Abstract To solve the problems that support vector regression(SVR) models cannot actively select optimal parameters and kernel functions, we optimize the support vector regression model by the aquila optimizer(AO) and construct the aquila optimized support vector regression (AO-SVR) model. The four models, AO-SVR and SVR, gray wolf optimized support vector regression(GWO-SVR), and whale optimization algorithm support vector regression(WOA-SVR), are combined with atmospheric pollutants, meteorological factors and hourly zenith tropospheric delay(ZTD) data in five cities of Lhasa, Urumqi, Changchun, Wuhan, and Shanghai from 2020-01-01 to 30 to predict the changes of PM2.5 concentrations in the five cities on 2020-01-31, respectively. The results show that the AO-SVR model has better applicability; the predicted values in Shanghai are the closest to the actual observed values.
Key words :
SVR
GWO
WOA
AO
altitude
ZTD
Cite this article:
MENG Chunyang,XIE Shaofeng,WEI Pengzhi et al. PM2.5 Concentration Prediction Using AO-SVR Model[J]. jgg, 2023, 43(3): 269-274.
MENG Chunyang,XIE Shaofeng,WEI Pengzhi et al. PM2.5 Concentration Prediction Using AO-SVR Model[J]. jgg, 2023, 43(3): 269-274.
URL:
http://www.jgg09.com/EN/ OR http://www.jgg09.com/EN/Y2023/V43/I3/269
[1]
LIU Jiangtao,LIU Shuangtong,YE Zhengzhen,GAO Zhiyu. A Regional Precise Zenith Tropospheric Delay Combined Prediction Model [J]. jgg, 2022, 42(9): 951-956.
[2]
WANG Biaoji,HUANG Guoyong. Real Time Tropospheric Delay Modeling of Regional CORS Network Observation Data [J]. jgg, 2022, 42(6): 622-625.
[3]
HUANG Cong,GUO Hang. Accuracy Analysis of ZTD and Precipitable Water Vapor Inversion Based on GPT3 Model [J]. jgg, 2022, 42(5): 489-493.
[4]
WANG Xuke,YAN Shiwei,ZHAO Hong,YANG Xiaolei. Research on the Adaptability of Different Tropospheric Zenith Delay Models in Northwest China [J]. jgg, 2021, 41(9): 920-923.
[5]
E Shenglong,ZHOU Gang,LONG Hai,LUO Yingting,XU Hailin,RAO Zhangquan,ZHOU Yongyan. Performance Evaluation of BDS Global Positioning Service and Zenith Tropospheric Delay Estimation [J]. jgg, 2021, 41(8): 789-794.
[6]
MA Xiaping,LI Qinzheng,CHEN Peng. Evaluation on Precision of Tropospheric Delay Models Based on Radiosonde Data [J]. jgg, 2020, 40(2): 123-128.
[7]
ZHANG Yonglin,CAI Changsheng. Method and Accuracy Assessment of Zenith Tropospheric Delay Derived from ERA5 Re-Analysis Data [J]. jgg, 2020, 40(1): 62-65.
[8]
. [J]. jgg, 2020, 40(1): 66-70.
[9]
MAO Yuhui,YUE Zhongqi,XIE Binbin,DUAN Jinjue,WANG Yintao. Research on GPS/Galileo Real-Time Zenith Troposphere Delay Estimation [J]. jgg, 2019, 39(7): 728-732.
[10]
WANG Zhaoyang,XING Zhe,ZHOU Xinghua,YANG Fanlin,TANG Qiuhua,ZHOU Dongxu. Study on the Method of Extracting Zenith Tropospheric Delay by GPS/GLONASS in Coastal Area [J]. jgg, 2019, 39(6): 629-633.
[11]
LI Li,SONG Yue,YI Jinhua,TIAN Ying,ZHOU Jialing. Study on the Direct Conversion Model Between Tropospheric Delay and Precipitable Water Vapor [J]. jgg, 2019, 39(5): 492-495.
[12]
E Shenglong,LUO Yingting,WU Hao,XIA Pengfei,XU Hailin,TAN Liqing. A New Technique for Profiling Tropospheric Refractivity Based on Single Ground-Based GNSS Receiver [J]. jgg, 2019, 39(12): 1283-1286.
[13]
LIU Xiaosheng,QIN Zhiqiang. GA-SVR Combined Model for Forecasting Landside Displacement: Study on Based on Phase-Space Reconstruction [J]. jgg, 2017, 37(10): 1024-1028.
[14]
YAN Huineng,DAI Wujiao,LIU Bin. Regional Spatio-Temporal Zenith Tropospheric Delay Modeling Using Principal Component Analysis [J]. jgg, 2017, 37(10): 1074-1078.
[15]
FAN Lei,ZHONG Shiming,TAN Bingfeng,OU Jikun. Comparison of the Zenith Tropospheric Delay Estimated by Precise
Point Positioning Using BDS and GPS Data Respectively [J]. jgg, 2015, 35(1): 67-71.