New Delhi, Dec 21 (PTI) Cholera outbreaks in coastal regions of India can be predicted with an 89 per cent success rate using climate data taken from Earth orbiting satellites combined with artificial intelligence (AI) techniques, according to a study.
The research, published in the International Journal of Environmental Research and Public Health, is the first to demonstrate the use of sea surface salinity, or dissolved salts in water, for forecasting cholera.
The researchers from ESA Climate Office and the Plymouth Marine Laboratory (PML) in the UK focused on predicting cholera outbreaks around the northern Indian Ocean, where they said over half of global cases of the bacterial disease were reported in the 2010-16 period.
'The model showed promising results, and there's a lot of scope for developing this work using different cholera surveillance datasets or in different locations,” said Amy Campbell, who led the study.
Cholera is a waterborne disease caused by the intake of water or food contaminated with the bacterium Vibrio cholerae, which is found in many coastal regions of the world, particularly in densely populated tropical areas.
The pathogen generally lives under warm temperatures, moderate salinity and turbidity -- the degree to which water loses its transparency due to the presence of suspended particles -- and can be harboured by plankton and debris in the water.
Researchers noted that global warming and an increase in extreme weather events are driving outbreaks of cholera -- a disease that affects 1.3 to 4 million people each year worldwide, and causes up to 143,000 fatalities.
The relationship between the environmental drivers of new cholera cases during a time period, are complex, they said.
They vary seasonally, with different lagged effects, for example from the monsoon season, the researchers explained.
They say machine learning algorithms can help to overcome these issues by learning to recognise patterns across large datasets in order to make testable predictions.
Machine learning (ML) is a type of AI which involves the study of computer algorithms that improve automatically through experience.
The research team used an ML algorithm called the random forest classifier which can recognise patterns across long datasets and make testable predictions.
The algorithm was trained on disease outbreaks reported in coastal districts in India between 2010 and 2018, and learned the relationships with six satellite-based climate records generated by ESA's Climate Change Initiative (CCI).
By including or removing environmental variables and sub-setting for different seasons, the algorithm identified key variables for predicting cholera outbreaks, including land surface temperature and sea surface salinity.
'It would be interesting to test the impact of including socio-economic datasets; remote sensing data could be used to develop records to account for human factors that are important for cholera incidence, such as access to water resources,' Campbell added. PTI SAR SAR