Research Article
Bayesian Geospatial Calibration of Reinforcement Learning for Malaria Transmission Control: Parameter Estimation
Kipngetich Gideon*
,
Victor Muthama Musau,
Margaret Wambui Kinyua
Issue:
Volume 12, Issue 2, April 2026
Pages:
17-24
Received:
18 April 2026
Accepted:
3 May 2026
Published:
10 June 2026
DOI:
10.11648/j.ijdsa.20261202.11
Downloads:
Views:
Abstract: Malaria has been one of the major public health issues that has not been extensively addressed. Controlling the spread of infectious diseases in space and time requires robust adaptive policies that significantly account for heterogeneity, uncertainty, and optimal sequential decision-making. This study presents an innovative framework that integrates Bayesian spatiotemporal modeling with reinforcement learning (RL) with the 5D3 algorithm. The disease risk at location i and time t is modeled using a logistic regression with spatial random effects and Bayesian inference performed using the non-reversible Metropolis-Hastings algorithm, and the parameter estimates are used to calibrate a stochastic reinforcement learning environment via episodic parameter sampling. The study identified significant drivers of malaria risk: rainfall, temperature, secondary and tertiary levels of education, higher wealth index, female gender, treated nets, and spray repellents, while quantifying uncertainty via credible intervals. The spatial random effect captured unmeasured local heterogeneity, and the temporal effect accounted for seasonality, which is essential for reliable parameter estimation. Therefore, a reinforcement learning agent can learn optimal, spatially adaptive intervention policies under uncertainty, making the model suitable for public health decision-making where spatial heterogeneity and uncertainty are prominent. The proposed calibrated model within a policy-learning environment using posterior samples can be replicated to simulate realistic transmission scenarios for malaria and evaluate dynamic control strategies.
Abstract: Malaria has been one of the major public health issues that has not been extensively addressed. Controlling the spread of infectious diseases in space and time requires robust adaptive policies that significantly account for heterogeneity, uncertainty, and optimal sequential decision-making. This study presents an innovative framework that integrat...
Show More
Research Article
GIS-Enhanced Bayesian Reinforcement Learning for Vector-Borne Infectious Disease Transmission
Kipngetich Gideon*,
Victor Muthama Musau,
Margaret Wambui Kinyua
Issue:
Volume 12, Issue 2, April 2026
Pages:
25-36
Received:
12 March 2026
Accepted:
26 March 2026
Published:
10 June 2026
DOI:
10.11648/j.ijdsa.20261202.12
Downloads:
Views:
Abstract: Vector-borne infectious diseases has continue to pose a significant challenge to global public health, and accurate and timely transmission prediction are crucial for effective intervention and control. The development of accurate and efficient vector-borne infectious disease predictive models has been the current trend in disease modeling. Modeling transmission, however, has assumed a discrete transmission space, which is not always ideal in the real world, and little attention has been paid to overestimation biases in predictions. The effectiveness of a predictive model is also determined by its capability to capture a significant number of data characteristics to enhance robust and accurate prediction of cases. The study proposed the application of a GIS-enhanced Bayesian Reinforcement learning model for the transmission of vector-borne infectious diseases, and model performance assessment was determined. The Bayesian quantifies the uncertainty in the parameters of models, and min-max ensemble Q-value estimation minimizes overestimation bias in the model. Simulation study was used to evaluate model performance, success rate, and interaction rate. The findings show that vector and human can avoid interaction with a success rate of 96.2% when human select combined intervention actions spray repellent, insecticide treated nets, larval management, and vaccination. Other variables such as education, wealth index, community participation, and gender empowerment significantly influence the transmission of the disease in the area. The model demonstrates a better performance in describing the transmission of the disease, therefore setting the stage for future research in predictive modeling within sub-Saharan disease-prone regions. The model can be used to determine the appropriate actions that the human should adopt to reduce human-vector interaction.
Abstract: Vector-borne infectious diseases has continue to pose a significant challenge to global public health, and accurate and timely transmission prediction are crucial for effective intervention and control. The development of accurate and efficient vector-borne infectious disease predictive models has been the current trend in disease modeling. Modelin...
Show More
