Geo-Location Based Plant Disease Diagnosis with Treatment Recommendation Multilingual Chatbot

Abstract

Plant diseases significantly affect agricultural productivity by reducing crop quality, decreasing yield, and causing economic losses to farmers. Traditional disease identification methods mainly depend on manual observation, which is time-consuming and often inaccurate due to similarities between disease symptoms. Recent advancements in artificial intelligence and deep learning have improved automated plant disease detection using leaf image classification. However, most existing systems focus only on disease identification and provide limited recommendation support based on environmental conditions. To address this limitation, this research proposes a Geo-Location Based Plant Disease Diagnosis with Treatment Recommendation Multilingual Chatbot that integrates plant image analysis, geolocation data, weather monitoring, and conversational agricultural assistance into a unified framework. The proposed system accepts plant leaf images along with latitude and longitude coordinates as input from users. Deep learning algorithms are used to identify plant species and classify disease categories from uploaded images. Simultaneously, weather parameters such as temperature, humidity, rainfall, and seasonal conditions are analyzed according to the user’s geographical location. Based on the identified disease and environmental conditions, the chatbot module generates personalized treatment measures, preventive suggestions, irrigation advice, and crop maintenance recommendations. The framework considers multiple plant categories including flower plants, fruit plants, vegetable plants, and common agricultural crops with healthy and diseased leaf classes.