Epidemic Modelling of COVID-19

We built an approach to simulate the effect of different public health interventions against the spread of COVID-19. Although created for the Cox’s Bazar refugee settlement in Bangladesh, the model is designed to be generalizable to other settings.

The results are helping professionals in Cox’s Bazar settlement make faster and more informed decisions. 

About the Project

Located in Bangladesh, the Cox’s Bazar settlement houses the Kutupalong-Balukhali Expansion Site, a collection of camps for refugees and internally displaced persons (IDPs) which form the most densely populated and interconnected site with almost 600,000 Rohingya refugees. Measures that proved effective in slowing down the spread of the virus, including social distancing and household quarantine, are not always possible or easy to implement here.

Our team worked with public health professionals, data scientists, and academics spanning multiple UN agencies and universities to model the impact of various public health operational interventions in the site.

A collaboration between

The Tool in Action

Modelling Scenarios

The team looked at various scenarios that could support more effective and efficient decision-making and advocacy. 

The Baseline

To determine the effect that any protective measures would have on the spread of COVID-19, we simulated what the spread would look like with no interventions.
This graph represents the simulated spread of new COVID-19 cases over time. Since data from the settlement is not complete, it is important to look at the relative changes to this curve, rather than the exact number of infections predicted.

Home Care

We simulated the difference between treating all positive cases in treatment centers vs encouraging home isolation for certain cases.
This scenario doesn't have a large impact on the disease's spread. Moreover, encouraging people to pursue home treatment for mild to severe cases could alleviate pressure on treatment centers.

Wearing Masks

We simulated the effects of different levels of compliance with mask wearing on the spread of COVID-19 over time  in the settlement.
Even if just half of the people in the settlement wore masks, and even if the masks only reduced the probability of transmitting COVID-19 by 50%, this graph shows just how effective masks can be.

Learning Centres

We explored the different possibilities for reopening learning centers, which are vital to the community and which were closed in March 2020.

Reopening learning centres could lead to more people getting infected. Strategies like reducing required attendance and implementing mask-wearing could mitigate these negative effects.

What Users Say

“PulseSatellite is an exciting example of a system combining AI and human experience to greatly improve the use of satellite imagery in the UN system. By employing artificial intelligence and a great and intuitive interface, the power of satellite imagery is much more accessible to UN colleagues.

Lars Bromley, Geospatial Specialist, UNOSAT

“PulseSatellite is a promising tool that will allow UN agencies to use their own models while including the analyst during on-the-fly training and evaluation. It will also help to scale the deployment phase providing a user-friendly interface.”

Edoardo Nemni, Machine Learning Researcher, UNOSAT

“We wanted to build a web-based tool that is tailored to the needs of UN agencies and that is easy to use. The collaborative nature of the system is what hopefully makes it invaluable, both because it allows teams across time zones and geographies to work on the same project, and because it encourages teams to upload and use their own models, as well as share them with others.

Tomaz Logar, Data Engineer, UN Global Pulse and PulseSatellite Project Lead
Scroll to Top