The objective of this study is to evaluate the water conditions in a coffee plantation using precision agriculture (PA) techniques associated with geostatistics and high-resolution images. The study area is 1.2 ha of coffee crops of the Topázio MG 1190 cultivar. Two data collections were performed: one in the dry season and one in the rainy season. A total of 30 plants were marked and georeferenced within the study area. High-resolution images were obtained using a remotely piloted aircraft (RPA) equipped with a multispectral sensor. Leaf water potential was obtained using a Scholander pump. The spatialization and interpolation of the leaf water potential data were performed by geostatistical analysis. The vegetation indices were calculated through the images obtained by the RPA and were used for a regression and correlation analysis, together with the water potential data. The degree of spatial dependence (DSD) obtained by the geostatistical data showed strong spatial dependence for both periods evaluated. In the correlation analysis and linear regression, only the red band showed a significant correlation (39.93%) with an R² of 15.95%. The geostatistical analysis was an important tool for the spatialization of the water potential variable; conversely, the use of vegetation indexes obtained by the RPA was not as efficient in the evaluation of the water conditions of the coffee plants.

Neste estudo objetivou-se identificar comprimentos de onda e faixas espectrais provenientes de reflectâncias hiper e multiespectrais utilizando regressão PLS e promover avaliação comparativa desses métodos e de dez índices de vegetação, para determinar aqueles que melhor estimam níveis de severidade de mofo-branco em feijão. Foram implantados experimentos nos municípios de Viçosa e de Oratórios, estado de Minas Gerais. Reflectâncias hiperespectrais foram obtidas com espectroradiômetro cuja faixa útil de leitura adotada foi entre 440 e 900 nm. Reflectâncias multiespectrais foram obtidas de imagens de câmara constituídas de cinco bandas (vermelho, verde, azul, Red-edge e infravermelho). Os índices de severidade da doença foram baixos; em Viçosa a média foi de 5,8% e em Oratórios, 7,4%. Modelos matemáticos utilizando reflectâncias hiperespectrais tiveram melhor desempenho para estimar mofo-branco; a banda do red-edge apresentou os comprimentos de onda que melhor estimam a severidade do mofo-branco. Índices de vegetação resistentes a efeitos da reflectância de solo estimaram melhor o mofo-branco do que os demais índices.

The integration of machine learning (ML) techniques with unmanned aerial vehicle (UAV) imagery holds strong potential for improving yield prediction in agriculture. However, few studies have combined biophysical field variables with UAV-derived spectral data, particularly under conditions of limited sample size. This study evaluated the performance of different ML algorithms in predicting Arabica coffee (Coffea arabica) yield using field-based biophysical measurements and spectral variables extracted from multispectral UAV imagery. The research was conducted over two crop seasons (2020/2021 and 2021/2022) in a 1.2-hectare experimental plot in southeastern Brazil. Three modeling scenarios were tested with Random Forest, Gradient Boosting, K-Nearest Neighbors, Multilayer Perceptron, and Decision Tree algorithms, using Leave-One-Out cross-validation. Results varied considerably across seasons and scenarios. KNN performed best with raw data, while Gradient Boosting was more stable after variable selection and synthetic data augmentation with SMOTE. Nevertheless, limitations such as small sample size, seasonal variability, and overfitting, particularly with synthetic data, affected overall performance. Despite these challenges, this study demonstrates that integrating UAV-derived spectral data with ML can support yield estimation, especially when variable selection and phenological context are carefully addressed.

This study aimed to identify wavelengths based on leaf reflectance (400-1050 nm) to estimate white mold severity in common beans at different seasons. Two experiments were carried out, one during fall and another in winter. Partial Least Squares (PLS) regression was used to establish a set of wavelengths that better estimates the disease severity at a specific date. Therefore, observations were previously divided in two sub-groups. The first one (calibration) was used for model building and the second subgroup for model testing. Error measurements and correlation between measured and predicted values of disease severity index were employed to provide the best wavelengths in both seasons. The average indexes of each experiment were of 5.8% and 7.4%, which is considered low. Spectral bands ranged between blue and green, green and red, and red and infrared, being most sensitive for disease estimation. Beyond the transition ranges, other spectral regions also presented wavelengths with potential to determine the disease severity, such as red, green, and near infrared.

The identification of stress conditions in soybean crops is, in most cases, inaccurate, since they may not be noticeable to their full extent if only walking observations are carried out in the crop fields. This study aimed to identify the stress conditions in soybean crops, in three growing environments, in the Minas Gerais state, Brazil, using image processing techniques obtained by UAV, leaf and soil sensors, and climate data. The surveys encompassed two growth stages [beginning of blooming (R1) and beginning of seed enlargement (R5)] and consisted on UAV flights; mapping of chlorophyll content, soil moisture and soil pH; in addition to climate data. The HSV and yCbCr color models applied to RGB images showed the best Kappa accuracy index for the identification of crop features. The soil pH and moisture (water availability), solar radiation and temperature affected the crop growth and development in the study regions, in the R1 and R5 reproductive stages. However, the soil pH had less influence than the climatic variables. The R5 stage showed a greater vulnerability to stress caused by soil moisture and temperature.

Remotely piloted aircraft (RPA) are essential in precision coffee farming due to their capability for continuous monitoring, rapid data acquisition, operational flexibility at various altitudes and resolutions, and adaptability to diverse terrain conditions. This study evaluated the soil water conditions in a coffee plantation using remotely piloted aircraft to obtain multispectral images and vegetation indices. Fifteen vegetation indices were chosen to evaluate the vigor, water stress, and health of the crop. Soil samples were collected to measure gravimetric and volumetric moisture at depths of 0–10 cm and 10–20 cm. Data were collected at thirty georeferenced sampling points within a 1.2 ha area using GNSS RTK during the dry season (August 2020) and the rainy season (January 2021). The highest correlation (51.57%) was observed between the green spectral band and the 0–10 cm volumetric moisture in the dry season. Geostatistical analysis was applied to map the spatial variability of soil moisture, and the correlation between vegetation indices and soil moisture was evaluated. The results revealed a strong spatial dependence of soil moisture and significant correlations between vegetation indices and soil moisture, highlighting the effectiveness of RPA and geostatistics in assessing water conditions in coffee plantations. In addition to soil moisture, vegetation indices provided information about plant vigor, water stress, and general crop health.