Air Pollution Data and Forecasting Data Monitored through Google Cloud Services by using Artificial Intelligence and Machine Learning

Abstract

The air to sustain life on Earth is a crucial ingredient. Consumption of fossil fuels, other nonrenewable energy sources, and environmental changes caused by industrial processes contribute significantly to the growth of air pollution. In order to maintain the health and success of all species living on Earth, the air quality must be continuously monitored. This work details the implementation and strategy of AI-based air pollution monitoring and forecasting based on Internet of Things (IoT). In addition, a web-based dashboard using Google's cloud platform and the ‘firebase’ API tracks air pollution levels in real-time, both here and now and in the future. The air's purity can find by some components like carbon monoxide (CO), ammonia (NH4), and ozone. These components are calculated by using different types of sensors. Sensors are placed in various places in Vijayawada's surroundings. To calculate the air pollution in respective areas, using other techniques based on the time series modelling process and by integrating the Auto regression model to the moving Average Model. In this process, input parameters are training data sets collected concerning time series. These input parameters are found by using innovative technology. Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are two examples of performance indices used to verify the efficacy of different Time Series models (RMSE). Raspberry Pi-3 computer learning algorithm blinked. It is a node at the network's periphery. An online dashboard built on the open-source Google cloud firebase tracks air pollution readings and predictions for the next four hours.