Prediction of GNSS Vertical Coordinate Time Series Based on Prophet-XGBoost Model
Abstract According to the non-stationary and nonlinear characteristics of GNSS time series, we analyze the applicability and characteristics of XGBoost and Prophet models, and construct a Prophet-XGBoost prediction model. Firstly, using the Prophet model, we decompose the GNSS original time series, then carry out partial prediction by XGBoost model. We obtain prediction results by equal weight addition. We select the daily coordinate time series data of U component of ALGO, ALRT and BRST IGS stations in the experiment, and use MAE and RMSE as evaluation indexes. The experimental results show that compared with the single XGBoost model and Prophet model, the MAE and RMSE values of Prophet-XGBoost model are optimized to a certain extent. The effectiveness of this method is verified and can be used for GNSS time series prediction.
Key words :
XGBoost model
Prophet model
time series
prediction
Cite this article:
LU Tieding,LI Zhen. Prediction of GNSS Vertical Coordinate Time Series Based on Prophet-XGBoost Model[J]. jgg, 2022, 42(9): 898-903.
LU Tieding,LI Zhen. Prediction of GNSS Vertical Coordinate Time Series Based on Prophet-XGBoost Model[J]. jgg, 2022, 42(9): 898-903.
URL:
http://www.jgg09.com/EN/ OR http://www.jgg09.com/EN/Y2022/V42/I9/898
[1]
LEI Heng,ZHOU Xiaolan,WANG Yongqiang. Research on Landslide Early Warning and Prediction Based on Combined Response of Multifractal Characteristics and Sub Item Prediction [J]. jgg, 2022, 42(9): 885-891.
[2]
ZHANG Yilei,BIAN Jiawen,DING Kaihua,RAN Jianuo,LIU Wenping. GPS Coordinate Time Series Reconstruction Based on ICEEMDAN and SSA Joint Algorithm [J]. jgg, 2022, 42(9): 904-909.
[3]
GUO Shiwei,SHI Chuang,WEI Na,ZHANG Tao. Effect of Geocenter Motion Induced by Ocean Tide Loading on Periodic Signals of GPS Position Time Series [J]. jgg, 2022, 42(8): 790-795.
[4]
LI Lu,QU Wei,ZHANG Qin,LI Jiuyuan,WANG Yuhao,LIU Xiangbin. Application of Optimized Recurrent Neural Network in Prediction of Landslide Displacement [J]. jgg, 2022, 42(6): 594-600.
[5]
LI Xiaobin. Analysis of Landslide Deformation Potential Based on Limit Displacement Criterion and Deformation Prediction [J]. jgg, 2022, 42(6): 588-593.
[6]
LU Tieding,TAO Rui,CHENG Yuanming,ZHOU Ziqi,HE Jinliang. Optimized EWT-NLM Adaptive GNSS Vertical Time Series Noise Reduction Method [J]. jgg, 2022, 42(5): 451-456.
[7]
FAN Xiaomeng,HU Chuan,LI Chenghong,ZHANG Chongyang. Improved DINEOF for Interpolating GNSS Coordinate Time Series [J]. jgg, 2022, 42(5): 462-465.
[8]
NING Bo,LIU Yujian,WANG Andong. Stability Evaluation and Development Trend Analysis of Giant Ancient Landslide [J]. jgg, 2022, 42(5): 515-519.
[9]
LU Tieding,HE Jinliang,XU Huaqing,HE Xiaoxing. An Improved Gross Error Detection Method for GNSS Elevation Time Series Based on MAD [J]. jgg, 2022, 42(4): 349-354.
[10]
XU Huaqing,LU Tieding,HE Xiaoxing,ZHOU Shijian,TAO Rui. GNSS Coordinate Time Series Gross Error Detection Based on SSA-Sn [J]. jgg, 2022, 42(3): 258-263.
[11]
QIAN Wei,YUE Jianping,SHAN Lijie,HAN Chenyu. Prophet-VAR Length-of-Day Variations Prediction Method Considering Atmospheric Angular Momentum [J]. jgg, 2022, 42(3): 264-268.
[12]
ZHOU Ziqi,ZHOU Shijian,TAO Rui. Surface Subsidence Prediction Based on EWT-Prophet Method [J]. jgg, 2022, 42(3): 247-252.
[13]
WANG Zhaoyang,XING Zhe,ZHANG Feng,YANG Xiaotong,WANG Liyan. Noise Analysis of the GPS Coordinate Time Series in the West Antarctic with Consideration of Common Mode Error [J]. jgg, 2022, 42(2): 132-138.
[14]
CAO Tingting,LI Zhifeng,GOU Haoyang. Research on Least Squares Harmonic Estimation in Extracting the Multipath Effect of GNSS Coordinate Time Series [J]. jgg, 2022, 42(2): 139-142.
[15]
SUI Zhemin,LI Jianzhang,WANG Sifan,GAO Zhiyu. Noise and Velocity Field Analysis of Shanxi CMONOC Coordinate Time Series [J]. jgg, 2022, 42(2): 148-152.