Proceedings
Topics
| Filter results40 paper(s) found. |
|---|
1. Beyond the Mean: A Quantile Count Regression Analysis of Precision Farming Technology Adoption Intensity by German FarmersThis study examines the factors influencing precision agriculture technology adoption intensity among German farmers using an innovative quantile count regression approach that reveals heterogeneous relationships across different segments of the adoption distribution. While previous research has primarily relied on mean-based regression models that may mask important variation in adoption determinants, this analysis provides new insights into how factors affect low, moderate, and high technol... M. Michels, O. Musshoff |
2. Worldwide Crop Precision Agriculture Adoption: 2026 UpdateRobotics, machine vision, and drone spraying have attracted much attention in recent years. But the technologies introduced in the 2000s and earlier, such as yield monitors, guidance, variable rate technology (VRT), and digital imagery continue to advance worldwide, more on large mechanized grain and oilseed farms. This update summarizes census estimates and adoption surveys with statistically reliable random sampling from 24 countries. Within-country and farm size breakdowns are reported whe... B. Erickson, J. Mcfadden, E. Morimoto, J. Lowenberg-deboer |
3. Expanding Access to High-Resolution Soil pH Measurement: From Smallholder Farms to 200-Hectare FieldsSoil pH is one of the most influential and correctable soil properties affecting crop productivity. It governs nutrient availability, toxicity risk, microbial activity, and overall soil function. Yet timely and spatially representative pH measurement remains inconsistent across agricultural systems due to laboratory turnaround times, sampling costs, limited field access, and sub-field variability not captured by conventional sampling density. This study evaluated multiple strategies... T. Lund, C. Maxton, E. Lund |
4. Benchmarking Precision Agriculture Adoption in the United States and BrazilThe United States has long been regarded as a global leader in agricultural technology and productivity. However, rapid advancements in other major producing countries are challenging this position. Brazil, in particular, has paired large-scale crop expansion with accelerated digital transformation, raising important questions about where the United States continues to lead and where it risks losing its competitive edge. Understanding how precision agriculture technologies are being adopted a... J. Colussi, B. Erickson, T. Malone, M. Langemeier, C. Fiechter |
5. Understanding Adoption and Post-Adoption Impacts of Smart Farming Technologies in ItalySmart farming technologies (SFTs) are increasingly promoted as key enablers of agricultural efficiency, resource optimization, and environmental sustainability. However, despite rapid technological advancement, empirical evidence on realized economic and resource-use impacts under real farming conditions remains limited, creating uncertainty about the magnitude and distribution of impacts. Existing evidence remains largely focused on perceived drivers, barriers, and intentions to adopt, rathe... |
6. Accuracy Analysis of C/A Code-based GNSS Receivers in Kinematic ConditionPrecision agriculture has emerged as a strategic approach to optimize input use and maximize crop productivity. One of the key pillars of this practice is the collection of georeferenced data, essential for the monitoring and efficient management of cultivated areas. This report aims to compare the performance of different positioning signal reception technologies under dynamic conditions. Three C/A code navigation receivers integrated into smartphones, one conventional navigation GPS receive... S. Ribeiro, G. Sanches, C.N. Ricci, J. Regazzo, J.P. Molin |
7. Digital Agriculture in Dairy Farming: Connectivity Diagnosis and Barriers to Technology Adoption in an Agrotechnological DistrictThe integration of digital tools and communication systems has underpinned a profound transformation in global production chains, aiming to optimize farm operations through technological innovation. Within this context, the present study forms part of the Semear Digital project, coordinated by Embrapa, and is grounded in the premise that digital inclusion constitutes an indispensable strategy for the sustainability and competitiveness of contemporary dairy farming. The primary object... M.D. Melo, C.M. Paiva, A.L. Oliveira, F.N. Maciel, G.C. Siqueira , M.R. Borges , G.S. Furtado, P.M. Leme |
