Machine learning on chlorophyll flouresence and finger millet images infected by blast disease Eastern Africa
Finger millet is one among the small grain millets which is an important food and income source for most of the people in the rural and semi-arid areas in eastern Africa. Most of the farmers use unimproved varieties which are vulnerable to biotic and abiotic stresses. Finger millet blast disease, caused by the filamentous oomycete fungus M. oryzae, accounts for up to 90% of yield losses experienced in combination with other abiotic stresses. Artificial intelligence (AI) techniques like machine learning and deep learning have transformed agriculture into "smart" agriculture by enabling the development of effective early crop disease detection tools. These methods can accurately and quickly identify crop diseases because they are fully automated. Smart agriculture has been adopted in recent years to increase yield.
By utilizing Chl-F and analyzing images of finger millet, this project advances knowledge on the application of AI techniques which aids in the early detection of blast disease in finger millet.