A Deep Learning Model for Identification of Yellow Wheat Rust

Abstract

Wheat (Triticum aestivum L.) is a vital staple food in many cropping systems worldwide. It is grown in various nations, including Pakistan. Wheat is subject to different biotic and abiotic challenges. Rust is one of the most significant biotic constraints that appears almost every year in our country. Among the rusts, yellow wheat rust is caused by Puccinia striiformis f.sp. tritici and is geographically widespread. It damages all the major wheat-producing areas, causing significant losses to wheat crop quality and yield. Disease symptom detection needs to be performed at an early stage in order to improve wheat productivity. In the last few years, deep learning has provided significant breakthroughs in image processing. This research aims to develop a deep learning approach-based model for the automatic detection and classification of yellow wheat rust. The model harnessed the power of Convolutional Neural Networks (CNNs), which enables the system to learn various features from pictures of wheat rust without exhaustive programming.