Analysis Of Areca Nut Leaf Pathology And Recommendation System Using Generative AI

In tropical regions where areca nut leaf agriculture has a substantial impact on economic and cultural elements, this research explores the essential topic of areca nut leaf disease identification and prognosis. The goal is to solve the problems caused by several diseases that could endanger the productivity and quality of areca nut leaf production, requiring creative solutions that go beyond conventional practices. To determine which model is best for disease detection and prognosis, the proposed methodology compares four models: Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), ResNet20, and ResNet44. The paper shows ways to inhibit or treat the condition by combining the model which has highest accuracy, ResNet44, an accuracy of $97.11 \%$, with a Long Short-Term Memory (LLM) model. The goal is to improve the predicted accuracy of disease monitoring models by implementing data fusion approaches that combine soil conditions and meteorological data. The results show that ResNet44 performed the best, with an accuracy of $97.11 \%$, indicating that it is useful for identifying and treating diseases. The model also included a chatbot to help farmers communicate and get their questions answered, emphasizing the value of intuitive user interfaces in disease control. This strategy not only gives farmers the information and resources they need to reduce losses and increase crop resilience, but it also encourages long-term viability by using eco-friendly solutions. The multimodal strategy, which strikes a balance between technological innovation, community involvement, and governmental support, emphasizes the importance of a comprehensive plan for the identification and prediction of areca nut sickness.