CNNRF-Ensemble: A Multifaced Approach For Predicting White Spot Syndrome Virus In Shrimp Farming

Shrimp farming has traditionally served as a crucial source of seafood and revenue for coastal countries, filling the rapid growth demand, especially in Bangladesh. However, the White Spot Syndrome Virus(WSSV) creates and constantly threatens the global shrimp population, impacting the economic and ecological systems. Recently, researchers have tried to predict disease, but no studies have achieved significant accuracy using ML and DL algorithms. In this study, we have proposed an optimized CNNRF-Ensemble model for predicting WSSV using multifaceted data, including geographical features, environmental attributes, farm characteristics, operational practices, and socioeconomic indicators. Our proposed model achieved 95.714% accuracy in sequential model and afterwards, combining with RandomForestClassifier in Ensemble learning we obtained 99.99% accuracy. Our study suggested deep learning as an accurate, easy and low-cost method to predict shrimp WSSV, which helps to predict viruses and create awareness of shrimp firming.