收藏切换
Atmospheric Precipitable Water Modeling Method Based on Integration Algorithm of Random Forest and Multilayer Perceptron
收藏切换
Kai LI1, 2, Li LI1, 2, *, Hang YU1, 2, Zhounan DONG1, 2, Qimin HE1, 2
Journal of Geodesy and Geodynamics | 2025, 45(5) : 518 - 525
Less
收藏切换
Journal of Geodesy and Geodynamics | 2025, 45(5): 518-525
Atmospheric Precipitable Water Modeling Method Based on Integration Algorithm of Random Forest and Multilayer Perceptron
Full
Kai LI1, 2, Li LI1, 2, *, Hang YU1, 2, Zhounan DONG1, 2, Qimin HE1, 2
Affiliations
  • 1 School of Geography Science and Geomatics Engineering, Suzhou University of Science and Technology, 99 Xuefu Road, Suzhou 215009, China
  • 2 Research Center of Beidou Navigation and Environmental Remote Sensing, Suzhou University of Science and Technology, 99 Xuefu Road, Suzhou 215009, China
  • LI Kai, postgraduate, majors in GNSS meteorology, E-mail:

About Author:

LI Kai, postgraduate, majors in GNSS meteorology, E-mail:

Published: 2025-05-15 doi: 10.14075/j.jgg.2024.05.231
Outline
收藏切换

Based on the data of 56 sounding stations in China from 2009 to 2019, we analyze the correlation between precipitable water vapor(PWV) and zenith tropospheric delay(ZTD), water vapor pressure (Es), atmospheric pressure (Ps), surface temperature (Ts), and weighted mean temperature (Tm), and then construct the China PWV models using multiple linear regression (MLR), random forest (RF), multilayer perceptron (MLP), and MLP-RF integration algorithm. The accuracy of these models are evaluated. The results show that the correlation coefficients between PWV and Ts, Ps, Es, Tm and ZTD are 0.78, -0.71, 0.77, 0.74 and 0.99, respectively. The average RMSE of yearly PWV models based on MLR, RF, MLP and MLP-RF are 1.25 mm, 0.44 mm, 0.28 mm, and 0.21 mm, and the average MAE are 0.98 mm, 0.31 mm, 0.18 mm, and 0.14 mm, respectively. The average RMSE of seasonal MLR, RF, MLP, and MLP-RF PWV models are 0.60 mm, 0.45 mm, 0.29 mm, and 0.21 mm, and the MAE are 0.49 mm, 0.33 mm, 0.19 mm, and 0.14 mm, respectively. The yearly MLP-RF PWV model is with the highest accuracy, which is suitable for real time PWV acquisition and research in China region.

precipitable water vapor(PWV)  /  random forest(RF)  /  multilayer perceptron(MLP)  /  multiple linear regression(MLR)
李锴, 李黎, 余航, 董州楠, 何琦敏. 基于随机森林和多层感知机集成算法的大气可降水量建模方法. 大地测量与地球动力学, 2025 , 45 (5) : 518 -525 . DOI: 10.14075/j.jgg.2024.05.231
Kai LI, Li LI, Hang YU, Zhounan DONG, Qimin HE. Atmospheric Precipitable Water Modeling Method Based on Integration Algorithm of Random Forest and Multilayer Perceptron[J]. Journal of Geodesy and Geodynamics, 2025 , 45 (5) : 518 -525 . DOI: 10.14075/j.jgg.2024.05.231
  • Research and PracticeInnovation Programfor Graduate Students ofJiangsu Province(SJCX23_1718)
  • Research and PracticeInnovation Programfor Graduate Students ofJiangsu Province(SJCX24_1901)
  • Science and Technology Program of Jiangsu Province(BK20230660)
  • National Natural Science Foundation of China(42204014)
Year 2025 volume 45 Issue 5
29
10
Cite this Article
BibTeX
Article Info
doi: 10.14075/j.jgg.2024.05.231
  • Receive Date:2024-05-14
  • Online Date:2026-10-30
  • Published:2025-05-15
Article Data
Affiliations
History
  • Received:2024-05-14
Funding
Research and PracticeInnovation Programfor Graduate Students ofJiangsu Province(SJCX23_1718)
Research and PracticeInnovation Programfor Graduate Students ofJiangsu Province(SJCX24_1901)
Science and Technology Program of Jiangsu Province(BK20230660)
National Natural Science Foundation of China(42204014)
Affiliations
    1 School of Geography Science and Geomatics Engineering, Suzhou University of Science and Technology, 99 Xuefu Road, Suzhou 215009, China
    2 Research Center of Beidou Navigation and Environmental Remote Sensing, Suzhou University of Science and Technology, 99 Xuefu Road, Suzhou 215009, China
References
Share
https://castjournals.cast.org.cn/joweb/ddcl/EN/10.14075/j.jgg.2024.05.231
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT