The development of approaches to determine the spatial variability of nitrogen (N) into coffee leaves is essential to increase productivity and reduce production costs and environmental impacts associated with excessive N applications. Thus, this study aimed to assess the potential of the Random Forest (RF) machine learning method applied to vegetation indices (VI) obtained from Remotely Piloted Aircraft (RPA) images to measure the N content in coffee plants. A total of 10 VI were obtained from multispectral images by a camera attached to a rotary-wing RPA. The RGB orthomosaic was used to determine sampling points at the crop area, which were ranked by N levels in the plants as deficient, critical, or sufficient. The chemical analysis of N content in the coffee leaves, as well as the VI values in sample points, were used as input parameters for the image training and its classification by the RF. The suggested model has shown global accuracy and a kappa coefficient of up to 0.91 and 0.86, respectively. The best results were achieved using the Green Normalized Difference Vegetation (GNDVI) and Green Optimized Soil Adjusted Vegetation Index (GOSAVI). In addition, the model enabled the evaluation of the spatial distribution of N in the coffee trees, as well as quantification of N deficiency in the crop for the whole area. The GNDVI and GOSAVI allowed the verification that 22% of the entire crop area had plants with N deficiency symptoms, which would result in a reduction of 78% in the amount of N applied by the producer.

Mechanized operations on terrain slopes can still lead to considerable errors in the alignment and distribution of plants. Knowing slope interference in semi-mechanized planting quality can contribute to precision improvement in decision making, mainly in regions with high slope. This study evaluates the quality of semi-mechanized coffee planting in different land slopes using a remotely piloted aircraft (RPA) and statistical process control (SPC). In a commercial coffee plantation, aerial images were collected by a remotely piloted aircraft (RPA) and subsequently transformed into a digital elevation model (DEM) and a slope map. Slope data were subjected to variance analysis and statistical process control (SPC). Dependent variables analyzed were variations in distance between planting lines and between plants in line. The distribution of plants on all the slopes evaluated was below expected; the most impacted was the slope between 20–25%, implementing 7.8% fewer plants than projected. Inferences about the spacing between plants in the planting row showed that in slopes between 30–40%, the spacing was 0.53 m and between 0 and 15% was 0.55 m. This denotes the compensation of the speed of the operation on different slopes. The spacing between the planting lines had unusual variations on steep slopes. The SCP quality graphics are of lower quality in operations between 30–40%, as they have an average spacing of 3.65 m and discrepant points in the graphics. Spacing variations were observed in all slopes as shown in the SCP charts, and possible causes and implications for future management were discussed, contributing to improvements in the culture installation stage.

Computer vision algorithms for counting plants are an indispensable alternative in managing coffee growing. This research aimed to develop an algorithm for automatic counting of coffee plants and to determine the best age to carry out monitoring of plants using remotely piloted aircraft (RPA) images. This algorithm was based on a convolutional neural network (CNN) system and Open Source Computer Vision Library (OpenCV). The analyses were carried out in coffee-growing areas at the development stages three, six, and twelve months after planting. After obtaining images, the dataset was organized and inserted into a You Only Look Once (YOLOv3) neural network. The training stage was undertaken using 7458 plants aged three, six, and twelve months, reaching stability in the iterations between 3000 and 4000 it. Plant detection within twelve months was not possible due to crown unification. A counting accuracy of 86.5% was achieved with plants at three months of development. The plants’ characteristics at this age may have influenced the reduction in accuracy, and the low uniformity of the canopy may have made it challenging for the neural network to define a pattern. In plantations with six months of development, 96.8% accuracy was obtained for counting plants automatically. This analysis enables the development of an algorithm for automated counting of coffee plants using RGB images obtained by remotely piloted aircraft and machine learning applications.

The implantation of coffee crop plantations requires cartographic data for dimensioning areas and planning the planting line. Digital terrain models (DTMs) obtained from remotely piloted aircraft (RPA) can contribute to efficient data collection for topography making this technique applicable to precision coffee projects. Aiming to achieve efficiency in the collection, processing and photogrammetric products quality, flight configurations and image processing were evaluated. Two hundred sixty-five points obtained by Global Navigation Satellite System (GNSS) receivers characterized the topographic surface. Then eighteen flight missions were carried out by RPA in the configurations of altitude above ground level (AGL) and frontal and lateral image overlay. In addition, different point cloud formats evaluated the image processing (time) efficiency in DTM. Flights performed at 120 m AGL and 80 × 80% overlap showed higher assertiveness and efficiency in generation DTMs. The 90 m AGL flight showed great terrain detail, causing significant surface differences concerning the topography obtained by GNSS. An increase in image overlap requires longer processing times, not contributing linearly to the geometric quality of orthomosaic. Slope ranges up to 20% are considered reliable for precision coffee growing projects; above 20% overestimates the slope values of the land. Changes in flight settings and image processing are satisfactory for precision coffee projects. Image overlap reduction was significant in reducing the processing time without influencing the quality of the DTMs. In addition, image processing performed in shallow point clouds did not interfere with the DTMs quality.