The main goal of this project is to provide the heatlh institutions with the ability to predict the new Covid expected cases so that they can organize and optimize their resources. This is done with a Predictive Model that uses the variables which Covid spread depends on. Here, the SIR model for spread of desease is used to develop a solution. Once the model is able to predict the uppcoming daily Covid new cases, a Linear Optimization model is introduced in order to optimize the usage of the available health resources needed for the treatment. By the implementation of the plan here suggested, SDG 3 (Health and Well Being) in its article 3.9 (Air Quality) is directly tackled since the death ratio in Covid patients in correlation to air quality can be calculated and studied as well as decreased. The second goal of this proposal is to enhance air quality when an upturn in Covid cases is produced. That should be done by the local government due to the fact that activities ought to be regulated in order to enhance air quality, here SDG 11 (Sustainable Cities and Communities) in its article 11.6 is tackled.
Considering that the TYR team is constituted by one member, the resources disposed are limited so the blueprint here provided might be below expectations because only the main idea is presented without any tangible technical support.
What inspired the team to choose this challenge is the belief that SDGs are one of the most important agreements ever made and every community should take them as a standard for the uppcomming decissions.
The approach to develop this project has been to try and correlate as many SDGs as possible to the Covid19 pandemic. Air polution and its correlation with respiratory deseases has been the outcome here deduced. With that in mind there was a need to create a Model that can withstand the input of data that can lead to a prediction of new Covid cases. An Autoregressive Model has been the choice due to its capacity to manage several inputs of data. Also, the Lineal Optimization Method has been chosen as a result of its capacity to handle big datasets and find the best path to optimize resources.
Some credit has to be granted to external help in the development of the final solution and some of the details of the proposal. Without them the final outcome would be inferior to the showcased here.
https://drive.google.com/file/d/1tfyqYJTGUnntYvGe5tMF3PQTazdziEDm/view?usp=sharing