Heuristic predictive modeling for state/district level projection map by IISC and JNCASR team

The model offers a state-wise analysis, which throws up several interesting features of the pandemic wave in India.

Objective: The objective is to develop a Heuristic predictive modeling for state/district level projection map for Covid-19 in India

Link to public calculator: https://mesoscalelab.github.io/covid19/

When the Caring Indians project began, a key question was what will be India’s projected need for medical supplies (ventilators, PPEs, etc) in the coming days. This information, specially with state & district level granularity, was considered crucial to many of the proposed projects. In the absence of proper modeling efforts for India, a team initiated the work of trying to create a model that not only considered a pan-India, but state and district level scenarios. The model being built is a heuristic predictive model that captures the essential trend-lines from open-source data from other nations. Simply-speaking a heuristic model in this case is a statistical rule-based model, which captures the essential aspects of how the viral disease spreads in a large cluster of population, as it is unfurling in the world now.

The model offers a state-wise analysis, which throws up several interesting features of the pandemic wave in India.

Aim of this model is not to be precise, rather to provide a conservative but realistic (in terms of global trends) estimates for the pandemic. This is one model where we hope to have overestimate and be incorrect than correct.

Contact Person:

Aloke Kumar https://twitter.com/aalokelab

Santosh Ansumali https://twitter.com/SAnsumali

Related Posts

Comments (2)

I am thoroughly intrigued by the model you considered, and I am extremely thankful to you for the initiative.
This is likely to be a great tool for understanding the course of the epidemic in India for policymakers and
ordinary people alike. I have one question. Does your model take into account the possible effects of
migration (say across districts), and partial lockdown (i.e., only a fraction of the people are allowed out
so that person-to-person interaction is a fraction of what would be normal)? I believe both these factors
will be important determinants in the actual progression of the disease in India.

Again, many thanks for your excellent initiative.

Good start. I saw your github data.

Did you know about a similar effort where Ankur Goel, IIT/Delhi Mechanical alum is working on for India? A brief intro of the other study is included below.

COVID19 Moblity Data Network https://www.covid19mobility.org/ . We are accessing the effectiveness of lockdown and social distancing measures using mobility data from Facebook, Camber and telcos. The daily situation reports generated are given to public officials and policymakers to make better decisions. I am leading the India initiative of the project.

Leave a comment