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.

Northeast Brazil (NEB), particularly its semiarid region, represents an area highly susceptible to the impacts of climate change, including severe droughts, and intense anthropogenic activities. These stresses may be accelerating environmental degradation and desertification of soil in NEB. The main aim of this study was to gain geospatial insights into the biophysical parameters of surface energy balance and actual evapotranspiration on a multi-temporal scale, aiming to detect and analyze the spectral behavioral patterns of areas vulnerable to degradation processes, based on thematic maps at the surface, for NEB and mainly the semiarid region of NEB from 2000 to 2019. Geospatial data from 8-day MODIS sensor products were used, such as surface reflectance (Terra/MOD09A1 and Aqua/MYD09A1), surface temperature (Terra/MOD11A2 and Aqua/MYD11A2), and actual evapotranspiration (Terra/MOD16A2 and Aqua/MYD16A2), version 6. Therefore, in this study, pixel-to-pixel values were processed by calculating the average pixel statistics for each year. From the reflectance product, digital processing of the surface albedo and spectral vegetation indices was also carried out, using computational programming scripts and machine learning algorithms developed via the Google Earth Engine (GEE) platform. The study also presents a seasonal analysis of these components and their relationships over 20 years. Through vegetation indices and statistical correlations, a new predictive model of actual evapotranspiration was developed. The quantitative and spatiotemporal spectral patterns of the parameters were assessed through descriptive statistics, measures of central tendency and dispersion, and statistical error analyses and correlation indices. Thematic maps highlighted the pixel-to-pixel results, with patterns of high temperature distribution mainly in the central and northeastern part of NEB and the semiarid region of NEB, highlighting the formation of persistent heat islands over time. Meanwhile, in these areas, the maps of actual evapotranspiration showed a drastic reduction due to the lesser availability of energy. Over time, the semiarid region of NEB presented areas with little and/or no vegetation cover, which were highly well-defined between the years 2012 and 2019, confirming that these areas are extremely vulnerable to degradation and desertification processes due to significant loss of vegetative and water resilience. The components of energy balance were highly interconnected to climatological and environmental conditions, showing the severe results of drought and accentuation of the water deficit in NEB, presenting a greater condition of aridity in the semiarid region of NEB over time.

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.

Crop productivity can be affected by biotic and abiotic stressors, and plant growth-promoting bacteria (PGPB) from the genera Bacillus and Burkholderia have the potential to maintain fruit yield and quality, as these bacteria can promote plant growth by solubilizing nutrients, fixing atmospheric nitrogen, producing phytohormones, and exhibiting antagonistic activity against pathogens. This study aimed to evaluate the effects of inoculating plants with Bacillus subtilis and Burkholderia seminalis on their morphological characteristics, fruit technological attributes and yield of common cherry tomatoes (Solanum lycopersicum L.) subjected to induced water deficit. The study was arranged on a split-plot randomized block design, with four water replacement levels (40%, 60%, 80% and 100% of crop evapotranspiration, ETc) and three inoculation treatments (Bacillus subtilis ATCC 23858, Burkholderia seminalis TC3.4.2R3 and non-inoculation). Data were subjected to analysis of variance using the F-test and compared using Tukey’s test (p < 0.05) and multivariate statistics from principal component analysis. Inoculation with Burkholderia seminalis increased the plant fresh and dry shoot and root mass, as well as root volume. Inoculation with Bacillus subtilis increased carotenoid and chlorophyll b contents. Both inoculations enhanced leaf water content in plants experiencing severe water deficit (40% of ETc). The use of these strains as PGPB increased the fruit soluble solids content. Higher productivity in inoculated plants was achieved through a greater number of fruits per cluster, despite the individual fruits being lighter. Treatments with higher water replacement levels resulted in greater yield. Inoculations showed biotechnological potential in mitigating water deficit in cherry tomatoes.