8. Impact of Sampling Density on the Spatial Prediction of Soil Chemical Attributes Using Geostatistics and Machine LearningSoil sampling at high grid densities represents a significant economic barrier to the adoption of Precision Agriculture (PA) in Brazil. This study evaluates the trade-off between sampling density and interpolation quality by comparing geostatistical methods and machine learning algorithms. Three distinct approaches were statistically assessed: Ordinary Kriging (OK), Random Forest (RF), and the hybrid Random Forest Regression Kriging (RFRK). The analysis was conducted across six fields totalin... S. Ribeiro, H. Fantin Gebler, J.P. Molin, R.F. Da Silva |
9. Determinants of the Intensity of Digital Precision Technology Adoption in Brazilian FeedlotsPrecision livestock farming has gained prominence as a tool to enhance managerial control and reduce risk in intensive production systems. In the case of Brazilian beef cattle feedlots, characterized by high price volatility, tight margins, and increasing pressure for environmental performance, the adoption of digital technologies represents a relevant strategy to improve decision-making processes. Unlike studies that focus solely on binary adoption (adopt/non-adopt), understanding adoption i... G. , M.J. Carrer, M. , L.C. David, H.M. Souza Filho, E. Bonjour |
10. Correcting LiDAR-based Plant Height Estimation Errors in Dense Cotton CanopiesCotton is a perennial plant grown as an annual crop and, if not properly managed, excessive vegetative growth may reduce yield, making the use of plant growth regulators (PGR) essential. In precision agriculture, spatial representation of PGR requirements depends on plant height measurements, which are typically labor-intensive. LiDAR sensors mounted on drones have been widely used to estimate plant height. However, under certain conditions, cotton plants can become highly vigorous, resulting... P. Zolin, L. Peranzoni Deponti, L. Bastos, L.R. Amaral |
11. Agronomist-in-the-Loop Semantic 3D Reconstruction of Cotton Boll Morphology from UAV Imagery for Precision AgricultureStandard aerial photogrammetry is failing precision agriculture in one specific area: the detailed morphological assessment of complex, cluttered canopies. While creating a field-level map is trivial, recovering the geometry of a single cotton boll from a drone altitude of 30 meters is often mathematically intractable for standard Structure-from-Motion (SfM) solvers. These traditional pipelines depend on pixel-perfect consistency, which breaks down am... P. Sundaravadivel, H. Manjunatha, S. Borah, A. Anand, A. Price, H. Torbert, L. Tamil, T. Stroud |
12. Performance of Unmanned Aerial Vehicles to Broadcast-interseed Cover Crops at Different Crop StagesDrones have become more affordable, making them a viable option to use for broadcast-interseeding cover crops within crops prior to harvest. This strategy has become popular in the USA over the past three years. However, limited information exists on spreading with drones and the in-field performance and setups to ensure uniform distribution. Therefore, the objective of this study was to assess the distribution uniformity of broadcast- interseeded cover crops into cash crops prior to ha... J.P. Fulton, A. Thomas, S.A. Shearer, E. Hawkins, S. Khanal |
13. Comparing UAV-based Multispectral Indices with Thermal and Energy Balance Models for Barley Yield Components EstimationAccurate estimation of barley yield components is essential for improving crop management and breeding strategies under contrasting water regimes. This study evaluates the potential of integrating unmanned aerial vehicle (UAV)-based multispectral and thermal imagery with energy balance modeling to predict grain yield (GY), thousand kernel weight (TKW), and grain filling period (GFP). A recombinant inbred line (RIL) population derived from SBCC073 × Cierzo was grown under irrigated and r... D. Gomez-candon, A. Cabeza, D. Villegas, A.M. Casas, E. Igartua |
