) and ribeye area (REA) were performed on 111 Nellore heifers using ultrasound imaging. The animals were managed in crop–livestock integrated systems with different supplementation levels (SL). Four multiple regression equations were developed to estimate CY and HCW, using five predictor variables: SFT, REA, REA per 100 kg of body weight (REA100), live weight (LW), and SL. For the CY prediction models, when ultrasound measurements (SFT, REA, and REA100) were considered, the generated equations showed low R² and concordance correlation coefficient (CCC) values, indicating low predictive capacity for this trait. For HCW, the predictor variables stood out due to their high R² values. Additionally, the equation based solely on ultrasound measurements achieved a CCC greater than 0.800, demonstrating high predictive capacity. Based on these results, it can be concluded that ultrasound-derived measurements are effective for generating useful models to predict HCW. Thus, it will be possible to estimate the amount of carcass that will be produced even before the animals are sent to slaughterhouses. Full article

This study evaluated housing designs and bedding systems to improve air quality in swine facilities, focusing on odor and particulate matter (PM) reduction. Three experimental animal house designs (M1, M2, M3) were tested: M1 used circulating airflow with negative pressure, M2 featured a plug flow air pattern with a perforated plastic bed, and M3 employed a sawdust bedding system with recirculating ventilation. Nine fattening swine were housed in each 12 m² house over 110 days (6 May to 26 August 2018). Appropriate air samples were collected, and odorous compounds, volatile organic acids (VOA), PM, and bacterial concentrations measured. Results showed that M3 had the lowest ammonia (NH₃) levels (5.9 ± 1.5 ppm) and undetectable hydrogen sulfide (H₂S), while M1 recorded the highest NH₃ (9.1 ± 2.2 ppm). VOA concentrations were significantly lower in M3 (75 ± 1.3 ppbv) compared to M1 (884 ± 15 ppbv) and M2 (605 ± 10.3 ppbv). PM10 levels were highest in M3 (312 ± 11 μg/m³) and lowest in M1 (115 ± 3 μg/m³), and thus bacterial counts were elevated in M3 (2117 ± 411 cfu/min), whereas M1 showed the lowest bacterial count of 1029 ± 297 cfu/min. The sawdust bedding system effectively reduced odorous compounds, highlighting its potential for odor control. However, higher PM levels in M3 emphasize the need to balance environmental management with animal welfare. These findings suggest that optimizing housing designs and bedding systems can enhance air quality in swine facilities while addressing sustainability and welfare concerns. Full article

This paper presents whole-body vibration prediction in an agricultural tractor based on selected operational parameters using machine learning. Experiments were performed using a Landini Powerfarm 100 model tractor on farmlands and service roads located at the Osijek School of Agriculture and Veterinary Medicine. The methodology adhered to the HRN ISO 5008 protocols for establishing test surfaces, including a smooth 100 m track and a rugged 35 m track. Whole-body vibrational exposure assessments were carried out in alignment with the HRN ISO 2631-1 and HRN ISO 2631-4 guidelines, which outline procedures for evaluating mechanical oscillations in occupational settings. The obtained whole-body vibration data were divided into three datasets (one for each axis) and processed using linear regression as a baseline and compared against three machine learning models (gradient boosting regressor; support vector machine regressor; multi-layer perception). The most accurate machine learning model according to the R² metric was the gradient boosting regressor for the x-axis (R²: 0.98) and the y-axis (R²: 0.98), and for the z-axis (R²: 0.95), the most accurate machine learning model was the SVM regressor. The application of machine learning methods indicates that machine learning models can be used to predict whole-body vibrations more accurately than linear regression. Full article

Smart agricultural machinery is built upon traditional agricultural equipment, further integrating modern information technologies to achieve automation, precision, and intelligence in agricultural production. Currently, significant progress has been made in the autonomous operation and monitoring technologies of smart agricultural machinery in China. However, challenges remain, including poor adaptability to complex environments, high equipment costs, and issues with system implementation and standardization integration. To help industry professionals quickly understand the current state and promote the rapid development of smart agricultural machinery, this paper provides an overview of the key technologies related to autonomous operation and monitoring in China’s smart agricultural equipment. These technologies include environmental perception, positioning and navigation, autonomous operation and path planning, agricultural machinery status monitoring and fault diagnosis, and field operation monitoring. Each of these key technologies is discussed in depth with examples and analyses. On this basis, the paper analyzes the main challenges faced by the development of autonomous operation and monitoring technologies in China’s smart agricultural machinery sector. Furthermore, it explores the future directions for the development of autonomous operation and monitoring technologies in smart agricultural machinery. This research is of great importance for promoting the transition of China’s agricultural production towards automation and intelligence, improving agricultural production efficiency, and reducing reliance on human labor. Full article

