Machine Learning Models for Dengue Forecasting in Singapore

TL;DR

This paper compares various machine learning models, including traditional, supervised, and deep learning techniques, for forecasting weekly dengue cases in Singapore, highlighting CNNs' superior performance with meteorological and search trend data.

Contribution

It systematically evaluates multiple ML models for dengue forecasting and demonstrates the effectiveness of CNNs with combined meteorological and search trend features.

Findings

CNNs achieved the lowest RMSE in 2019 forecasts.

Deep learning models outperform traditional statistical models.

Inclusion of search engine trends improves forecast accuracy.

Abstract

With emerging prevalence beyond traditionally endemic regions, the global burden of dengue disease is forecasted to be one of the fastest growing. With limited direct treatment or vaccination currently available, prevention through vector control is widely believed to be the most effective form of managing outbreaks. This study examines traditional state space models (moving average, autoregressive, ARIMA, SARIMA), supervised learning techniques (XGBoost, SVM, KNN) and deep networks (LSTM, CNN, ConvLSTM) for forecasting weekly dengue cases in Singapore. Meteorological data and search engine trends were included as features for ML techniques. Forecasts using CNNs yielded lowest RMSE in weekly cases in 2019.