Google LLC has teamed up with SC Johnson, the maker of Off brand bug repellent, to release a publicly available forecasting app that predicts mosquito numbers nationwide called the OffCast Mosquito Forecast.
The app allows anyone on a desktop or a mobile device to enter a ZIP code and get a seven-day forecast of mosquito populations for the continental United States in a display similar to weather apps. This way users can plan their own outdoor activities accordingly.
For most people, mosquitoes are an annoying pest that ruins picnics and BBQs, but they’re also a major health hazard. For example, mosquitoes are vectors for a number of dangerous diseases worldwide including Zika, malaria, dengue fever and yellow fever. They are responsible for more than 700 million infections a year across the globe.
According to the blog post Thursday announcing the release, although it will be limited to the U.S. initially, it is planned to roll it out to other regions such as Brazil and Mexico in the near future. By offering it to these areas, it will be able to aid even more greatly in helping people avoid mosquito bites and therefore lower the spread of these dangerous diseases.
“We are putting the power in consumers’ hands in providing them with a tool to help predict their exposure and prevent mosquito bites,” said Maude Meier, an entomologist at SC Johnson. “It’s an exciting time to be working in the field of insect science as we find new opportunities to combine science and technology to be a force for good in our mission to prevent the spread of insect-borne diseases.”
To get the job done, OffCast taps Google Earth Engine, a cloud-based geospatial analysis platform that uses satellite imagery and cloud computing to extract localized weather data points. This information is then fed into an algorithm co-developed by researchers from SC Johnson’s Center for Insect Science and Family Health and experts from Climate Engine to model the weather data into relevant mosquito information.
The way this is done is by applying weather data – such as humidity and sun, warming and cooling trends – to the lifecycle of the mosquito, starting from when populations lay eggs to when they could swarm and bite humans.
This is refined with additional on-the-ground insect data from VectorBase, an organization that captures and counts mosquitoes and is funded by the U.S. National Institute of Allergy and Infectious Diseases. VectorBase uses more than 5,000 trapping locations to increase the model’s accuracy. The model itself has been developed based on six years of data collected from more than 33 million mosquitoes across 141 different species.
Google and SC Johnson hope that the mosquito forecasting app will help reduce the number of pest-borne diseases by adjusting human behavior. The app is already available today on desktop and mobile for people to try out and see what mosquito populations will be near them.