Prediction of Air Quality Index (AQI)
Abstract
Abstract
Growing economy of a country has its pros and cons. Swift development of industries on an extensive scale has led to immense growth in air pollution. It happens to be elementary root of maladies and early deaths around the world. The UN responsible agency for international public health has estimated that outside atmosphere consisting of air pollution takes about three million people’s lives every year. Therefore, contamination amount in air for a city needs to be checked on a daily basis in real-time to maintain the air quality. The nature of air of some areas is reported through a unitless quantity which is said to be air quality index (AQI). Accordingly, to find a sample from the time-series data, a number of different approaches can be implemented as well as reported in literature. Through this paper, we propose a Deep Learning-based model to forecast the concentration of air pollutants. We express the difficulty of forecasting contaminant’s availability in a sequential manner as a time series-analysis where the present concentration level is based on preceding concentration, weather forecasting, etc. Output results confirm that the given method gives minute errors in terms of both root mean square error and Min/Max aggregation of AQI values.
Keyword: Air Quality Index, LSTM, Pollutants.
Cite this Article
Neeraj Kumar, Apoorva Jain, Shalini Sati, Kushagra Kapoor, Pratham Garg. Prediction of Air Quality Index (AQI). Journal of Electronic Design Technology. 2020; 11(2): 28–34p.
Full Text:
PDFDOI: https://doi.org/10.37591/joedt.v11i2.4165
Refbacks
- There are currently no refbacks.
Copyright (c) 2020 Journal of Electronic Design Technology