The coffee crops are exposed to different pathogens that directly affect yield. These include nematodes, which attack the roots of plants and compromise their physiological development. Given the losses caused by this pathogen and the lack of information on spatial distribution in infested areas, it is important to adopt technologies that enable crops under different management systems to be monitored during their growth cycle. The remote sensing associated with machine learning algorithms is presented as a potential tool for monitoring agricultural crops. The present study assesses different machine learning algorithms, using radiometric values of multispectral images as input datasets, and identifies the best algorithms, to estimate the physiological agronomic parameters in coffee crops submitted to 11 treatments for nematode management. Based on the association between the images taken by a low-cost camera (bands: (R) red, (G) green and (B) blue) mounted on a remotely piloted aircraft (RPA), machine learning algorithms (Random Forest (RF) and support-vector machines (SVM)), the results made it possible to estimate with satisfactory accuracy (root mean square error (RMSE) less than 26.5% the main physical parameters of coffee plants: chlorophyll, plant height, branch length, number of branches and number of nodes per branch. With Planet satellite-derived multispectral bands, the SVM algorithm estimated plant canopy diameters with an RMSE of 7.74%. Based on the spatial distribution maps of the physical parameters, the application machine learning methods offered an opportunity to better use remote sensing data for monitoring coffee crop growth conditions and accurately guiding several management techniques.

咖啡作物暴露于直接影响产量的不同病原体。其中包括线虫，它们攻击植物的根部并损害其生理发育。鉴于这种病原体造成的损失以及缺乏有关受侵染地区空间分布的信息，采用能够在不同管理系统下监测作物生长周期的技术非常重要。与机器学习算法相关的遥感被认为是监测农作物的潜在工具。本研究评估不同的机器学习算法，使用多光谱图像的辐射值作为输入数据集，并确定最佳算法，以估计提交 11 种线虫管理处理的咖啡作物的生理农艺参数。