Disease Identification and Mapping using CNN in Paddy Fields

Abstract

Rice, a globally vital staple crop, sustains over half of the world’s caloric needs while supporting the livelihoods of small-scale farmers and landless laborers. The escalating global population has led to an increased demand for rice production. Sri Lanka, renowned for its premium rice quality, has a rich history of paddy cultivation. However, a substantial portion of the country’s 708,000 hectares of paddy land remains underutilized due to water scarcity and unstable terrain. The objective of this project is to enhance paddy crop quality during the critical vegetative phase by employing machine learning and web development for early disease identification. The vegetative phase significantly influences overall yield, resistance to pests and diseases, nutrient assimilation, and environmental sustainability in agriculture. This project primarily focuses on early disease identification during this phase and presents the findings through a user-friendly map interface. Early identification of paddy diseases is vital for effective crop management and high yields. These diseases, caused by various pathogens, can severely impede plant growth and productivity if not promptly detected and treated. Identifying them early enables farmers and experts to take timely, targeted actions such as applying suitable fungicides or implementing cultural practices to control their spread and minimize crop damage. A logical map, displaying disease spread percentages, will gauge the impact of infections on paddy plants. The reliability of this mapping process hinges on model accuracy, which was rigorously validated using multiple metrics to ensure its effectiveness.