Remote sensing is essential in precision agriculture as this approach provides high-resolution information on the soil’s physical and chemical parameters for detailed decision making. Globally, technologies such as remote sensing and machine learning are increasingly being used to infer these parameters. This study evaluates soil fertility changes and compares them with previous fertilization inputs using high-resolution multispectral imagery and in situ measurements. A UAV-captured image was used to predict the spatial distribution of soil parameters, generating fourteen spectral indices and a digital surface model (DSM) from 103 soil plots across 49.83 hectares. Machine learning algorithms, including classification and regression trees (CART) and random forest (RF), modeled the soil parameters (N-ppm, P-ppm, K-ppm, OM%, and EC-mS/m). The RF model outperformed others, with R² values of 72% for N, 83% for P, 87% for K, 85% for OM, and 70% for EC in 2023. Significant spatiotemporal variations were observed between 2022 and 2023, including an increase in P (14.87 ppm) and a reduction in EC (−0.954 mS/m). High-resolution UAV imagery combined with machine learning proved highly effective for monitoring soil fertility. This approach, tailored to the Peruvian Andes, integrates spectral indices and field-collected data, offering innovative tools to optimize fertilization practices, address soil management challenges, and merge modern technology with traditional methods for sustainable agricultural practices. Full article

Effective water and soil management is crucial for crop productivity, particularly in rice cultivation, where poor soil quality and water scarcity pose challenges. The response of deeper-rooted rice grown in soils amended with different soil amendments (SAs) to Internet of Things (IoT)-managed alternate wetting and drying (AWD) irrigations remains undetermined. This study explores the effects of various SAs on DRO-1 IR64 rice plants under IoT-based soil moisture monitoring of AWD irrigation. A greenhouse experiment executed at the Tokyo University of Agriculture assessed two water management regimes—continuous flooding (CF) and AWD—alongside six types of SAs: vermicompost and peat moss (S + VC + PM), spirulina powder (S + SPP), gypsum (S + GS), rice husk biochar (S + RHB), zeolite (S + ZL), and soil without amendment (S + WA). Soil water content was continuously monitored at 10 cm depth using TEROS 10 probes, with data logged via a ZL6 device and managed through the ZENTRA Cloud application (METER GROUP Company). Under AWD conditions, VC + PM showed the greatest decline in volumetric water content due to enhanced root development and water uptake. In contrast, SPP and ZL maintained consistent water levels. Organic amendments like VC + PM improved soil properties and grain yield, while AWD with ZL and GS optimized water use. Strong associations exist between root traits, biomass, and grain yield. These findings highlight the benefits of integrating SAs for improved productivity in drought-prone rice systems. Full article

Stable pear cultivation relies on cross-pollination, which typically depends on insects or wind. However, natural pollination is often inconsistent due to environmental factors such as temperature and humidity. To ensure reliable fruit set, artificial pollination methods such as wind-powered pollen sprayers are widely used. While effective, these methods require significant labor and operational costs, highlighting the need for a more efficient alternative. To address this issue, this study aims to develop a fully automated drone-based pollination system that integrates Artificial Intelligence (AI) and Unmanned Aerial Vehicles (UAVs). The system is designed to perform artificial pollination while maintaining conventional pear cultivation practices. Demonstration experiments were conducted to evaluate the system’s effectiveness. Results showed that drone pollination achieved a fruit set rate comparable to conventional methods, confirming its feasibility as a labor-saving alternative. This study establishes a practical drone pollination system that eliminates the need for wind, insects, or human labor. By maintaining traditional cultivation practices while improving efficiency, this technology offers a promising solution for sustainable pear production. Full article

