Vidarbha Region Crops: Cotton, Soyabean and Maize Disease Detection using Modified Autoencoder

Every nation’s economy depends heavily on agriculture and India is recognized as an agro-based country. To produce healthy crops with free of disease is one of the primary goals of agriculture. The soil and water resources of our vidarbha are fertile and the climate is moderate. But numerous diseases affect crop production and cause enormous crop losses, endangering the lives of helpless farmers. Manual monitoring of these plant diseases is not possible as this plants are cultivated in huge acres of land. Early detection of diseases prevents the rapid spread of disease to the whole field. This study aims to use a Deep learning (DL) model to accurately classify three leaf datasets of cotton soyabean and Maize crop leaves as either infected or healthy. This paper presents exhaustive experimental evaluations on ensemble model to tune hyper-parameters named learning rate, optimizer and no of epochs. The suggested hyper-parameter settings can be directly utilized while employing the ensemble model for disease detection and prediction. Extensive evaluations on this dataset and another public dataset demonstrate the advantage of the proposed method. Our method outperformed the state-of-the-art techniques and displayed comparatively better results. Remarkably, our approach demonstrated even higher performance than widely used ensemble techniques, generally considered benchmarks in the field.