Artificial Intelligence (AI) has changed how processes are developed, and decisions are made in the agricultural area replacing manual and repetitive processes with automated and more efficient ones. This study presents the application of deep learning techniques to detect and segment weeds in agricultural crops by applying models with different architectures in the analysis of images captured by an Unmanned Aerial Vehicle (UAV). This study contributes to the computer vision field by comparing the performance of the You Only Look Once (YOLOv8n, YOLOv8s, YOLOv8m, and YOLOv8l), Mask R-CNN (with framework Detectron2), and U-Net models, making public the dataset with aerial images of soybeans and beans. The models were trained using a dataset consisting of 3021 images, randomly divided into test, validation, and training sets, which were annotated, resized, and increased using the Roboflow application interface. Evaluation metrics were used, which included training efficiency (mAP50 and mAP50-90), precision, accuracy, and recall in the model’s evaluation and comparison. The YOLOv8s variant achieved higher performance with an mAP50 of 97%, precision of 99.7%, and recall of 99% when compared to the other models. The data from this manuscript show that deep learning models can generate efficient results for automatic weed detection when trained with a well-labeled and large set. Furthermore, this study demonstrated the great potential of using advanced object segmentation algorithms in detecting weeds in soybean and bean crops.

Integrating advanced technologies such as artificial intelligence (AI) with traditional agricultural practices has changed how activities are developed in agriculture, with the aim of automating manual processes and improving the efficiency and quality of farming decisions. With the advent of deep learning models such as convolutional neural network (CNN) and You Only Look Once (YOLO), many studies have emerged given the need to develop solutions to problems and take advantage of all the potential that this technology has to offer. This systematic literature review aims to present an in-depth investigation of the application of AI in supporting the management of weeds, plant nutrition, water, pests, and diseases. This systematic review was conducted using the PRISMA methodology and guidelines. Data from different papers indicated that the main research interests comprise five groups: (a) type of agronomic problems; (b) type of sensor; (c) dataset treatment; (d) evaluation metrics and quantification; and (e) AI technique. The inclusion (I) and exclusion (E) criteria adopted in this study included: (I1) articles that obtained AI techniques for agricultural analysis; (I2) complete articles written in English; (I3) articles from specialized scientific journals; (E1) articles that did not describe the type of agrarian analysis used; (E2) articles that did not specify the AI technique used and that were incomplete or abstract; (E3) articles that did not present substantial experimental results. The articles were searched on the official pages of the main scientific bases: ACM, IEEE, ScienceDirect, MDPI, and Web of Science. The papers were categorized and grouped to show the main contributions of the literature to support agricultural decisions using AI. This study found that AI methods perform better in supporting weed detection, classification of plant diseases, and estimation of agricultural yield in crops when using images captured by Unmanned Aerial Vehicles (UAVs). Furthermore, CNN and YOLO, as well as their variations, present the best results for all groups presented. This review also points out the limitations and potential challenges when working with deep machine learning models, aiming to contribute to knowledge systematization and to benefit researchers and professionals regarding AI applications in mitigating agronomic problems.

The applicability of remote sensing enables the prediction of nutritional value, phytosanitary conditions, and productivity of crops in a non-destructive manner, with greater efficiency than conventional techniques. By identifying problems early and providing specific management recommendations in bean cultivation, farmers can reduce crop losses, provide more accurate and adequate diagnoses, and increase the efficiency of agricultural resources. The aim was to analyze the efficiency of vegetation indices using remote sensing techniques from UAV multispectral images and Sentinel-2A/MSI to evaluate the spectral response of common bean (Phaseolus vulgaris L.) cultivation in different phenological stages (V4 = 32 DAS; R5 = 47 DAS; R6 = 60 DAS; R8 = 74 DAS; and R9 = 89 DAS, in 99 days after sowing—DAS) with the application of doses of magnesium (0, 250, 500, and 1000 g ha⁻¹). The field characteristics analyzed were mainly chlorophyll content, productivity, and plant height in an experimental area by central pivot in the midwest region of Brazil. Data from UAV vegetation indices served as variables for the treatments implemented in the field and were statistically correlated with the crop’s biophysical parameters. The spectral response of the bean crop was also detected through spectral indices (NDVI, NDMI_GAO, and NDWI_GAO) from Sentinel-2A/MSI, with spectral resolutions of 10 and 20 m. The quantitative values of NDVI from UAV and Sentinel-2A/MSI were evaluated by multivariate statistical analysis, such as principal components (PC), and cophenetic correlation coefficient (CCC), in the different phenological stages. The NDVI and MCARI vegetation indices stood out for productivity prediction, with r = 0.82 and RMSE of 330 and 329 kg ha⁻¹, respectively. The TGI had the best performance in terms of plant height (r = 0.73 and RMSE = 7.4 cm). The best index for detecting the relative chlorophyll SPAD content was MCARI (r = 0.81; R² = 0.66 and RMSE = 10.14 SPAD), followed by NDVI (r = 0.81; R² = 0.65 and RMSE = 10.19 SPAD). The phenological stage with the highest accuracy in estimating productive variables was R9 (Physiological maturation). GNDVI in stages R6 and R9 and VARI in stage R9 were significant at 5% for magnesium doses, with quadratic regression adjustments and a maximum point at 500 g ha⁻¹. Vegetation indices based on multispectral bands of Sentinel-2A/MSI exhibited a spectral dynamic capable of aiding in the management of bean crops throughout their cycle. PCA (PC1 = 48.83% and PC2 = 39.25%) of the satellite multiple regression model from UAV vs. Sentinel-2A/MSI presented a good coefficient of determination (R² = 0.667) and low RMSE = 0.12. UAV data for the NDVI showed that the Sentinel-2A/MSI samples were more homogeneous, while the UAV samples detected a more heterogeneous quantitative pattern, depending on the development of the crop and the application of doses of magnesium. Results shown denote the potential of using geotechnologies, especially the spectral response of vegetation indices in monitoring common bean crops. Although UAV and Sentinel-2A/MSI technologies are effective in evaluating standards of the common bean crop cycle, more studies are needed to better understand the relationship between field variables and spectral responses.