Soybeans are key in generating foreign currency for the world economy. Geotechnologies, through vegetation indices (VIs) generated by orbital images or remotely piloted aircraft, are essential tools for assessing the impact of climate on productivity and the ecoclimatic suitability of crops. This study aimed to correlate the growth indices from the CLIMEX model, previously validated, with VIs derived from orbital remote sensing and ecological niche modeling for soybean cultivation in six irrigated pivots located in the northwest of Minas Gerais, Brazil. The maximum normalized difference vegetation index (NDVImax) and the maximum soil-adjusted vegetation index (SAVImax) were extracted from Landsat-8 OLI/TIRS sensor images for the 2016 to 2019 harvests during the R1 to R3 phenological stages. The maximum NDVI values varied across the study regions and crops, ranging from 0.27 to 0.95. Similarly, SAVI values exhibited variability, with the maximum SAVI ranging from 0.13 to 0.85. The growth index (GI_w), derived from the CLIMEX model, ranged from 0.88 to 1. The statistical analysis confirmed a significant correlation (p < 0.05) between NDVImax and GI_w only for the 2018/19 harvest, with a Pearson correlation coefficient of r = 0.86, classified as very strong. Across all harvests, NDVI consistently outperformed SAVI in correlation strength with GI_w. Using geotechnologies through remote sensing shows promise for correlating spectral indices and climate suitability models. However, when using a valid model, all crops did not correlate. Still, our study has the potential to be improved by investigating new hypotheses, such as using drone images with better resolution (spatial, spectral, temporal, and radiometric) and adjusting the response of soybean vegetation indices and the phenological stage. Our results correlating the CLIMEX model of growth indices with vegetation indices have the potential for monitoring soybean cultivation and analyzing the performance of varieties but require a more in-depth view to adapt the methodology. Full article

In agricultural planting, early plant classification is an indicator of crop health and growth. In order to accurately classify early plants, this paper proposes a classification method combining a dual attention mechanism and multi-scale module. Firstly, the ECA module (Efficient channel attention) is added to enhance the attention of the network to plants and suppress irrelevant background noise; secondly, the MSFN (Multi-scale Feedforward Network) module is embedded to improve the ability to capture complex data features. Finally, CA (Channel attention) is added to further emphasize the extracted features, thus enhancing the discrimination ability and improving the accuracy of the model. The experimental results show an accuracy of 93.20%, precision of 94.53%, recall of 93.27%, and an F1 score of 93.39%. This study can realize the classification of early plants, and effectively distinguish crops from weeds, which is helpful to identify and realize accurate weeding, thus promoting the intelligent and modern process of agricultural production. Full article

The mapping and monitoring of rice fields on a large scale using medium and high spatial resolution data (<10 m) is essential for efficient agricultural management and food security. However, challenges such as managing large volumes of data, addressing data gaps, and optimizing available data are key focuses in remote sensing research using automated machine learning models. In this sense, the objective of this study was to propose a pipeline to characterize and classify three different irrigated rice-producing regions in the state of Santa Catarina, Brazil. To achieve this, we used Sentinel-1 Synthetic Aperture Radar (SAR) polarizations and Sentinel-2 optical multispectral spectral bands along with multiple time series indices. The processing of input data and exploratory analysis were performed using a clustering algorithm based on Dynamic Time Warping (DTW), with K-means applied to the time series. For the classification step in the proposed pipeline, we utilized five traditional machine learning models available on the Google Earth Engine platform to determine which had the best performance. We identified four distinct irrigated rice cropping patterns across Santa Catarina, where the northern region favors double cropping, the south predominantly adopts single cropping, and the central region shows both, a flattened single and double cropping. Among the tested classification models, the SVM with Sentinel-1 and Sentinel-2 data yielded the highest accuracy (IoU: 0.807; Dice: 0.885), while CART and GTBoost had the lowest performance. Omission errors were reduced below 10% in most models when using both sensors, but commission errors remained above 15%, especially for patches in which rice fields represent less than 10% of area. These findings highlight the effectiveness of our proposed feature selection and classification pipeline for improving the generalization of irrigated rice mapping in large and diverse regions. Full article

