Overview
The Institute of Advanced Virology (IAV) has built a DEWS that combines six years of dengue case data (Mar 2020‑Feb 2026) with climate variables to forecast district‑wise dengue risk.
Key Developments
- Integration of epidemiological records from the State Surveillance Unit with rainfall, temperature and humidity data from the India Meteorological Department.
- Weekly forecasts are displayed on a public portal (https://dews.iav.res.in) and classified into four risk levels – very high, high, moderate and low.
- Model treats each district as an independent unit, accounting for local water bodies, drainage and urban features.
- Initial validation (Mar‑Jul 2026) shows a positive correlation between predicted and actual dengue cases.
Important Facts
Climate is a strong early‑warning signal for dengue because it directly affects the biology of the Aedes mosquito. Warm temperatures speed up mosquito development and shorten the extrinsic incubation period, raising transmission efficiency. Moderate humidity prolongs mosquito survival, while moderate rainfall creates breeding sites; heavy rain can wash them away.
Kerala’s warm and wet climate makes it conducive for Aedes mosquito proliferation, prompting the state to seek predictive tools.
Predicting dengue is difficult. Apart from climate, urbanisation, human mobility, water‑storage practices, population immunity to the four dengue serotypes and changes in vector biology influence transmission. Heavy reliance on climate variables may miss sudden shifts in these factors.
Under‑reporting is another hurdle. Many infections are mild or asymptomatic, and testing capacity varies across districts. For example, Thiruvananthapuram appears as a hotspot partly because of stronger surveillance.
Exam Relevance
Understanding DEWS helps aspirants link climate change, vector‑borne diseases and public‑health governance – topics covered in GS3 (Health, Science & Technology). The model illustrates how data‑driven policy can improve disease surveillance, a key discussion point for questions on health infrastructure and technology adoption.
The initiative also touches on inter‑departmental coordination (Health Department, Meteorological Department, research institutes) – a classic GS2 (Polity) theme of collaborative governance.
Way Forward
To become a routine public‑health tool, DEWS must be updated yearly, incorporate additional variables (e.g., mobility data, serotype prevalence) and address data quality issues such as under‑reporting. The platform could later be adapted for other Aedes‑borne illnesses like chikungunya and Zika, strengthening Kerala’s overall disease‑surveillance capacity.
In summary, the IAV‑DEWS project showcases the use of machine learning for proactive health planning, a model that other Indian states may emulate.