14. Generation of a Digital Terrain Model in Areas with Dense Vegetation Cover for the Identification of Erosive Processes from LiDAR Data Obtained with a Matrice 300 DroneThe analysis of relief, as a conditioning element of surface processes, depends on its adequate representation through Digital Terrain Models (DTM), especially in studies aimed at identifying erosive processes. In this context, the use of LiDAR sensors makes it possible to detect terrain features even under dense vegetation cover, overcoming the limitations of optical sensors. Thus, this research aimed to demonstrate the applicability of the Matrice 300 RTK drone, equipped with the LiDAR L1 (... P. Rezende, R. Fernandes De Queiroz, H.A. Machado, D.S. Freitas |
15. Automated Initial Plant Stand Assessment in Bean Crops Using Uav-based Yolov8 DetectionThe use of RGB images acquired by unmanned aerial vehicles (UAVs), combined with artificial intelligence techniques, has increased significantly in recent years for object identification and crop monitoring in agriculture. These technologies enable rapid plant stand count, facilitating decision-making processes. However, limited information is available regarding the optimal flight height for identifying bean plants at early growth stages. Therefore, the objective of this study was to evaluat... G. Valdes Fernandez , G. Lacerda Da Silveira, R. Fernandes Queiroz Alves , T. Costa Barboza, M.C. Arnosti, A. Felipe Dos Santos, W.B. Da Silva, O. Pereira Da Costa |
16. UAV-Based Detection and Precision Management of Cirsium arvense: An End-to-End Workflow from Deep Learning to Variable-Rate SprayingUnmanned aerial vehicles (UAVs) combined with deep learning can enable site-specific weed management by transforming high-resolution imagery into actionable prescription maps for precision spraying. This study presents and validates an end-to-end operational workflow for detecting Cirsium arvense under real field conditions and converting detections into sprayer-compatible management zones. A 24.61 ha arable field in northwestern Hungary was surveyed using a multirotor UAV equipped w... M. László |
17. Autonomous Edge-AI–Enabled Drone Systems for Real-Time Agricultural Inference and Decision-MakingHigh-throughput, low-latency phenotyping and field surveillance remain critical bottlenecks in precision agriculture and environmental monitoring due to delayed data turnaround, large data volumes, computationally intensive preprocessing, and expertise-heavy analysis workflows. These constraints hinder timely crop improvement, pest and disease management, and informed agronomic decision-making. To address these challenges, we present an integrated, end-to-end autonomous drone system that enab... |
18. High Resolution 3D Crop Analysis and Decision Support using UAV LiDAR TechnologyAgriculture is one of the most significant economic activities in Brazil, with coffee cultivation playing a particularly prominent role in the state of Minas Gerais, which leads national production. During the early stages of the coffee growth cycle, systematic monitoring practices are required to assess the spatial uniformity of plant development. These observations support management decisions, including the identification of areas requiring specific interventions and the targeted applicati... A. Pavanelli, L. Carneiro De Souza, C.E. Inácio, M. De Oliveira, V. Rennó, F. Portelinha, L. Mendes |
19. Development and Field Validation of a Scalable UAV-Based Framework for Automated Cattle Counting and Herd Management in Extensive Production SystemsBrazil holds the largest commercial cattle herd in the world, with more than 230 million head, representing approximately 20% of the global population. In this context, technologies capable of optimizing herd monitoring are strategic for increasing production efficiency, reducing operational costs, and promoting sustainability in livestock systems. Among these technologies, computer vision–based systems have emerged as a promising alternative for automated animal detection and counting ... F. H. S. Sousa , T. S. Maciel, M. M. Dos Reis, R.D. Santos, A. M. Santos, A. M. S. De Souza, A. K. F. Veras, G. G. Ferreira, M. P. M. Nunes, M. C. R. Seruffo, L. C. C. Daher, A. G.m. Silva |
20. A Machine Learning Framework for Crop Productivity Classification and Risk AssessmentThe integration of Artificial Intelligence and Remote Sensing is essential for the early identification of agricultural fields with suboptimal growing conditions. Such capabilities are vital for targeted interventions, supply chain logistics, and agricultural risk management. This study developed and validated a machine learning framework designed to classify the productivity conditions of corn, soybean, and wheat into ‘Low’, ‘Medium’, and ‘High’ tiers, uti... J.D. Xavier, K. Schenatto, G.V. Miranda, C.L. Bazzi, R. Sobjak |
