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.

The beneficial effects of silicon (Si) on plants have been widely reported for its fruit qualitative improvements, growth gains, and protection against abiotic and biotic stresses. This study aimed to evaluate the combined effect of soil water potential (Ψs) (−30 and −60 kPa) and the foliar application of Si (0.0 (control), 1.0, 2.0, 3.0, and 4.0 g L⁻¹) in the development of tomatoes grown in a greenhouse. We evaluated the biometric parameters and gas exchange in three periods (20, 34, and 48 days after planting). The rates of transpiration (E), stomatal conductance (gs), and net photosynthesis assimilation (A_n) were lower when the plants were subjected to water deficit. The foliar application of Si attenuated the effect of the water deficit in both levels applied to the crop. A high response was observed at −60 kPa, regardless of the evaluated period. However, a significant effect was not observed on the relative chlorophyll index and biomass accumulation when Si was applied. A foliar application up to 2.8 g L⁻¹ promotes increases in A_n,gs, and E. It is highlighted that Si can promote improvements in gas exchange when plants are affected by a water deficit.

Precision irrigation is essential to improve water use efficiency (WUE), defined as the amount of biomass produced per unit of water used by plants. Our objective is to evaluate the effect of different soil volumetric water content (VWC) in plant growth, fruit yield, quality, and WUE of cherry tomatoes grown in a greenhouse. We tested four VWC thresholds (0.23, 0.30, 0.37, and 0.44 m³ m⁻³) to trigger a drip irrigation system in two tomato cultivars (‘Sweet Heaven’ and ‘Mascot F1’). The experiment was arranged in a split-plot design with four replications. We used capacitance sensors connected to an open-source, low-cost platform to monitor and control the irrigation in real-time based on demand. Plants were watered every time the soil VWC dropped below the set thresholds. The treatment with VWC 0.44 m³ m⁻³ resulted in the highest fruit yield, with 102.10% higher WUE when compared to the VWC 0.23 m³ m⁻³ in both cultivars. Fruit quality traits such as longitudinal and equatorial diameter increased asymptotically with soil water content. In contrast, treatments with deficit irrigation increased the fruit soluble solids by 15.73% in both cultivars. These results strongly suggest that accurate control of the soil VWC is essential to modulate the fruit yield and quality attributes in tomatoes produced in the greenhouse.

The objective of this study was to develop and calibrate a photovoltaic-powered soil moisture sensor (SMS) for irrigation management. Soil moisture readings obtained from the sensor were compared with gravimetric measurements. An automated SMS was used in two trials: (i) okra crop (Abelmoschus esculentus) and (ii) chili pepper (Capsicum frutescens). All sensors were calibrated and automated using an Arduino Mega board with C++. The soil moisture data were subjected to descriptive statistical analysis. The data recorded by the equipment was correlated with the gravimetric method. The determination coefficient (R²), Pearson correlation (r), and root mean square error (RMSE) were adopted as criteria for equipment validation. The results show that our SMS achieved an R² value of 0.70 and an r value of 0.84. Notably, there was a striking similarity observed between SMS and gravimetric data, with RMSE values of 3.95 and 4.01, respectively. The global model developed exhibited highly efficient outcomes with R² (0.98) and r (0.99) values. The applicability of the developed SMS facilitates irrigation management with accuracy and real-time monitoring using digital data. The automation of the SMS emerges as a real-time and precise alternative for performing irrigation at the right moment and in the correct amount, thus avoiding water losses.

A uniformidade de aplicação de água é um importante fator a ser considerado na avaliação dos sistemas de irrigação por aspersão. A uniformidade em sistemas convencionais de aspersão depende de fatores como: o tipo de aspersor e suas condições operacionais, a disposição e o espaçamento entre aspersores no campo, e a velocidade e a direção do vento durante o período de aplicação de água. Tendo em visa que as complexas relações entre esses fatores e a uniformidade podem ser caracterizadas de forma mais eficiente com o auxílio da modelagem matemática, neste estudo, foram avaliadas simulações, fornecidas pelo modelo semiempírico de RICHARDS & WEATHERHEAD (1993), da distribuição espacial da água aplicada pelo canhão PLONA-RL250, operando sob diferentes condições de vento. Valores de uniformidade de Christiansen (CUC), obtidos com dados de ensaios de campo e em simulações digitais, foram comparados, mostrando-se, por meio de diversos índices (R² = 0,73; desvio absoluto médio de 4,1% e índice de desempenho de 0,78), que o modelo semiempírico avaliado fornece estimativas adequadas do CUC de sistemas convencionais de irrigação. Demonstra-se que a modelagem matemática permite reduzir o esforço e o tempo requeridos em trabalhos de campo envolvendo a avaliação da distribuição de água de canhões hidráulicos operando sob condições de vento.

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.