Rapid adoption across crops, including soybean, runs alongside validation under local conditions.
ARARA research from the late 1990s and 2000s preceded wider sensing and spraying use. The 2021 agricultural drone rules and crop-specific quality evaluations support adoption.
30 sources
Explains MAPA registration for both own-farm and service operators, alongside separate aviation, airspace and state checks.
Provides the RPAS registration, record-update and monthly reporting pathways.
Catalog and abstract of an 83-page technical book, noting that adoption needs more local technical evidence; the full book has not been fully reviewed.
Describes market growth and unregistered operations; service economics include support equipment and spare batteries. Fleet figures are attributed estimates.
Distinguishes effective from total spray width and measures costs including mixing, movement and charging.
Original trial compares two drone speeds with ground application in soybean, measuring upper/middle canopy deposition under specified conditions.
Breeding research estimates wheat height and soybean maturity from imagery, emphasizing image quality and agronomic experimental design.
Abstract of a 2023 thesis reviewing agricultural drone development; full-text review remains incomplete.
A conference abstract compares drone and ground spraying in vineyards, emphasizing canopy coverage and technology-specific application methods.
The project tests affordable consumer drones for grain, pasture and forestry mapping with field comparisons of derived vegetation indicators.
Research begun in 2024 investigates drone application parameters for grains and vegetables, including spray patterns at different flight heights.
A commercial coffee-field study finds that spray volume, flight height and speed influence application uniformity, motivating crop- and aircraft-specific calibration.
The repository description identifies a 2020 study using drone imagery to assist cover-crop biomass assessment before no-till squash; numerical outcomes were not verified.
This 2014 chapter describes Brazil’s ARARA development during 1999–2005 and autonomous operation in 2006, alongside sensing and control architecture; its regulations and specifications are historical.
A 2022 conference record concerns preliminary comparison of two aircraft for RGB orthomosaic generation; the retrieved description does not establish comparative performance.
A 2025 research bulletin abstract ties vineyard disease-control performance to trellis design and specified flight/application conditions, not a universal drone prescription.
The retrieved description of a 2014 outreach article documents the emergence of drones as precision-agriculture tools in Brazil rather than supplying current market statistics.
The repository verifies a 2024 paper on localized herbicide spraying in soybeans; unreliable full-text retrieval prevented verification of efficacy or savings claims.
A technical chapter connects flight operations, imagery acquisition and model training for livestock monitoring; autonomous flight does not eliminate data-quality design.
The technical publication’s abstract discusses modified and multispectral cameras for vegetation monitoring and emphasizes consistent image quality.
A feedlot study estimates cattle growth from repeated aerial body measurements; the researchers identify other breeds and commercial-scale validation as future work.
A 2019 Dronecoria workshop combined aircraft construction with native-seed pelletization for ecological restoration; this documents development rather than crop-yield outcomes.
The service documents georeferenced TIFF inputs, resolution, orthorectification and calibration requirements, illustrating an explicit data contract for palm-detection analytics.
A conference abstract outlines comparison of imaging sensors for crop and pasture biophysical measurements; it does not provide sufficient detail to declare a winning sensor.
The abstract describes open Python scripts for vineyard vegetation indices, statistics and GeoTIFF export, demonstrating portable image-processing workflows.
The abstract describes citrus-orchard ground-cover estimation with open-source Fiji ImageJ and Weka, including supervised labels and model evaluation.
A soybean Bt trial found that travel speed affected downwash and control performance; greater coverage speed did not necessarily improve biological outcomes.
The abstract compares open-GIS tree counting in three mango orchards; processing quality changes precision and recall, so the most intensive processing is not automatically best.
A 2025 abstract addresses soil and residue interference in soybean vegetation indices, motivating careful processing before interpreting plant condition.
The retrieved description links application service economics, work rate and flight speed; the proceedings paper investigates downwash, but its detailed results were not verified.
No sources match these filters.