21. Yield Stability in Continuous Corn Under Three Years of Nitrogen Management: Linking UAV Derived Vegetation Indices to Temporal VariabilityContinuous corn production systems are highly sensitive to nitrogen (N) management, and year to year variability in weather conditions can strongly influence crop performance and yield stability. Understanding how different N fertilization strategies affect yield evaluation and fertilizer recommendations from remote sensing platforms, consistency across multiple growing seasons, is essential for the development of future decision support systems. Because vegetation indices (VIs) derived from ... E. Lord, E. Fallon, A. Cambouris |
22. Comparison of Orbital and UAV Remote Sensing for Coffee Crop Monitoring in Mountainous TerrainMonitoring coffee crops is an important step for the success of production systems. Recently, manual field inspections have been replaced by automated techniques aimed at improving spatial coverage and reducing costs. One such technique is remote sensing, which can be performed using both orbital platforms and Unmanned Aerial Vehicles (UAVs). However, coffee cultivation presents significant imaging challenges due to plant spacing, where wide row spacing results in greater spectral variability... I. Araújo Barbosa, M.H. Pereira, D. Queiroz, A.L. Coelho, D. Sárvio Valente, M.C. Moreira |
23. Temporal Variability of Vegetation Indices and Spatial Autocorrelation Applied to Specific Management in Mountain Coffee CropsThe characterization of spatial and temporal variability in agricultural crops is an important stage for the application of precision agriculture, enabling the definition of management zones and the prescription of inputs for variable rate application. In this context, the use of unmanned aerial vehicles (UAVs) equipped with multispectral sensors has enabled the acquisition of spectral data with spatial and temporal resolutions compatible with the objectives of the intended activity. Asso... I. Araújo Barbosa, D. Queiroz, A.L. Coelho, D. Sárvio Valente, M.C. Moreira, B. Costalonga Vargas |
24. Enhancing Weed Detection in Corn Crops Through Attention-based Models and Curated DatasetsWeed infestation is one of the leading causes of global agricultural productivity losses, directly impacting production costs, environmental sustainability, and food security. In precision agriculture, automated weed detection from aerial imagery enables site-specific herbicide application, reducing chemical overuse and environmental impact. Deep learning-based computer vision techniques have been widely adopted for this purpose, with Convolutional Neural Networks (CNNs) historically dominati... T.M. Martins, E.C. Tetila, J.G. Barbedo, J.C. Felipe, L. Zhao |
25. Sun-view Geometry Causes Hotspot Effect in UAV Imagery During Summer in Tropical RegionsHigh-resolution imagery acquired by Unmanned Aerial Vehicles (UAVs) is essential for remote sensing applications. However, the high solar elevation around noon during summer in tropical regions produces a hotspot effect when the camera is mapping at nadir. The sun-view alignment generates a bright spot in each image acquired during the flight, which significantly changes the digital number and, consequently, the estimated surface reflectance. The objective of this research was to analyze the ... W. Maes, L. Rodrigues , A.M. Tommaselli, R.P. Silva, V. Carreira |
26. Using Hyperspectral Imagery to Monitor Peanut Physiological Responses to Water StressPeanut production in Georgia plays an important role in the United States agriculture, as it is the country’s largest peanut producer. However, increasing climate variability poses major risks in peanut productivity, particularly through drought and heat stress. This study aimed to detect and monitor physiological responses of nine peanut genotypes under irrigated and drought conditions using high-resolution hyperspectral imaging (HSI). A field trial was conducted in the 2025 season at ... |
27. Assessing Metering and Spreading Performance of Drones (UAVs) for Application of Dry MaterialsAlong with pesticide applications, the use of UAVs (also commonly referred to as drones) for applying dry materials has increased rapidly in the United States. Currently, various types of product metering and spreading systems are available on commercial drones for applying dry materials. However, limited information is available on their application performance, especially the metering accuracy and the uniformity of distribution across the swath. Therefore, research studies were conducted to... S. Virk, E. Ward, J. Sizemore |
