dailymail.co.ukdailymail.co.uk - September 14 view article

Researchers tap NASA satellites to predict malaria outbreaks 12 WEEKS before they occur and pinpoint them down to the household

A group of researchers is using data from NASA satellites to predict outbreaks of malaria, which is difficult to track and control because it spreads mostly in remote areas.

Specifically, they're combing NASA weather satellites with the Land Data Assimilation System (LDAS), a land-surface modeling system that can track and predict temperatures, rainfall levels, soil moisture content, and vegetation.

They're working to create models that will indicate where mosquitoes - which carry the deadly disease - are, as well as predict outbreaks 12 weeks in advance and pinpoint them down to the household.

Scroll down for video 

A group of researchers is using data from NASA satellites to predict outbreaks of Malaria, which is difficult to track and control because it spreads mostly in remote areas. The map shows cases in Peru, one of the countries most affected by the diseas

Malaria is one of the deadliest diseases to humans - it causes high fever, headaches, and chills and has a high fatality rate. 

In the rainforests of Peru, one of the areas most affected by disease, the number of cases has raised serious concern -  the country saw 65,000 reported cases in 2014 and as well as the next year in 2015.

It's been difficult to contain because where the outbreaks begin and how they spread has been difficult to track. 

The Peruvian government has set up posts where people can report cases, but this hasn't led to valuable data - the country is filled with seasonal laborers like miners and loggers who move around, meaning the post where malaria is reported is often hundreds of miles from where it was contracted. 

'It's an exercise in indirect reasoning,' said Ben Zaitchik, the project's co-investigator and an associate professor at Johns Hopkins University's Department of Earth and Planetary Sciences.

'These models let us predict where the soil moisture is going to be in a condition that will allow for breeding sites to form.' 

Malaria is one of the deadliest diseases to humans - it causes high fever, headaches, and chills and has a high fatality rate.

It's especially dangerous for children, the elderly, and pregnant women. 

In the rainforests of Peru, one of the areas most affected by the mosquito-borne disease, the number of cases has raised serious concern -  the country saw 65,000 reported cases in 2014 and as well as the next year in 2015.

It's been difficult to contain because where the outbreaks begin and how they spread has been difficult to track.  

They are creating models that will indicate where mosquitoes - which carry the deadly disease - are, as well as predict outbreaks 12 weeks in advance and pinpoint them down to the household.

The Peruvian government has set up posts where people can report cases, but this hasn't led to valuable data - the country is filled with seasonal laborers like miners and loggers who move around, meaning the post where malaria is reported is often hundreds of miles from where it was contracted.

The NASA satellites, however, can help researchers more accurately pin down where the cases are being contracted simply by tracking the areas with warm air and still water where mosquitoes are. 

While the tools can't identify puddles, it can track flooding and saturated soil that would cause water to pool and sit still. 

Researchers from various universities are partnering with NASA's Applied Sciences Program and the Peruvian government for the project.

The LDAS also tracks another important factor in malaria outbreaks - deforestation. All together, the approach is to develop a regional-based statistical model and another more detailed agent-based model that together will create a vivid picture of where outbreaks occur 

To combat malaria, researchers are combining data from NASA weather satellites with the Land Data Assimilation System (LDAS), a land-surface modeling system that can track and predict temperatures, rainfall levels, soil moisture content, and vegetation.

They're developing two tools, a regional-based statistical model and another more detailed agent-based model that together will create a vivid picture of where outbreaks occur so help can be dispatched.

For the regional-based model, researchers will combine reported cases with population estimates that take seasonal migration into account - this way, mosquitoes as well as human movement will be accounted for. 

The green on the map indicates cases of malaria. One of the most affected places on Earth is in the Amazon rainforest

For the agent-based model (named because it models the behavior of every agent, or every human, mosquito, and malaria parasite within an area), researchers will look at tighter spaces by zooming in with hydrology data.

They'll look at specific neighborhoods and track the movement of people, and when combined with LDAS data, this will serve as a predictive model for outbreaks.

Pan believes this will allow them to for see outbreaks 12 weeks in advance and pinpoint them down to the household, enabling the Ministry of Health to distribute resources (such as nets and sprays) where needed.

'Malaria is a vector-borne disease, which means you have to have a vector, or mosquito, in this case, transmit the disease,' said principal investigator William Pan, an assistant professor of global environmental health at Duke University.

'The key to our malaria forecasting tool lies in pinpointing areas where prime breeding grounds for these mosquitoes overlap simultaneously with human populations.' 

NASA satellites including Landsat, Global Precipitation Measurement, and Terra and Aqua will serve as inputs for LDAS.

The LDAS also tracks another important factor in malaria outbreaks - deforestation. 

All together, the approach is to develop a regional-based statistical model and another more detailed agent-based model that together will create a vivid picture of where outbreaks occur so help can be dispatched.

For the regional-based model, researchers will combine reported cases with population estimates that take seasonal migration into account - this way, mosquitoes as well as human movement will be accounted for.

Pan believes this will allow them to for see outbreaks 12 weeks in advance and pinpoint them down to the household, enabling the Ministry of Health to distribute resources (such as nets and sprays) where needed

'It's much easier to float logs down a river when its high, and at the same time mosquitoes thrive because pockets of water emerge along the riverbank,' Pan explained.

'So these types of conditions correspond with high malaria risk.' 

For the agent-based model (named because it models the behavior of every agent, or every human, mosquito, and malaria parasite within an area), researchers will look at tighter spaces by zooming in with hydrology data.

They'll look at specific neighborhoods and track the movement of people, and when combined with LDAS data, this will serve as a predictive model for outbreaks.

Pan believes this will allow them to for see outbreaks 12 weeks in advance and pinpoint them down to the household, enabling the Ministry of Health to distribute resources (such as nets and sprays) where needed.

As part of the Malaria Cero program, the Peruvian government aims to eliminate the disease by 2021. Colombia and Ecuador have expressed interest in the tools as well. In the future, the tool could be adapted to prevent outbreaks of other diseases

'Instead of treating 100 percent of the community, we could focus vector control in certain households or specific areas of the community,' Pan explained. 

'It's a targeted strategy that can achieve the same reduction in malaria, but at potentially lower cost and with a more rapid response.' 

The project is three years in the works, and the forecasting tools could be ready for use within a few years.

As part of the Malaria Cero program, the Peruvian government aims to eliminate the disease by 2021.

Colombia and Ecuador have expressed interest in the tools as well. 

In the future, the tool could be adapted to prevent outbreaks of other diseases.

'I think that government health agencies will find not just one but many uses for the system that can benefit a lot people,' he said. 

'That's always been our goal.' 

dailymail.co.ukdailymail.co.uk - September 14 view article