Issue |
E3S Web Conf.
Volume 165, 2020
2020 2nd International Conference on Civil Architecture and Energy Science (CAES 2020)
|
|
---|---|---|
Article Number | 02014 | |
Number of page(s) | 3 | |
Section | Environmental Engineering, Pollution Control and Prevention | |
DOI | https://doi.org/10.1051/e3sconf/202016502014 | |
Published online | 01 May 2020 |
Research on Urban Air Quality Prediction Based on Ensemble Learning of XGBoost
1 School of management, Tianjin University of Technology, Tianjin 300384, China
2 School of management, Tianjin University of Technology, Tianjin 300384, China
* Corresponding author 245952376@qq.com, ycwang@sina.com
In recent years, with the rapid development of China’s economy and the continuous improvement of people’s quality of life, air pollution caused by a large amount of energy consumption has become increasingly serious. Air quality index (AQI) has become an important basis to measure air quality. At present, the research on air quality assessment and prediction methods has become increasingly active at home and abroad, which is of great significance to guide people’s production and life. In this paper, Taking Shijiazhuang, Hebei Province as an example and using the XGBoost model of the machine learning ensemble algorithm, regression fitting was performed on the six pollutant concentrations that currently mainly affect air quality, and the hourly prediction of AQI was achieved.The trained model has lower mean absolute error (MAE) and higher correlation coefficient (R-square), which improves the prediction ability of urban air quality prediction, provides a new idea for urban air quality prediction, and has a broad application prospect in the future urban air quality prediction.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.