Applications of the remote sensing technology to detect and monitor the rust disease in the wheat – a literature review

The wheat production loss induced by rust pathogens is huge per annum globally. Those pathogens cause substantial fungal diseases of the wheat. Therefore, it is significant to be curbed on a global scale. Wheat rust early detection would improve wheat yield and its quality traits. In this paper, a review was accomplished to demonstrate the necessity for reliable health condition monitoring of the wheat at ground-based, airborne and spaceborne scales applying remotely sensed sensors and techniques. Several deep learning algorithms integrating with spectral data could promisingly detect wheat leaf rust infection at ground-based and field scales. Multispectral and hyperspectral sensors also indicated sound capabilities in the discrimination of wheat rust infection using machine learning algorithms such as SVM. Furthermore, a weather-based model comprising the combination of meteorological data with machine learning techniques represented a great potential for wheat rust early detection.