Different stages of disease detection in squash plant based on machine learning

To increase agriculture production, accurate and fast detection of plant disease is required. Expert advice is needed to detect disease in plants, nutrition deficiencies or any other abnormalities caused by extreme weather conditions. But this process is very tedious, costly, and takes more time. In this paper, hyperspectral imaging and machine learning were used to detect different stages (early, middle, and critical stage) of the powderly mildew disease (PMD) in squash plants. An unmanned aerial vehicle (UAV) was used to collect the data from the field and Locality Preserving Discriminative Broad Learning (LPDBL) was used to distinguish the diseased and healthy plants. In addition, the ability to detect the diseased plant by the proposed method was evaluated using 10 different spectral vegetation indices (VIs). The results show the proposed method detected the disease accurately in the early, middle, and critical stages of the squash plant. The proposed method's performance is compared with six different PMDs under indoor laboratory test and UAV-based field test conditions. The comparison's results show that the LPDBL provides better accuracy in detecting disease in the squash plant.