Artificial Neural Network Assisted Weather Based Plant Disease Forecasting System

Abstract

An interactive plant disease forecasting system was developed using Artificial Neural Network model with multilayer perceptron architecture having two hidden layers. When data from the same site are used for both training and testing, the prediction accuracy of the model was found to be between 81-87% for rice blast disease. Being a multivariate non-linear non-parametric data driven self adaptive statistical method, it shows significantly higher accuracy then the conventional regression based models.
DOI: 10.17762/ijritcc2321-8169.1506136