AI Driven Open Data Lake for Coronavirus (COVID-19) Research and Application

Our focus is to leverage on the amount of data, skillsets, and network of existing volunteers through implementations of AI related methodologies to help medical communities, local government policy makers, and independent groups to answer key questions related to COVID-19 related to their fields.
Join the Fight. Sitting still is not enough.

Data on its own is meaningless.
Actionable intelligence is priceless.

Since WHO announced COVID-19 to be a pandemic, the dynamics of how we respond to it has changed tremendously. Similarly where a website where it provides verified news and data is no longer enough: covid19ai, the natural progression of CoronaTracker.

While CoronaTracker may have been a portal for verified news and statistics, it has also gathered immense amount of data that enabled researches to be conducted in various fields to better understand the impact of COVID-19, how to work on it, and recover from this aftermath when the time comes. These data will be part of the covid19ai open data lake project.

Open Data Lake

The current state of analysis work currently is highly fragmented. Data is everywhere and anywhere.

For swift actions to be taken in fighting COVID-19, we need to improve efficiency through an open data lake.


Empower researchers in relevant fields to uncover insights which may be limited by conventional methods.

The key is help researchers save time in figuring, looking, and getting data they need to efficiently progress their work.


Enable stakeholders to make well-informed decisions to best flatten the COVID-19 curve.

They need information to decided and act. Researches help to provide the information. COVID19AI is the material for researchers.

Current Work in Progress

Here are the 6 research topics we are currently working on:

  • Epidemic curves by country
  • Economic impact of COVID-19
  • Differentiating country covid rates by cultural factors
  • Differentiating country COVID-19 rates by demographic factors
  • Climate factors influencing COVID-19 rates
  • Transportation/network model (flights/telco) to predict COVID-19 trends

If any of these topics interests you, or you would like to explore new topics that this open data lake project may enable you, head to our research team slack channel.

Research Team Slack Channel


  • People with experience in medical domains (virology, epidemics, biology)
  • Cross-domain expertise (people who would be working on the intersections between domains such as technology + healthcare)
  • Communications and partnerships (For our work to have greater impact, we need to effectively spread our core message and mission to organizations and stakeholders that can help us)
  • Data engineers and data scientists (there will be a mountain of data that need to be worked on).
  • Developers (we still need to build traditional non-AI systems to help with data pipeline.)
  • Researchers & principal investigators, traditional academic background that are familiar with the process.

Please spread our "Invitation of Participation" document across your social channels to maximize reach about who we are and what we need help with right now.

Invitation to Participation

Join us.

Our slack and trello as those are the main tools that are used right now. Get started by joining the group to know how you could contribute. You can always leave if it is not your calling.

Let us know in the message your area of expertise and areas you'd like to contribute or be part of.

Fields marked with an asterisk (*) are required.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Partners and Sponsors