Density assessment workflow of Aedes aegypti breeding container detections for modeling immature mosquito abundance at the flight range scale in the city of Rio de Janeiro, Brazil. Mapping of Aedes aegypti breeding containers was performed using satellite imagery and street views by applying and fine-tuning single-stage object detection networks (left). Container densities were calculated within a 1000 m circular flight range buffer around egg trap locations. For the assessment of the research question, univariate negative binomial regression models were trained using temporally aggregated egg and larval counts from entomological monitoring (middle). Entomological surveillance data on immature Aedes aegypti abundance were collected by the Municipal Health Department of Rio de Janeiro (right). Credit: Scientific reports (2024). DOI: 10.1038/s41598-024-67914-w
The Aedes aegypti mosquito is responsible for the spread of infectious diseases such as dengue fever, Zika virus, chikungunya and yellow fever worldwide. To combat these widely transmissible diseases that affect millions of people, detailed maps of mosquito distribution, with data on the spatial and temporal spread of populations, are essential.
Led by geoinformation scientists from Heidelberg University, an international research team has developed a new AI-based method for mapping mosquito populations. Satellite and street images are analyzed to more accurately assess the environmental conditions that favor the presence of Aedes aegypti. This helps improve the planning of intervention measures and achieve more targeted disease control.
Also known as the Egyptian tiger mosquito, Aedes aegypti is found primarily in tropical and subtropical regions of the world, particularly in cities, where it prefers to breed in artificial water containers such as drinking water tanks, car tires, trash cans, or flower pots. As the global availability and acceptance of vaccines against the diseases it transmits is still limited, with the exception of yellow fever, mosquito population control is currently the most effective intervention.
Vector control measures, which can be very costly, include spraying insecticides and releasing mosquitoes infected with the natural bacteria Wolbachia. This bacteria can prevent the transmission of the virus by Aedes aegypti and hinder its spread.
The implementation of these control measures requires urban distribution maps of mosquitoes, particularly in large cities that are particularly affected, such as Rio de Janeiro (Brazil).
“Accurate maps are not only financially interesting for efficient planning of mitigation measures, but they are also ecologically relevant, because some of these interventions, such as mass spraying of insecticides, carry a risk of resistance development,” says Steffen Knoblauch, a doctoral student at the Institute of Geography at Heidelberg University.
Until now, mosquito distribution maps have been based mainly on manual field measurements using individual traps to count eggs and larvae each month. In large urban areas, however, it would take countless traps and a large staff to maintain a reliable overview of the spread of mosquito populations.
Another challenge is the limited range of mosquitoes, which is about 1,000 meters without wind. This makes it difficult to establish mosquito distribution maps in large urban areas from measurements made using mosquito traps.
To overcome this problem, geoinformation scientists at Heidelberg University have developed a new approach to mapping mosquito populations.
“It uses the fact that the density of known breeding sites can be a significant indicator of the number of eggs and larvae measured in traps, as shown by research in Rio de Janeiro,” says Professor Alexander Zipf, head of the Geoinformatics/GIS research group at the Institute of Geography and director of the Heidelberg Institute for Geoinformation Technology (HeiGIT).
Using artificial intelligence, researchers analyze satellite and street view images to detect and map potential breeding sites in cities. In combination with field measurements, it is then possible to assess more precisely than before the environmental conditions that favor the presence of Aedes aegypti.
In collaboration with Brazilian researchers, Professor Zipf’s team is also working on analyzing mobile communication data to model the movements of Rio de Janeiro residents. Combined with accurate mosquito distribution maps, these data can help better track the occurrence of infectious diseases transmitted by Aedes aegypti and integrate the knowledge gained into intervention maps. One challenge is modeling human movement patterns at different times of the day, as the mosquito tends to be active early in the morning and evening.
In addition to the geoinformaticians from Heidelberg, researchers from Austria, Brazil, Germany, Singapore, Thailand and the USA contributed to this work. The research results were published in the journal Scientific reports and the International Journal of Applied Earth Observation and Geoinformation.
More information:
Steffen Knoblauch et al., High-resolution mapping of juvenile Aedes aegypti abundance in urban areas using breeding site detection from satellite and street images, Scientific reports (2024). DOI: 10.1038/s41598-024-67914-w
Steffen Knoblauch et al, Semi-supervised detection of water reservoirs to support vector control against emerging infectious diseases transmitted by Aedes Aegypti, International Journal of Applied Earth Observation and Geoinformation (2023). DOI: 10.1016/j.jag.2023.103304
Provided by Heidelberg University
Quote: Geoinformatics: Using AI to Better Target Mosquitoes (2024, September 2) retrieved September 2, 2024 from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.
