Work

Ai-powered Arecanut Plant Disease Diagnosis and Kannada Language Chatbot for Precision Agriculture

Year: 2026
Type: article
Abstract: Arecanut is an important plantation crop in Karnataka, and delayed recognition of plant-health problems can reduce yield and farm income.Manual inspection is subjective and time-consuming, and technical crop-health information is rarely available in the regional language.This paper presents a preliminary decision-support system that couples deep-learning image classification with a Kannada-language chatbot interface for arecanut farmers.An uploaded image is resized to 227 × 227 pixels, rescaled, and classified by a sequential convolutional neural network (CNN) with an AlexNet-style arrangement of five convolutional layers and batch normalization, trained with the Adam optimizer and rotation, zoom and horizontal-flip augmentation for 50 epochs.A Flask web application returns the predicted class with related symptom and management information and hosts the "Areca Assistant" chatbot, which answers follow-up questions in Kannada.After 50 epochs the model reached a training accuracy of 99.03% and a validation accuracy of 99.67%, and a scikit-learn classification report on 8,143 evaluation samples gave macro-averaged precision, recall and F1-score of 0.98, 0.99 and 0.98.The labelled data span several crops, and an independent test set, field trials and a quantitative chatbot evaluation remain to be carried out.The main contribution is the integration of image-based screening and regional-language assistance in a single workflow that can support smallholder arecanut growers in early disease awareness.
Source: IJARCCE
Language: English
Subfield: Plant Science
Open Access status: diamond
OpenAlex ID: W7236034028
FWCI:
Cites: 13
Cited by:
Related to: 10