Neural Network based Ensemble Learning Model for Elevating Wheat Disease Classification

Detecting a disease visually is a time-consuming and error-prone operation, and in the agricultural arena, for disease control, crop yield loss prediction, and global food security, automatic and accurate evaluation of disease severity in crops is a particularly demanding study area. Deep Learning (DL), the latest innovation in the era of Artificial Intelligence (AI), is promising for fine-grained categorization of crop diseases since it eliminates labor-intensive feature extraction and segmentation. To diagnose the disease from photos, multiple pretrained models which are ResNet50, EfficientNetB0 and InceptionV3 along with Vision Transformer (ViT) and a hybrid Convolutional Neural Network (CNN) model have been trained on the wheat disease dataset. Again, an ensemble model of the hybrid CNN and the ViT has been proposed which has been compared with all the other models and the proposed model elevates the accuracy to 99.34%, which is the highest among all the accuracies of other models.

I. Introduction

During the period from 1971 to 1975, the rice price was increasing globally, which caused food shortages in Bangladesh. In addition, Bangladesh was already lagging behind in food production due to the Liberation War along with natural disasters and population growth. It was then decided rice alone could not fulfill the nation’s food demand, and wheat was chosen as an alternative winter crop. Since then wheat has been growing in popularity in Bangladesh, but climate change has a significant impact on Bangladesh and so the likelihood of growing wheat and potatoes would be substantially hampered by a shift in the average temperature of 2-4 °C, and output loss may surpass 60% of the possible yields [1]. Wheat consumption in 2021 has seen twice as much demand as in 2015 according to [2]. The reasons behind this are the good quality flour being cheaper than medium quality rice, the increase of the obese and diabetic patients, and the rise in the popularity of bakery products such as biscuits and cakes. However, the production of wheat hasn’t been able to keep up with the demand of the ever-growing population [3]. On the other hand, global food demand has been increasing from COVID-19 and the Russia-Ukraine war has further increased that [4]. Almost 90% of wheat and other grains are shipped from Ukraine, the "breadbasket of the world" but due to the war, the crops could not leave Ukraine. Thus, the global wheat demand is increasing. In addition, the crop fields that were destroyed during the war will not get the people food in the next harvesting season, which will increase the global food shortage even more.