Intelligent autonomous system for the detection and treatment of fungal diseases in arable crops

In this paper, the development phases of a ground-based real-time remote sensing system are described. The proposed system can be carried by tractors or robotic platforms. This prototype system makes possible the detection of plant diseases automatically in arable crops at an early stage of disease development, even before the diseases are visibly detectable, during field operations. The methodology uses differences in reflectance and fluorescence properties between healthy and diseased plants. Hyperspectral reflectance, fluorescence imaging, and multispectral imaging techniques were developed for simultaneous acquisition in the same canopy. New fluorescence acquisition techniques were developed, experimental platforms were constructed, and the advantage of using sensor fusion was proven. An intelligent multisensor fusion decision system based on neural networks was developed aiming at predicting the presence of diseases or plant stresses, in order to treat the diseases in a spatially variable way. A robust multi-sensor platform integrating optical sensing, GPS and a data processing unit was constructed and calibrated. The functionality of automatic disease sensing and detection devices is crucial in order to conceive a site-specific spraying strategy against fungal foliar diseases. Furthermore, field tests were carried out to optimise the functioning of the multi-sensor disease-detection device. An overview is provided on how disease presence data are processed in order to enable an automatic site-specific spraying strategy in winter wheat. Furthermore, mapping of diseases based on automated optical sensing and intelligent prediction provide a spatially variable recommendation for spraying.