Reviewed by Lexie CornerSep 3 2024
A recent study conducted by Heidelberg University geoinformation scientists, published in Scientific Reports, details a new AI-supported technique developed by a global research team for mapping mosquito populations. This method utilizes satellite and street view images to better understand the environmental factors that support the presence of Aedes aegypti mosquitoes.
AI-assisted breeding site count from satellite and street view imagery as significant predictor for Aedes aegypti egg and larval counts, as monitored by mosquito traps. Image Credit: Steffen Knoblauch / Street view images: © Google
The Aedes aegypti mosquito is a key vector for infectious diseases like dengue, Zika, chikungunya, and yellow fever. Detailed maps of mosquito distribution, showing both geographic and temporal population spread, are crucial for effective disease control and targeted intervention efforts.
Commonly known as the Egyptian tiger mosquito, Aedes aegypti is predominantly found in tropical and subtropical urban areas, where it thrives in artificial water containers such as drinking water tanks, car tires, garbage cans, and plant pots. Reducing mosquito populations remains the most effective measure for controlling these diseases, as vaccines—except for yellow fever—are not yet widely available or accepted.
Control methods, such as insecticide spraying and releasing mosquitoes infected with the Wolbachia bacterium, which can inhibit virus transmission, are costly but necessary. Urban mosquito distribution maps are particularly important for implementing these strategies in heavily affected cities like Rio de Janeiro, Brazil.
Precise maps are not only interesting from a financial standpoint to effectively plan mitigation measures but are also ecologically relevant, because some of these interventions, like extensive spraying of insecticides, harbor the risk of resistance development.
Steffen Knoblauch, Doctoral Student, Institute of Geography, Heidelberg University
Until now, most mosquito distribution maps have been manually created using data from single mosquito traps that count eggs and larvae each month. However, accurately tracking mosquito populations across large urban areas would require numerous traps and a significant workforce.
Another challenge is the mosquitoes' limited flying range—approximately 1,000 meters without wind assistance—making it difficult to create comprehensive distribution maps for large cities based solely on trap data.
To address this, geoinformation experts at Heidelberg University have developed a novel method for mapping mosquito populations.
It utilizes the fact that the density of known breeding sites can be a significant predictor for the number of eggs and larvae measured in the traps, as shown by the investigations in Rio de Janeiro.
Prof. Dr. Alexander Zipf, Head, Geoinformatics/GIScience Research Group, Institute of Geography and Director, Heidelberg Institute for Geoinformation Technology, Heidelberg University
The researchers use artificial intelligence to analyze satellite and street view images, mapping and identifying potential mosquito breeding areas in cities. This approach, combined with field measurements, allows for a more accurate assessment of the environmental factors that support the presence of Aedes aegypti.
Prof. Zipf’s team is also collaborating with Brazilian researchers to analyze mobile communications data, estimating people's movements in Rio de Janeiro. When combined with precise mosquito distribution maps, this data can enhance tracking of the prevalence of infectious diseases carried by Aedes aegypti and improve intervention strategies.
One challenge is modeling human movement patterns at different times of day, as mosquitoes are most active in the early morning and evening.
The study was a collaborative effort involving researchers from Austria, Brazil, Germany, Singapore, Thailand, and the USA, alongside the Heidelberg geoinformation experts. The research was funded by the German Research Foundation and the Klaus Tschira Foundation, which supports HeiGIT, an institute affiliated with Heidelberg University.
Journal References
Knoblauch, S., et. al. (2024) High-resolution mapping of urban Aedes aegypti immature abundance through breeding site detection based on satellite and street view imagery. Scientific Reports. doi.org/10.1038/s41598-024-67914-w
Knoblauch, S., et. al. (2023) Semi-supervised water tank detection to support vector control of emerging infectious diseases transmitted by Aedes Aegypti. International Journal of Applied Earth Observation and Geoinformation. doi.org/10.1016/j.jag.2023.103304