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.

Current irrigation management zones (IMZs) for variable rate irrigation (VRI) systems are static. They are delineated in the beginning of the season and used thereafter. However, recent research has shown that IMZ boundaries are transient and change with time during the growing season. The primary goal of this study was to explore the potential of using vegetation indices (VIs) developed from unmanned aerial vehicle (UAV) and satellite images to predict cotton physiological parameters that can be used to delineate in-season boundaries of IMZs. A 2 year study was conducted in a 38 ha commercial cotton field in southwestern Georgia, USA. Throughout the two growing seasons, VIs were calculated from UAV, PlanetScope, and Sentinel-2 images. Predawn leaf water potential (LWP_PD) and plant height were measured at 37 locations in the field on the same day as the flights and correlated with UAV and satellite based-VIs. GNDVI (Green normalized difference vegetation index) was the best predictor of plant height with correlation values of 0.72 (p < .0001) and 0.84 (p < .0001) for 2019 and 2020, respectively. A secondary goal was to compare the performance of dynamic VRI (DVRI) to conventional irrigation. The field was divided into alternating parallel conventional, and DVRI strips to compare the two scheduling methods. The conventional strips were irrigated using the farmer’s standard method and individual IMZs within the DVRI strips were irrigated based on soil water tension (SWT) measured with a wireless soil moisture sensor network. LWP and SWT measurements correlated well. IMZs were initially delineated using soil texture, apparent soil electrical conductivity (ECa), and yield maps and satellite images from previous years and were modified in-season to reflect patterns observed in the plant height maps. In 2020, the DVRI system prescribed an average irrigation amount of 50.8 mm while conventional irrigation applied an average of 58.4 mm. Average yields for DVRI and conventional were 1248 and 1191 kg ha⁻¹, respectively. The DVRI system resulted in average yield 4.6% higher than conventional irrigation, while applying 14.0% less water. Despite the lower water application by the DRVI system, the performance comparison between the DRVI and the conventional irrigation was not conclusive.

Using UAV and multispectral images has contributed to identifying field variability and improving crop management through different data modeling methods. However, knowledge on application of these tools to manage peanut maturity variability is still lacking. Therefore, the objective of this study was to compare and validate linear and multiple linear regression with models using artificial neural networks (ANN) for estimating peanut maturity under irrigated and rainfed conditions. The models were trained (80% dataset) and tested (20% dataset) using results from the 2018 and 2019 growing seasons from irrigated and rainfed fields. In each field, plant reflectance was collected weekly from 90 days after planting using a UAV-mounted multispectral camera. Images were used to develop vegetation indices (VIs). Peanut pods were collected on the same dates as the UAV flights for maturity assessment using the peanut maturity index (PMI). The precision and accuracy of the linear models to estimate PMI using VIs were, in general, greater in irrigated fields with R² > 0.40 than in rainfed areas, which had a maximum R² value of 0.21. Multiple linear regressions combining adjusted growing degree days (aGDD) and VIs resulted in decreased RMSE for both irrigated and rainfed conditions and increased R² in irrigated areas. However, these models did not perform successfully in the test process. On the other hand, ANN models that included VIs and aGDD showed accuracy of R² = 0.91 in irrigated areas, regardless of using Multilayer Perceptron (MLP; RMSE = 0.062) or Radial Basis Function (RBF; RMSE = 0.065), as well as low tendency (1:1 line). These results indicated that, regardless of the ANN architecture used to predict complex and non-linear variables, peanut maturity can be estimated accurately through models with multiple inputs using VIs and aGDD. Although the accuracy of the MLP or RBF models for irrigated and rainfed areas separately was high, the overall ANN models using both irrigated and rainfed areas can be used to predict peanut maturity with the same precision.

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.

Estimating cotton fiber quality early in the season, or its field variability, is impractical due to limitations in current methods, and it has not been widely explored. Similarly, few studies have tried estimating the parameters contributing to in-season cotton yield using UAV-based sensors. Thus, this study aims to explore the potential of using UAV-based multispectral images to estimate important in-season parameters, such as intercepted photosynthetically active radiation (IPAR), cotton height, the number of mainstem nodes, leaf area index (LAI), and end-of-the-season yield and cotton fiber quality parameters. Research trials were carried out in 2018 and 2020 in two experimental fields. In both years, a randomized complete block design was used with three cotton cultivars (2018), three plant growth regulators (2020), and three different irrigation levels to promote variability (both years). Cotton growth parameters were collected throughout the season on the same dates as UAV flights. Yield and fiber quality data were collected during harvest. The VI-based models used in this study were mostly sensitive to differences in cotton growth and final yield but less sensitive in detecting variation in cotton fiber quality indicators, such as length, strength, and micronaire, early in the season. The best performing regression model among the three fiber quality indicators was achieved in 2020, using a combination of four VIs, which explained 68% of the micronaire variability at 71 DAP. Results from this study also showed that multispectral-based VIs can be applied as early as the squaring stage at around 44 DAP to estimate most cotton growth indicators and final lint yield. Multiple linear regression validation models for height using NDVI, GNDVI, and RDVI obtained an R² of 0.62, and for LAI using MSR and NDVI an R² of 0.60. For lint yield, the best regression model combined four VIs and explained 66% of the yield variability. The ability to capture the variability in important growth and yield parameters early in the season can provide useful insights on potential crop performance and aid in in-season decisions.

Remotely sensed-based surface temperature is an important tool for crop monitoring and has great potential for improving irrigation management. However, current thermal satellite platforms do not display the fine spatial resolution required for identifying crop water status patterns at the field scale. The thermal sharpening (TsHARP) utility provides a technique for downscaling coarse thermal images to match the finer resolution of images acquired in the visible and near infrared bandwidths. This sharpening method is based on the inverse linear relationship between vegetation fraction calculated from the normalized difference vegetation index (NDVI) and land surface temperature (LST). The current study used the TsHARP method to sharpen low-resolution thermal data from the Moderate Resolution Imaging Spectrometer MODIS (1 km) to the finer resolution of Sentinel-2 (10 m) and Vegetation and Environment New micro-Spacecraft (VENµS) (5 m) visible-near infrared images. The sharpening methodology was evaluated at scene and field scales in southern Georgia and northern Mississippi, USA. A comparison of sharpened temperature was made with reference temperatures from Landsat-8 Operational Land Imager (OLI) in four different spatial resolutions (30, 60, 120, and 240 m) for method validation. Coarse resolution comparison on the dates in which imagery from both sensors were acquired on the same day resulted in average observed mean absolute error (MAE) of 1.63 °C, and R² variation from 0.34 to 0.74. Temperature errors at the field scale ranged from 0.25 to 3.11 °C using both Sentinel-2 and VENµS. Sharpened maps at 120 and 60 m resolution showed the highest consistency for all fields and dates. Maps sharpened using VENµS images showed comparable or higher accuracy than maps sharpened using Sentinel-2. The superior performance coupled with the better revisit time indicates that the VENµS platform has high potential for frequent in-season crop monitoring. Further research with ground data collection is needed to explore field use limitations of this methodology, but these results give useful insights of potential benefits of implementing the TsHARP technique as a tool for crop stress monitoring.