28. Co-registration of RGB UAV Orthomosaics Through a Semi-automated Affine Method Based on Ground Control Points and Phase Correlation ValidationUAV images are crucial for Precision Agriculture (AP) purposes which require the monitoring of spatial variability regarding plant growth, especially to assess variation at plant level over time in perennial crops, such as banana plantations. However, spatial misalignments between orthomosaics from different dates requires post-processing image matching, i.e., co-registration, to ensure reliable spatiotemporal variability analysis. This study proposes a method for the co-registration of RGB U... B.R. Costa, J.P. Molin, B. Barreto |
29. Individualization of Banana Canopies Using Multispectral Vegetation Index and the Watershed AlgorithmThe individualization of canopies in perennial crops is an essential step in precision agriculture, enabling plant counting, vigor monitoring, yield prediction, pest management, and harvest planning. Banana (Musa spp.), characterized by large leaves, closed canopy, and high biomass, presents specific challenges for automated segmentation. This study evaluated the performance of the watershed algorithm for canopy individualization, using different multispectral vegetation index, betwe... B.R. Costa, J.P. Molin, B. Barreto |
30. Determination And Calculation Of Eucalyptus Biomass From Lidar Sensor Data And Projection Of Available BiomassEucalyptus (Eucalyptus spp.) is one of the most widely cultivated forest species in Brazil and worldwide. Eucalyptus biomass is organic matter derived from the eucalyptus tree which can be used as a renewable energy source. In recent years, advances in remote sensing technologies have made it possible to estimate forest biomass more accurately and non-destructively, with the use of LiDAR (Light Detection and Ranging) sensors being particularly noteworthy. This system emits r... J.P. Da Silva, G.A. Araujo, L. Carvalho, J.P. Verçosa, A.C. Tavares |
31. Predicting Maize Physiological Traits from Multispectral UAV Imagery Using Machine Learning AlgorithmsMaize has major global importance for human and animal nutrition. The identification of physiological parameters is an essential tool for decision-making in crop management. When associated with these parameters, machine learning (ML) enables the analysis of large volumes of data, making it a suitable approach for robust datasets. Therefore, this study aimed to estimate physiological parameters correlated with vegetation indices through the application of ML models across different field area... E. Amaral, T. Costa Barboza, M. Ardigueri, U. Sigdel, L. Lacerda, A. Felipe Dos Santos |
32. Estimation of Agronomic Parameters in Maize Using UAV-based Vegetation Indices Obtained by a Multispectral SensorPrecision agriculture emerges as a response to optimize input use and to monitor crop spatial variability over time. In this context, the use of vegetation indices obtained by optical sensors embedded in drones or satellites has become a useful tool for predicting agronomic parameters in maize fields, such as aboveground dry biomass, leaf chlorophyll content, and grain yield. Thus, the objective of this study was to correlate field agronomic parameters with vegetation indexes obtained by a mu... B. Nogueira, A.C. Figueiró, A. , E. Bender, C.D. Lima, A.L. Vian, C. Bredemeier |
33. Sensor-based plant growth regulator management in cotton: plot-level and within-plant yield distributionCotton yield is distributed among canopy thirds, and the use of plant growth regulators (PGRs) modulate this balance, affecting fruiting and yield. Drone-mounted sensors can be used to estimate plant growth and generate maps for variable rate PGR applications to support management. This study compared traditional PGR management with fixed timing and rate to sensor-based management by evaluating PGR application rate and timing. Within-plant yield di... A. Rorato, P. . Zolin, G.J. Scarpin, L.P. Deponti, F.R. Echer, L. Bastos |
