Cotton Disease Detection using Machine Learning Techniques for Crop Health and Yield: A Study

Abstract

Cotton is one of the most important cash crops globally, contributing significantly to the agricultural economy and textile industries.However, cotton production is often affected by various diseases such as bacterial blight, leaf curl virus, and fungal infections, which lead to substantial yield losses and reduced fiber quality.Traditionally, disease detection in cotton relies on manual observation and expert knowledge, which is time-consuming, labor-intensive, and prone to human error.Cotton is a vital cash crop whose productivity is significantly affected by various diseases.Early and accurate detection of these diseases is essential to prevent crop loss and improve yield.This study explores the application of machine learning techniques for detecting cotton leaf diseases using image processing and classification models.Various algorithms, including Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Random Forests, are evaluated for their effectiveness in identifying common cotton diseases.The study aims to assist farmers and agronomists in disease management, promoting healthier crops and improved yield through technology-driven solutions.

Plant phenotyping relevance

綿花葉の病害状態を画像から推定する機械学習手法を比較評価しており、植物病害フェノタイピングが中心的な方法論的貢献である。

Code and data availability

The article is a review-style study with no public dataset, image collection, code, model, or supplement release; no availability statements or URLs are provided, and allowed_urls is empty.

No evidence-backed public reproduction asset is currently recorded.