# Leveraging Climate Data Through Intelligent Systems for the Prediction of Arbovirus Transmission by Aedes aegypti

## TL;DR

This study uses climate and mosquito data with intelligent systems to predict and control arbovirus transmission in Recife, Brazil.

## Contribution

The novel use of single-layer extreme learning machines for high-resolution prediction of Aedes aegypti breeding sites in urban tropical settings.

## Key findings

- Single-layer extreme learning machines provided the best balance of accuracy and efficiency in predicting mosquito breeding sites.
- High-resolution climate-driven predictions enabled earlier identification of high-risk areas for targeted interventions.
- The open-source framework can be adapted to other cities facing similar climate-related arbovirus risks.

## Abstract

Public health relevance—How does this work relate to a public health issue?
Arboviruses transmitted by Aedes aegypti represent a persistent and climate-sensitive public health threat in tropical urban settings such as Recife, Brazil.This study integrates climate, entomological, and epidemiological surveillance data to improve early prediction of arbovirus transmission risk.

Arboviruses transmitted by Aedes aegypti represent a persistent and climate-sensitive public health threat in tropical urban settings such as Recife, Brazil.

This study integrates climate, entomological, and epidemiological surveillance data to improve early prediction of arbovirus transmission risk.

Public health significance—Why is this work of significance to public health?
The study demonstrates that intelligent systems, particularly single-layer extreme learning machines, can accurately and efficiently forecast mosquito breeding sites at fine spatial scales.High-resolution, climate-driven predictions enable earlier identification of priority areas for intervention, improving the effectiveness of arbovirus control strategies.

The study demonstrates that intelligent systems, particularly single-layer extreme learning machines, can accurately and efficiently forecast mosquito breeding sites at fine spatial scales.

High-resolution, climate-driven predictions enable earlier identification of priority areas for intervention, improving the effectiveness of arbovirus control strategies.

Public health implications—What are the key implications or messages for practitioners, policy makers and/or researchers in public health?
Municipal health authorities can use these models to optimize vector control actions, targeting high-risk neighborhoods before outbreaks occur.The open-source, reproducible framework can be adapted to other cities facing climate-related arbovirus risks, supporting scalable and data-driven public health planning.

Municipal health authorities can use these models to optimize vector control actions, targeting high-risk neighborhoods before outbreaks occur.

The open-source, reproducible framework can be adapted to other cities facing climate-related arbovirus risks, supporting scalable and data-driven public health planning.

Arboviruses spread in urban tropics under climate change. At Aedes aegypti breeding sites in Recife, Brazil, we linked surveillance and climate data from the Pernambuco Water and Climate Agency (APAC), the Brazilian National Institute of Meteorology (INMET), Rapid Survey of Indices for Aedes aegypti (LIRAa), and Recife’s Open Data Portal. We modeled 2013–2021 cases and 2009–2017 breeding sites. We generated spatial fields with inverse distance weighting. We built bimonthly training grids with 5000 points and validation grids with 50,000 points. We tested linear regression, random forests, multilayer perceptrons, support vector regressors, and extreme learning machines in the Weka platform and Python Reservoir Computing Networks (PyRCNs). We ran 30 repetitions with cross-validation. The random forests performed well. Multilayer perceptrons reached very high correlations but needed longer training. Polynomial Support Vector Machines (SVMs) reached near-perfect accuracy but required very high computation. Single-layer extreme learning machines delivered the best trade-off, with low errors, correlations near 1.0, and short training times. The models produced fine-scale risk predictions and highlighted priority areas. The findings support earlier, targeted control and guide public health plans in Recife.