Collaboration between the South African National Science Agency (SANSA) and Amazon Web Services and African Data Science has yielded a scientific tool that will enable government to identify the location of informal settlements across the country.
Using a science competition platform called Zindi, over 180 data scientists from the continent took part in a hackathon competition to create a model that identifies new informal settlements that have not yet been spotted through the conventional on-the-ground monitoring.
From 12-15 June, 184 data scientists from 34 countries used SPOT satellite imagery provided by SANSA to create the models. $1 000 was up for grabs for the top three solutions. The data scientists were also given access to powerful computing capacity through virtual machines provided by Amazon Web Services.
It is very critical for government to know where informal settlements are located particularly during the Covid-19 pandemic. Informal settlements have always presented a challenge because people built their structures close to one another. This makes the areas inaccessible particularly during emergencies such as fire, floods or when an ambulance has to be dispatched to the area.
A month after the outbreak of the pandemic in South Africa, minister of human settlements, Lindiwe Sisulu expressed concern about overcrowding in informal settlements especially in the context of the Covid-19. She identified five informal settlements whose residents were to be re-located to help curb the spread of the coronavirus among the residents.
Knowing where informal settlements are situated would also help government to make evidence-based policies and ensure that all people have access to basic services they need to manage the pandemic.
“The idea was to get data scientists to work on a potential solution that SANSA could use to optimise our mapping processes,” said managing director of Earth Observations at SANSA, Andiswa Mlisa.
SANSA provided training data that had information about informal settlements around Johannesburg in Gauteng, and challenged the data scientists to create models that can find informal settlements in KwaZulu-Natal. Raphael Kiminya, a data scientist from Kenya, created a winning model. He found informal settlements in KwaZulu-Natal that manual labelling by SANSA data scientists did not flag in the training data.
Zindi Africa CEO, Celina Lee said. “What’s nice is that the model can pick up on what the human eye might just scan right over and not notice. These models won’t be replacing humans anytime soon; they remain tools developed to make the work of technicians easier, by pointing users towards where to look for informal settlements. Added Lee: “Right now, with the models that we have, it will almost be like a heatmap with different probabilities indicating where an informal settlement is likely to be.”
She said that it was exciting to work with SANSA on this project as it unlocked opportunities for many African data scientists to showcase their talents. The hackathon also illustrates the wealth of data that SANSA has to offer data scientists on the continent. “We would love to work with SANSA to tackle other problems. There is such great potential in SANSA’s data to generate insights in a quicker and more efficient way using,” Lee said.