Enhanced Dengue Outbreak Prediction in Tamilnadu using Meteorological and Entomological data

TL;DR

This study enhances dengue outbreak prediction in Tamil Nadu by integrating meteorological and entomological data using a Bidirectional Stacked LSTM model, significantly improving prediction accuracy.

Contribution

Introduces a Bidirectional Stacked LSTM model that combines climate and mosquito larval data for improved dengue prediction accuracy.

Findings

Prediction accuracy improved with mosquito larval index inclusion

Bidirectional Stacked LSTM outperforms other models

Climate and entomological data integration enhances outbreak forecasting

Abstract

This paper focuses on studying the impact of climate data and vector larval indices on dengue outbreak. After a comparative study of the various LSTM models, Bidirectional Stacked LSTM network is selected to analyze the time series climate data and health data collected for the state of Tamil Nadu (India), for the period 2014 to 2020. Prediction accuracy of the model is significantly improved by including the mosquito larval index, an indication of VBD control measure.