Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196033,
        author = {Latchiya R and Nandhini D},
        title = {Probabilistic Spatio-Temporal Modeling of Weather-Driven Disease Risks Using Hybrid Physics-Aware and Graph-Based Machine Learning Frameworks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2589-2598},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196033},
        abstract = {Weather also has a huge impact on the health of humans, and variations in weather conditions including changes in temperature, moisture, as well as rain caused seasonal diseases like influenza, heatstroke, skin infections and heart attacks. Conventional weather forecasting and health advisory systems are not integrated systems and they do not offer personalized preventive/avoidance advice. A new system of forecasting weather- related diseases was proposed in this project based on the use of modern machine learning methods. Gaussian Process Regression, Spatio-Temporal Graph Neural Network, Physics-Informed Neural Network, and Mixture Density Network are used to analyze historical meteorological data to produce correct and probabilistic forecasts. According to the predicted conditions, weather is categorized into classes, such as cold, hot and rainy, and the risks of associated illness are dynamically suggested with the help of the system as well as the preventive measures. Being embedded into a convenient web-interface the platform unites the climate information with health sensitivity. Empirical evidence confirms that the hybrid concept is effective in the prediction of complicated weather patterns, dependable disease threats, and enabling users to implement proactive health management practices.},
        keywords = {The Weather Prediction, Disease Risk, Gaussian Process, Graph neural network, Physics-informed Neural Network, Mixture Density Network, Public Health.},
        month = {April},
        }