Without air, humanity could not possibly survive. Air quality is negatively affected by continuous changes in almost every area of modern human civilization, posing a threat to sustainable development. By integrating sustainable practices into air quality monitoring and forecasting, we can aim to minimize the generation of risky contaminants and reduce the total environmental footprint of transportation, business, and home approaches.
Priyanka Maan, Bhoomi Gupta and Deepika Bansal
Department of Computer Science & Engineering, Faculty of Engineering & Technology, SRM University, Delhi-NCR, Haryana, 131029, India.
Department of Information Technology Maharaja Agrasen Institute of Technology
New Delhi 110086, India
Corresponding Author. Tel: 8512811975, E-mail:
Abstract. Without air, humanity could not possibly survive. Air quality is negatively affected by continuous changes in almost every area of modern human civilization, posing a threat to sustainable development. By integrating sustainable practices into air quality monitoring and forecasting, we can aim to minimize the generation of risky contaminants and reduce the total environmental footprint of transportation, business, and home approaches. In comparison to standard techniques, machine gaining knowledge based totally prediction technology studying techniques have been shown to the best equipment for studying such contemporary risks. To analyze and expect air satisfaction, the prevailing take a look at appears at six years' really worth of air pollution facts from 23 Indian towns. The dataset has undergone thorough preprocessing, and correlation analysis was used to identify essential properties.
An exploratory data analysis is conducted to determine the pollutants that might have a direct influence on the air quality index as well as to find patterns that are hidden in the dataset. Almost all contaminants have significantly decreased in the epidemic year of 2020. Four models of machine learning are employed to evaluate air quality while resampling is utilized to address the problem of data imbalance. The outputs of models are contrasted with established standard. The Support Vector Machine model is the least accurate. The most accurate model is the Gaussian Naive Bayes one. The known performance metrics is used to evaluate and compare these model’s performances. The winning one was the XGBoost one, which also exhibited the highest degree of linearity between predicted and the data that was observed.
Keywords: Air Quality Index, Support Vector Machine, Random Forest, Machine Learning, Deep Learning.
REFERENCES
- Alade, I. O., Abd Rahman, M. A., & Saleh, T. A. (2019). Predicting the specific heat capacity of alumina/ethylene glycol nanofluids using support vector regression model optimized with Bayesian algorithm. Solar Energy, 183, 74-82.
- Bellinger, C., Mohomed Jabbar, M. S., Zaïane, O., & Osornio-Vargas, A. (2017). A systematic review of data mining and machine learning for air pollution epidemiology. BMC public health, 17, 1-19.
- Kumar, K., & Pande, B. P. (2023). Air pollution prediction with machine learning: a case study of Indian cities. International Journal of Environmental Science and Technology, 20(5), 5333-5348.
- Castelli, M., Clemente, F. M., Popovič, A., Silva, S., & Vanneschi, L. (2020). A machine learning approach to predict air quality in California. Complexity, 2020.
- Gopalakrishnan, V. (2021). Hyperlocal air quality prediction using machine learning. Towards data science.
- Kumar, K., & Pande, B. P. (2023). Air pollution prediction with machine learning: a case study of Indian cities. International Journal of Environmental Science and Technology, 20(5), 5333-5348.
- Patil, R. M., Dinde, H. T., Powar, S. K., & Ganeshkhind, P. M. (2020). A literature review on prediction of air quality index and forecasting ambient air pollutants using machine learning algorithms. Int J Innov Sci Res Technol, 5(8), 1148-1152.
- Johansson, C., Zhang, Z., Engardt, M., Stafoggia, M., & Ma, X. (2023). Improving 3-day deterministic air pollution forecasts using machine learning algorithms. Atmospheric Chemistry and Physics Discussions, 2023, 1-52.
- Sonawani, S., & Patil, K. (2024). Air quality measurement, prediction and warning using transfer learning based IOT system for ambient assisted living. International Journal of Pervasive Computing and Communications, 20(1), 38-55.
- Van, N. H., Van Thanh, P., Tran, D. N., & Tran, D. T. (2023). A new model of air quality prediction using lightweight machine learning. International Journal of Environmental Science and Technology, 20(3), 2983-2994.
- Kumar, K., & Pande, B. P. (2023). Air pollution prediction with machine learning: a case study of Indian cities. International Journal of Environmental Science and Technology, 20(5), 5333-5348.
