Research Article
Comparative Study on the Methods of Atmospheric Early Warning Based on Machine Learning
@INPROCEEDINGS{10.1007/978-3-031-30237-4_14, author={Guanghua Yu and Jianghong Ou and Dahua Fan}, title={Comparative Study on the Methods of Atmospheric Early Warning Based on Machine Learning}, proceedings={Machine Learning and Intelligent Communication. 7th EAI International Conference, MLICOM 2022, Virtual Event, October 23-24, 2022, Proceedings}, proceedings_a={MLICOM}, year={2023}, month={4}, keywords={Atmospheric environment Data forecast Machine learning}, doi={10.1007/978-3-031-30237-4_14} }- Guanghua Yu
Jianghong Ou
Dahua Fan
Year: 2023
Comparative Study on the Methods of Atmospheric Early Warning Based on Machine Learning
MLICOM
Springer
DOI: 10.1007/978-3-031-30237-4_14
Abstract
This paper takes Beijing Meteorological environment data as the analysis object, and uses six eigenvalues to analyze PM2.5. Normal equation, gradient descent, ridge regression and xgboost are used to predict and analyze and compare the results. The mean square error of xgboost algorithm is 0.322. It is significantly lower than the other three algorithms, and its effect is far better than the other three algorithms, which is suitable for the prediction of this data.
Copyright © 2022–2025 ICST
