Integrating Ultraviolet and Solar Radiation Monitoring Data with an MMS-GRU Framework for Multi-Scale Dengue Forecasting
- 1Department of Industrial Engineering and Management, National Chin-Yi University of Technology, Taichung 411030, Taiwan
- 2International Master Program in Smart Manufacturing and Applied Information Science, National Chin-Yi University of Technology, Taichung 411030, Taiwan
Abstract
Dengue fever continues to expand across tropical and subtropical regions, straining public health surveillance systems, partly because dengue time series exhibit non-stationarity, multi-periodic structure, and climatic drivers that vary geographically. This study proposes MMS-GRU, a hybrid multi-scale framework that decomposes dengue and climate series using the Maximal Overlap Discrete Wavelet Transform (MODWT) to separate seasonal trends from short-term dynamics, applies a two-stage Lasso–SHAP procedure to select informative climate predictors, and feeds each frequency component into a Stacked Bidirectional Gated Recurrent Unit (SBi-GRU) to capture temporal dependencies. The framework was evaluated at three endemic sites (Iquitos, San Juan, and the Philippines) over 13-, 26-, and 52-week horizons, using conventional climate records and, for the Philippines, satellite-derived NASA POWER variables. MODWT produced lower errors than EEMD and CEEMDAN at all three sites, whereas the benefit of feature selection varied with site, horizon, and architecture, and UV index and solar radiation variables ranked among the most influential inputs for the Philippines. These findings indicate that combining multi-scale decomposition with interpretable feature selection is a promising basis for dengue forecasting, although repeated runs and comparison with simple benchmarks under a common protocol are needed before the framework can support vector control planning.
Related
- A Multi-Criteria Geostatistical Framework Integrating Centrality Measures and Satellite Validation for PM2.5 Monitoring Network Expansion in Upper Northern Thailand
- A hybrid approach for steady-state production optimization of a real oil and gas platform: Integrating physics-based models, machine learning techniques, and field monitoring signals
- An improved ratio-cum-exponential estimator for finite population mean with properties: Applications to radiation monitoring and economic management data
- Hankel-Koopman Finite-Horizon Energy Decomposition of Coupled Experimental Data: A Three-Phase Data-Driven Twin Forecasting Framework
- Learning Kolmogorov Backward Operators for Spectral Analysis and Forecasting: A Data-Driven Variational Galerkin Framework
BibTeX
@article{huang2026integrating,
title = {{Integrating Ultraviolet and Solar Radiation Monitoring Data with an MMS-GRU Framework for Multi-Scale Dengue Forecasting}},
author = {Mei-Ling Huang and Netnapha Chamnisampan and Yu-Fang Huang},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14213974},
url = {https://www.mdpi.com/2227-7390/14/21/3974},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Integrating Ultraviolet and Solar Radiation Monitoring Data with an MMS-GRU Framework for Multi-Scale Dengue Forecasting
AU - Mei-Ling Huang
AU - Netnapha Chamnisampan
AU - Yu-Fang Huang
PY - 2026
DA - 2026/10/31
JO - Mathematics
DO - 10.3390/math14213974
UR - https://www.mdpi.com/2227-7390/14/21/3974
AB - Dengue fever continues to expand across tropical and subtropical regions, straining public health surveillance systems, partly because dengue time series exhibit non-stationarity, multi-periodic structure, and climatic drivers that vary geographically. This study proposes MMS-GRU, a hybrid multi-scale framework that decomposes dengue and climate series using the Maximal Overlap Discrete Wavelet Transform (MODWT) to separate seasonal trends from short-term dynamics, applies a two-stage Lasso–SHAP procedure to select informative climate predictors, and feeds each frequency component into a Stacked Bidirectional Gated Recurrent Unit (SBi-GRU) to capture temporal dependencies. The framework was evaluated at three endemic sites (Iquitos, San Juan, and the Philippines) over 13-, 26-, and 52-week horizons, using conventional climate records and, for the Philippines, satellite-derived NASA POWER variables. MODWT produced lower errors than EEMD and CEEMDAN at all three sites, whereas the benefit of feature selection varied with site, horizon, and architecture, and UV index and solar radiation variables ranked among the most influential inputs for the Philippines. These findings indicate that combining multi-scale decomposition with interpretable feature selection is a promising basis for dengue forecasting, although repeated runs and comparison with simple benchmarks under a common protocol are needed before the framework can support vector control planning.
SN - 2227-7390
ER -