Remotely piloted aircraft system and machine learning for detection of coffee plants subjected to foliar application of chitosan

Considered a biostimulant, chitosan can affect the physiological responses of plants to waterdeficit, acting as an antitranspirant under agricultural stress. Currently, images obtained byRemotely Piloted Aircraft Systems (RPAS), together with machine learning techniques, aid inresolving agricultural problems, including water issues. Therefore, the objective of this studywas to differentiate between coffee plants subjected to the foliar application of chitosan andthose not subjected to it, based on spectral data extracted from RPAS-acquired images andclassification via machine learning. For this purpose, the random forest (RF) classifier wasapplied to two coffee cultivars (Catucaí Amarelo 2SL and Catuaí Vermelho IAC 99) over twoyears of study (2021 and 2022). The images were obtained by a 3DR SOLO aircraft with a ParrotSequoia sensor, processed in PIX4D Mapper software and analysed in QGIS and RStudiosoftware. The results showed good performance metrics for differentiating between coffeeplants subjected and not subjected to the foliar application of chitosan, indicating that thismethod is a valid approach for modelling the presence of the biostimulant in coffee plants,thus confirming that the model can efficiently support the practices of precision agriculture.