About the AIforGood Simulator Project
How did this project start and who is behind it
Together with the AI for Good community, we participated in HackfromHome in April 2020 and built the COVID-19 Simulator for refugee camps and other high density & low resource settings. The project is led by a large team of volunteers from all around the world, with experience in epidemiology modelling, data science, humanitarian work, social science, user research and AI ethics.
What are we building
The Simulator is a web tool for NGOs and local authorities to model COVID-19 outbreak inside refugee camps and prepare timely and proportionate response measures needed to flatten the curve and reduce the number of fatalities. This simulator helps to predict the worst possible outbreak scenarios and their potential outcomes and help NGOs design an optimal intervention strategy.
What problem are we trying to solve
7 million people in refuge-like situations live in camps. The camps are overcrowded and lack basic sanitation. Their inhabitants share a water tap with thousands of other people. There is not enough food, so they are malnourished and have a whole range of chronic, respiratory and mental health illnesses. The nearby hospitals don’t have enough ICU beds. Self-isolation has been imposed by many countries to combat COVID-19, but how do you isolate when you live in a trampoline-covered shelter less than a meter away from your neighbour. The abundance of news stories and research papers suggests how disastrous it could become if the virus seeps into a cramped refugee camp like Moria in Greece. Yet, there is no clear strategy for the camp authorities to avoid an outbreak and its fatalities.
Why refugee camps
Refugee camps usually have a very high population density which makes them particularly vulnerable to the spread of the pandemic. Within these camps, vulnerable groups extend beyond the old population and there are people with conditions like TB, HIV, malnutrition which exposes them at a higher risk to the virus.
Due to the lack of quarantine facilities in these camps, the virus left uncurbed will spread very quickly since young people and old people have regular interactions. There is already a relatively small number of medical staff working in the camps, lack of medical supply due to less attention paid to the refugee camps can mean that the medical staff is at a greater risk of getting infected.
Why a modeling approach
We believe that a modeling approach can help for the reasons outlined above. Most refugee camps are currently in lockdown and there is a limited influx or outflux of people so the geographical boundaries are contained. People in the camp follow a certain routine that can be predicted, for example, a family or an individual waiting in the water or food distribution line.
The ultimate goal is to help NGOs prepare the outbreak and design the optimal intervention strategy before the virus seeps into camps. This way the rate of spread and the number of fatalities can be much lower. At the moment we are working the NGOs in Moria camp in Greece and an IDP camp in Iraq. They think it would be useful not only to design interventions within camps, but also forecasting the demand for essential supplies and medical services in preparation for the outbreak. This way they can mobilise action and coordinate efforts to slow down the spread of COVID-19.
We made this happen thanks to our outstanding team and excellent advisors!
Program Lead, AI for Good
We are only in the beginning or our impact journey
Collaborated and tested our simulator
Supported this project
Reached through testing our models