Modelling and data-based analysis of COVID-19 outbreak in India : a study on impact of social distancing measures

In this manuscript, we model and visualize the region-wise trends of the evolution to COVID-19 infections employing a SIR epidemiological model. The SIR dynamics are expressed using stochastic differential equations. We first optimize the parameters of the model using RMSE as loss function on the available data using L-BFGS-B gradient descent optimisation to minimise this loss function. This helps to gain better approximation of the models parameter for specific country or region. The derived parameters are aggregated to project future trends for the Indian subcontinent for next 180 days, which is currently at an early stage within the infection cycle. The projections are meant to function a suggestion for strategies for the socio-political counter measures to mitigate COVID-19. This study considers the current data for India from various open sources. The SIR models prediction is found following the actual trends till date. The inflection point analysis is important to find out which countries have reached their inflection point of the number of infection. We found that if current restrictions like lockdown in India continues with same control, then India will observe it[s] peak in active patients count on 22 May 2020, it will take 28 August 2020 for 90% of the peak active infections to end. Inspired from the study of DDI Lab at Singapore university of technology and design (SUTD), this study additionally tries to model and quantify the variations in the count of active patients in the country which might occur due to effect of waiver in restrictions. It should be noted that these results were predicted using COVID-19 data of India till 03 May 2020.