Framework For Building Recommender Engine to Forecast Mangifera Indica Foliar Pathogens

Abstract

In Asia, there are many different types of horticulture farming. The fifth-most economically significant tropical fruit in the world is the mango (Mangifera indica L.). The mango fruit is consumed as a fresh fruit, in juices and beverages, jams, and other foods because of its distinctive flavour and nutritional content. Mangoes are grown in more than 90 countries, with Asia producing 75% of all mangoes worldwide. There are numerous different mango species, and each has an own commercial market. Yet, a variety of illnesses have a direct impact on the quantity and quality of fruit. The primary global constraint on mango output is diseases brought on by pathogenic fungus. The most significant diseases in India include stem-end rot (Lasiodiplodia spp. and Neofusicoccum spp.), powdery mildew (Pseudoidium anacardii), anthracnose (Colletotrichum spp.), mango deformation disease (Fusarium spp.), and grey leaf spot (Pestalotiopsis mangiferae). This research study's main goal was to use machine learning techniques to analyse leaves in order to forecast future leaf diseases. The framework for developing a recommender engine to predict leave diseases is presented in this research. It gathers information from a live test site in Western Gatz, India, and builds an expert model using the proper knowledge representation approaches. A knowledge-based recommendation engine is created for mango disease forecasting and pre-treatment as a result of this research.