34. Detection of latrine areas in equine paddocks using drones and computer visionEquines can exhibit behaviors that are harmful to the soil, such as spatial segregation, which is caused by their selective grazing pattern. This species may choose its feeding areas based on vegetation structural characteristics, such as forage density, leaf availability, and stage of maturity (which are perceived through their tactile receptors). When present daily, this natural behavior can impair soil health, as spatial segregation within paddocks intensifies and latrine (dung) areas form... |
35. Sugarcane row gaps enable the identification of critical rows for targeted interventionsDistinct patterns of sugarcane row gaps and associated plant population reduction drive the spatiotemporal variability of yield, creating a bottleneck for row prioritization in management decisions. This study tested the hypothesis that specific sugarcane rows within a field concentrate most of the linear gap lengths (LLG) and their associated economic and productive losses, consistent with the Pareto Principle. The objective was to identify rows that are critical in terms of LLG occurrence, ... E. Otavio Da Silva, J.P. Molin, R. Canal Filho, M.R. Cherubin |
36. Monitoring the Invasive Grass Eragrostis plana with Artificial Intelligence: A Comparative Study of Hyperspectral Data and Drone-Based Object DetectionThe invasion of exotic plant species is recognized as one of the major threats to biodiversity and ecosystem stability worldwide. In the Brazilian Pampa biome, Eragrostis plana Nees (commonly known as Annoni grass) has become one of the most aggressive invasive species since its introduction in the 1950s. Currently occupying approximately 20% of the native grassland vegetation in the state of Rio Grande do Sul, this species exhibits high adaptive capacity, rapid propagation, and the absence o... S. Camargo, N. Perez, T.S. Lopes, A.R. Silveira |
37. Weed mapping: advantages of RGB CNN-based approaches vs multispectral pixel-based methodsWeed detection remains a major challenge in modern agriculture, and accurate weed mapping is crucial to support rapid and efficient management interventions, ensuring crop productivity and economic viability. In this context, geotechnologies such as remote sensing and computer vision, together with the widespread adoption of drones, enable the acquisition of ultra–high spatial resolution imagery, allowing more detailed analyses in complex agricultural environments. Although multispectra... |
38. Weed identification in soybean fields using RGB UAV imagery acquired at different flight altitudesThe presence of weeds in agricultural fields is one of the main factors reducing crop productivity due to competition for light, water, and nutrients. In this context, digital agriculture and the use of unmanned aerial vehicles (UAVs) enable the acquisition of high-resolution imagery for detecting and monitoring these weeds. However, increasing flight altitude reduces spatial resolution, compromising the identification of key visual attributes (shape, texture, and edges) and making it more di... |
39. Generation of Ultra-High-Resolution Synthetic Data via Generative Super-Resolution to Support UAV Image Annotation and Model TrainingManual annotation of imagery acquired by unmanned aerial vehicles (UAVs) for detection/segmentation tasks is one of the main bottlenecks for deep learning applications in precision agriculture, due to the high cost and the time required to produce consistent labels. In addition, low-altitude flights to obtain ultra–high spatial resolution increase operational complexity and data volume, limiting the scalability of acquisition campaigns. Although neural network–based super-resoluti... M.A. Karasinski, R. Costa, C. Melville, E. Macedo, I.L. Gabriel Da Silva Carmo , S.V. Dantas Oliveira, M.P. Galvão, A.B. Bendahan, C.R. Bezerra |
40. Spreading Performance of a UAV for Cover Crop (Cereal Rye) Seeding at Varying Application Rates and Flight SpeedsWith the increased use of UAVs for pesticide applications in agriculture, there is growing interest in their use for applying dry solid materials, especially for seeding cover crops. However, limited information currently exists on the application performance of UAVs for broadcasting cover crop seed and the effects of different operational parameters. Therefore, studies were conducted to assess the spreading performance of a DJI Agras T25 UAV under varying application rates (22.4, 33.6, 44.8,... S. Virk, J. Sizemore |