Drinking water safe using machine learning

Waterborne illness is one of the leading causes of infectious disease outbreaks in refugee and internally displaced persons (IDP) settlements, but a team led by York University has developed a new technique to keep drinking water safe using machine learning, and it could be a game changer. The research is published in the journal PLOS Water.

Waterborne illness is one of the leading causes of infectious disease outbreaks in refugee and internally displaced persons (IDP) settlements. A team led by York University has developed a new technique to keep drinking water safe using machine learning, and it could be a game changer. The research is published in the journal PLOS Water.

As drinking water is not piped into homes in most settlements, residents instead collect it from public tap stands using storage containers.

“When water is stored in a container in a dwelling, it is at high risk of being exposed to contaminants. There must be enough free residual chlorine to kill any pathogens,” says Lassonde School of Engineering PhD student Michael De Santi. He was part of York’s Dahdaleh Institute for Global Health Research and led the research.

Recontamination of previously safe drinking water during its collection, transport and storage has been a major factor in cholera, hepatitis E, and shigellosis outbreaks in refugee and IDP settlements in Kenya, Malawi, Sudan, South Sudan, and Uganda.

“A variety of factors can affect chlorine decay in stored water. You can have safe water at that collection point. Still, once you bring it home and store it, sometimes up to 24 hours, you can lose that residual chlorine. Pathogens can thrive, and illness can spread,” says Lassonde Adjunct Professor Syed Imran Ali, a Research Fellow at York’s Dahdaleh Institute for Global Health Research.

Machine learning about drinking water

Using machine learning, the research team developed a new way to predict the probability that enough chlorine will remain. They used an artificial neural network (ANN) and ensemble forecasting systems (EFS).

“ANN-EFS can generate forecasts at the time of consumption that takes a variety of factors into consideration that affects the level of residual chlorine. That is opposed to the typically used models. This new probabilistic modelling is replacing the currently used universal guideline for chlorine use, which is ineffective,” says Ali.

Factors such as local temperature, how the water is stored and handled, the type and quality of the water pipes, water quality and whether a child dipped their hand in the water container can all play a role in how safe the water is to drink.

“However, it’s really important that these probabilistic models be trained on data at a specific settlement. Each one is as unique as a snowflake,” says De Santi. “Two people could collect the same water on the same day and store it for six hours. One could still have all the chlorine remaining in the water, and the other could have almost none left. Another ten people could have varying ranges of chlorine.”

Looking at refugee camps for drinking water

The researchers used routine water quality monitoring data from two refugee settlements in Bangladesh and Tanzania.

Determining how to teach the ANN-EFS to develop realistic probability forecasts with the smallest possible error required out-of-the-box thinking.

“How that error is measured is key. It determines how the model behaves in the context of probabilistic modelling,” says De Santi. “Using cost-sensitive learning, we found it could improve probabilistic forecasts and reliability. We are not aware of this being done before in this context.”

This model can say that under certain conditions, there is a 90 per cent chance that the remaining chlorine in the stored water after 15 hours will be below the safety level for drinking.

“That’s the kind of probabilistic determination this modelling can give us,” says De Santi. “Like with weather forecasts, if there is a 90 per cent chance of rain, you should bring an umbrella. We can ask water operators to increase the chlorine concentration. There will be a greater percentage of people with safe drinking water.”

“Our Safe Water Optimization Tool takes this machine learning work and makes it available to aid workers in the field. The only difference for water operators is we ask them to sample water in the container at the tap and in that same container at home after several hours,” says Ali.

“Michael is advancing the state of practice of machine learning models. Not only can this be used to ensure safe drinking water in refugee and IDP settlements, but it can also be used in other applications.”

Related Articles:

Send this to a friend