Air quality monitoring system with predictive model

Abstract

Given the constant need to monitor air quality due to increasing human activity, different alternatives for monitoring air quality under the guidelines provided by authorities such as the World Health Organization are increasingly necessary. In the case of countries like Colombia, specifically the city of Cartagena, which has its own air quality monitoring system for monitoring high-pollution areas, monitoring potential risk indicators such as particulate matter less than 10 and 2.5 micrograms (PM10 and PM2.5), and ozone (O3), despite having made significant progress in environmental policies, air quality monitoring systems must be strengthened. Therefore, the proposed solution is a solar-powered air quality monitoring system with a predictive model, using a group of sensors to take measurements of ambient pollutants. and through a Wi-Fi wireless connection, these data are transmitted to the server and database for display in the interface with the prediction algorithm, so that it contributes to the improvement objectives, and acts as a guide to ensure compliance with the guidelines proposed by entities such as the World Health Organization and the Institute of Hydrology, Meteorology and Environmental Studies. This document also describes a software system developed to receive, store, and analyze environmental data collected by sensors deployed in Cartagena since 2014. The system also includes predictive models capable of forecasting pollutant levels one hour into the future using machine learning techniques.

Trabajo de grado -- Facultad de Ingeniería