The South African National Space Agency (SANSA) has established a team of scientists to work on a potential solution for informal settlements in the country. This has become necessary as the COVID-19 pandemic has accentuated the rise of informal settlements in South Africa. By following the problem, the government intends to make evidence-based policies that will ensure that all people have access to the services they need to manage the crisis.
Speaking on the development, the Managing Director of Earth Observations at SANSA, Andiswa Mlisa, noted that “the idea was to get data scientists to work on a potential solution that SANSA could use to optimise our mapping processes”. To execute this, 184 data scientists from 34 countries used SPOT satellite imagery provided by SANSA to create the models between 12 to 15 June 2020. This also came with USD1000 compensation for the top three solutions, along with access to powerful computing capacity through virtual machines provided by Amazon Web Services.
In a press release by SANSA, the agency mentions that “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. The winning model, created by Raphael Kiminya, a data scientist from Kenya, found informal settlements in KwaZulu-Natal that manual labelling by SANSA data scientists did not flag in the training data”.
According to Zindi Africa CEO, Celina Lee, “the informal settlement that it picked up on, as an example, was a very small area that was surrounded by other homes, but you start to recognise it when you look at it more carefully”. “What’s nice is that the model can pick up on what the human eye might just scan right over and not notice,” Lee adds.
Speaking on the efficiency of the model, Lee says “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”.