Google Earth Engine to help predict malaria on maps

Scientists are developing an online platform, using data on Google Earth Engine, that health workers around the world can use to predict where malaria is likely to be transmitted.

Scientists are developing an online platform, using data on Google Earth Engine, that health workers around the world can use to predict where malaria is likely to be transmitted.

The goal is to enable resource poor countries to wage more targeted and effective campaigns against the mosquito-borne disease, which kills 600,000 people a year, most of them children, researchers at the University of California, San Francisco said.

Faced with a multitude of public health needs, countries often make the mistake of cutting their malaria efforts just when they are close to eliminating the disease, said Hugh Sturrock, an assistant professor of epidemiology and biostatistics.

'This can have disastrous consequences, since malaria can quickly rebound, putting years of expensive control efforts to waste,' he said.

'But with these maps, health workers will know exactly where to target their scarce resources. That way, they can keep fighting the disease until it's eliminated within their borders,' said Sturrock.

Google Earth Engine brings together the world's satellite imagery - trillions of scientific measurements dating back almost 40 years - and makes it available online with tools for scientists, independent researchers and nations to mine this massive warehouse of data to detect changes, map trends and quantify differences on the Earth's surface.

With the malaria prediction platform, local health workers will be able to upload their own data on where and when malaria cases have been occurring and combine it with real-time satellite data on weather and other environmental conditions within Earth Engine to pinpoint where new cases are most likely to occur.

That way, they can spray insecticide, distribute bed nets or give antimalarial drugs just to the people who still need them, instead of blanketing the entire country.

By looking at the relationship between disease occurrence and factors such as rainfall, vegetation and the presence of water in the environment, the maps will also help health workers and scientists study what drives malaria transmission.

The new tool will be piloted in Swaziland, a country in southern Africa that has limited malaria to a few small pockets across the country through the malaria elimination program it launched in 2008 with help from the Global Health Group.

Plans are to make the tool available to health workers in other countries working with the Global Health Group's Malaria Elimination Initiative. The tool could also be adapted to predict other infectious diseases.