The application of machine learning techniques to determine bioparameters, such as the leaf area index (LAI) and chlorophyll content, has shown significant potential, particularly with the use of unmanned aerial vehicles (UAVs). This study evaluated the use of RGB images obtained from UAVs to estimate bioparameters in sesame crops, utilizing machine learning techniques and data selection methods. The experiment was conducted at the Federal Rural University of Pernambuco and involved using a portable AccuPAR ceptometer to measure the LAI and spectrophotometry to determine photosynthetic pigments. Field images were captured using a DJI Mavic 2 Enterprise Dual remotely piloted aircraft equipped with RGB and thermal cameras. To manage the high dimensionality of the data, CRITIC and Pearson correlation methods were applied to select the most relevant indices for the XGBoost model. The data were divided into training, testing, and validation sets to ensure model generalization, with performance assessed using the R², MAE, and RMSE metrics. XGBoost effectively estimated the LAI, chlorophyll a, total chlorophyll, and carotenoids (R² > 0.7) but had limited performance for chlorophyll b. Pearson correlation was found to be the most effective data selection method for the algorithm. Full article

In recent years, the agriculture sector has undergone a significant digital transformation, integrating artificial intelligence (AI) technologies to harness and analyze the growing volume of data from diverse sources. Machine learning (ML), a powerful branch of AI, has emerged as an essential tool for developing knowledge-based agricultural systems. Grapevine red blotch disease (GRBD) and grapevine leafroll disease (GLD) are viral infections that severely impact grapevine productivity and longevity, leading to considerable economic losses worldwide. Conventional diagnostic methods for these diseases are costly and time-consuming. To address this, ML-based technologies have been increasingly adopted by researchers for early detection by analyzing the foliar symptoms linked to viral infections. This study focused on detecting GRBD and GLD symptoms using Convolutional Neural Networks (CNNs) in computer vision. YOLOv5 outperformed the other deep learning (DL) models tested, such as YOLOv3, YOLOv8, and ResNet-50, where it achieved 95.36% Precision, 95.77% Recall, and an F1-score of 95.56%. These metrics underscore the model’s effectiveness at accurately classifying grapevine leaves with and without GRBD and/or GLD symptoms. Furthermore, benchmarking was performed with two edge computer devices, where Jetson NANO obtained the best cost–benefit performance. The findings support YOLOv5 as a reliable tool for early diagnosis, offering potential economic benefits for large-scale agricultural monitoring. Full article

Resolving the genetic relationships between cultivars is one of the objectives of research in viticulture. To this end, both DNA markers and morphological analysis help to identify synonyms and homonyms and to determine the degree of relatedness between cultivars. Results of genetic analysis using single sequence repeats (SSRs) and single nucleotide polymorphisms (SNPs) point to Hebén as the female progenitor of many of the cultivars currently used in viticulture. Here, seed shape is compared between Hebén and genetically related cultivars. An average silhouette derived from seeds of Hebén was used as a model, and the comparisons were made visually and quantitatively by calculation of J-index values (percent similarity of the seeds and the model). Quantification of seed shape by J-index confirms the data of DNA markers supporting different levels of conservation of maternal seed shape in the varieties. Other seed morphological measurements help to explain the basis of the differences in shape between Hebén, genetically related groups and the external group of unrelated cultivars. Curvature analysis in seeds silhouettes confirms the relationship between Hebén and other cultivars and supports the utility of this technique in the analysis of parental relationships. Full article

The sugarcane cultivation has used heavy machinery on a large scale, which causes soil compaction. The minimum tillage has been used to reduce the traffic of machines on the crop, but there is a lack of appropriate tools for the implementation of this technique, especially in sugarcane areas. The University of Campinas—UNICAMP developed a conservation soil tillage tool called “Rotary paraplow”, the idea was to join the concepts of a vertical milling cutter with the paraplow, which is a tool for subsoiling without inversion of soil. The rotary paraplow is a conservationist tillage because it mobilizes only the planting line with little disturbance of the soil surface and does the tillage with the straw in the area. These conditions make this study pioneering in nature, by proposing an equipment developed to address these issues as an innovation in the agricultural machinery market. We sought to evaluate soil tillage using rotary paraplow and compare it with conventional tillage, regarding soil physical properties and yield. The experiment was conducted in an Oxisol in the city of Jaguariuna, Brazil. The comparison was made between the soil physical properties: soil bulk density, porosity, macroporosity, microporosity and penetration resistance. At the end, a biometric evaluation of the crop was carried out in both areas. The soil properties showed few statistically significant variations, and the production showed no statistical difference. The rotary paraplow proved to be an applicable tool in the cultivation of sugarcane and has the advantage of being an invention adapted to Brazilian soils, bringing a new form of minimal tillage to areas of sugarcane with less tilling on the soil surface, in addition to reducing machine traffic. Full article