Prediction of Autumn Ozone Concentration in the Pearl River Delta Based on Machine Learning

被引：2

作者：

Chen Z. ^{[1
]}

Liu R. ^{[1
,2
]}

Luo Z. ^{[1
]}

Xue X. ^{[1
]}

Wang Y. ^{[1
]}

Zhao Z.-J. ^{[3
]}

机构：

[1] Institute for Environmental and Climate Research, Jinan University, Guangzhou

[2] Guangdong-Hong Kong-Macau Joint Laboratory of Collaborative Innovation for Environmental Quality, Guangzhou

[3] School of Information Science and Technology, Fudan University, Shanghai

来源：

Huanjing Kexue/Environmental Science | 2024年 / 45卷 / 01期

关键词：

daily maximum 8-hour average concentration(MDA8-O[!sub]3[!/sub]); machine learning; ozone(O[!sub]3[!/sub]); Pearl River Delta(PRD); prediction;

D O I：

10.13227/j.hjkx.202302044

中图分类号：

学科分类号：

摘要：

Based on the observation data of the daily maximum 8-hour ozone (O3) average concentration [MDA8-O3, ρ (O3-8h)] and meteorological reanalysis data in the Pearl River Delta Region from 2015 to 2022, four machine learning methods, i. e., support vector machine regression (SVR), random forest(RF), multi-layer perceptron(MLP), and lightweight gradient boosting machine(LG)were used to establish MDA8-O3 prediction models. The results showed that the SVR model had the best prediction performance on MDA8-O3 during the whole year, the coefficient of determination (R2) reached 0.86, and the root mean square error(RMSE)and mean absolute error(MAE) were 16.3 μg·m−3 and 12.3 μg·m−3, respectively. The prediction performance of the SVR model in autumn was still slightly better than that of LG and MLP, with R2, RMSE, and MAE values of 0.88, 19.8 μg·m−3, and 16.1 μg·m−3, respectively. The RF model performed the worst in the autumn prediction. In addition, the models trained by data from the whole year had better prediction ability on autumn MDA8-O3 than that of those only trained by autumn data, and the R2 differed 0.08–0.14. © 2024 Science Press. All rights reserved.

引用

页码：1 / 7

页数：6

共 44 条

[31] Zhu J Y, An J L, Feng Y Z, Et al., Prediction of atmospheric ozone concentration in Nanjing based on lightweight gradient elevator [J], Environmental Science, 44, 7, pp. 3685-3694, (2023)
[32] Hipel K W, McLeod A I., Time series modelling of water resources and environmental systems, (1994)
[33] Libiseller C, Grimvall A., Performance of partial Mann-Kendall tests for trend detection in the presence of covariates[J], Environmetrics, 13, 1, pp. 71-84, (2002)
[34] Xiao X, Li C Q, Ma J, Et al., Analysis of Variation in Runoff of the Yi River Main Stream and Its Influencing Factors During 1955-2013, pp. 11-10, (2017)
[35] Gocic M, Trajkovic S., Analysis of changes in meteorological variables using Mann-Kendall and Sen's slope estimator statistical tests in Serbia[J], Global and Planetary Change, 100, pp. 172-182, (2013)
[36] Vapnik V N., Introduction:four periods in the research of the learning problem, The Nature of Statistical Learning Theory, pp. 1-15, (2000)
[37] Breiman L., Random forests[J], Machine Learning, 45, 1, pp. 5-32, (2001)
[38] Delashmit W H, Manry M T., Recent developments in multilayer perceptron neural networks, Proceedings of the Seventh Annual Memphis Area Engineering and Science Conference, pp. 1-15, (2005)
[39] Ke G L, Meng Q, Finley T, Et al., LightGBM:A highly efficient gradient boosting decision tree, Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 123-142, (2017)
[40] Wei J, Li Z Q, Pinker R T, Et al., Himawari-8-derived diurnal variations in ground-level PM<sub>2. 5</sub> pollution across China using the fast space-time Light Gradient Boosting Machine(LightGBM)[J], Atmospheric Chemistry and Physics, 21, 10, pp. 7863-7880, (2021)

← 1 2 3 4 5 →