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{177085,
        author = {S. Akshaya Shree and R. Sandhiya and A. Shayan Rasool and Dr. V. Nivedita},
        title = {Geo-Environmental Modeling and Machine Learning-Based Forecasting of Dengue Transmission Dynamics},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {1509-1514},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177085},
        abstract = {Dengue fever, transmitted by the Aedes aegypti mosquito, continues to pose an escalating public health threat in tropical and subtropical regions worldwide. Traditional surveillance systems reliant on manual reporting and reactive control measures have proven inadequate in addressing the rapid emergence and geographic expansion of dengue outbreaks. To combat this challenge, the proposed study introduces a machine learning-based framework capable of forecasting dengue outbreaks using integrated environmental, climatic, and epidemiological data.
By harnessing large-scale historical datasets—including meteorological variables (temperature, humidity, rainfall), population density, sanitation levels, and dengue case records—the model identifies underlying patterns correlated with outbreak occurrences. The system implements supervised learning techniques such as regression models, decision trees, CatBoost, and neural networks, transforming raw inputs into actionable insights through data preprocessing, feature transformation, and model training. The use of predictive analytics enables the identification of high-risk geographic zones and timeframes, facilitating early warnings, efficient allocation of health resources, and targeted interventions by public health authorities.
The model architecture incorporates real-time data integration and automated feature engineering, allowing it to adapt dynamically to changing epidemiological trends. Extensive model validation using cross-validation and performance metrics such as accuracy, precision, recall, and F1-score confirms the system’s robustness. This paper not only contributes to the development of intelligent healthcare surveillance systems but also reinforces the role of artificial intelligence in enhancing epidemiological preparedness and reducing the impact of vector-borne diseases on vulnerable populations.},
        keywords = {Dengue Fever, Machine Learning, Predictive Modeling, Outbreak Forecasting, Epidemiological Surveillance, Climatic Data, Health Informatics, Real-Time Monitoring, Public Health Analytics, Feature Engineering},
        month = {May},
        }