A Hybrid Model For Severity Prediction Of Leaf Smut Rice Infection

Computer Engineering,

Plant diseases have a profound impact on agricultural productivity, necessitating advanced predictive models for timely intervention. This study presents a novel approach for the severity prediction of leaf smut rice infection, leveraging a hybrid model combining deep learning techniques. Utilizing time series data sourced from relevant agricultural databases, the proposed model integrates features extraction and fusion methods to enhance predictive accuracy. Specifically, CNN algorithm is employed for its efficacy in capturing temporal dependencies and patterns in the data. Through comparative analysis, our results demonstrate the superiority of the hybrid model in accurately predicting the severity of leaf smut rice infection. This research contributes to agricultural sustainability by offering a reliable tool for early disease detection and management.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.