Application of Combined Model Based on LSSVM in Regional Quasi-Geoid Fitting
Abstract Aiming at the big model error of least squares support vector machine(LSSVM) in regional quasi-geoid fitting, we establish the combination model of LSSVM and Shepard interpolation model for GPS elevation conversion. We use LSSVM to fit the medium-long wave term in abnormal height, and use Shepard interpolation model to generalize and remove the residual of medium-long wave term. Combined with engineering examples in plain area and plateau mountainous area, we use the quadric surface model, the LSSVM, the Shepard interpolation model, the quadratic-Shepard model, and the LSSVM-Shepard model for elevation conversion and accuracy comparison. The results show that the accuracy of new combined model is higher than that of single model. Moreover, the conversion effect of LSSVM-Shepard model in the plain area is basically consistent with the quadratic-Shepard model, and the fitting effect is better than the quadratic-Shepard model in the plateau mountainous area.
Key words :
LSSVM
Shepard interpolation model
quasi-geoid
elevation conversion
Cite this article:
LI Mingfei,WU Junchao,ZHANG Yichi. Application of Combined Model Based on LSSVM in Regional Quasi-Geoid Fitting[J]. jgg, 2022, 42(9): 971-974.
LI Mingfei,WU Junchao,ZHANG Yichi. Application of Combined Model Based on LSSVM in Regional Quasi-Geoid Fitting[J]. jgg, 2022, 42(9): 971-974.
URL:
http://www.jgg09.com/EN/ OR http://www.jgg09.com/EN/Y2022/V42/I9/971
[1]
PANG Cong,LIAO Chengwang,JIANG Yong,CHENG Cheng,WU Tao,SHU Peng,DING Wei. Research on Identification of Seismic Event Properties Based on Least Squares Support Vector Machine and Entropy Feature [J]. jgg, 2022, 42(6): 655-660.
[2]
LI Mingfei,WU Junchao,QIN Chuan. Analysis and Comparison of Local Quasi Geoid Refinement Model Based on Remove-Restore Method [J]. jgg, 2020, 40(9): 952-956.
[3]
XIE Shaofeng,SU Yongning,LIU Chunli,LIU Lilong. Short-Impending Prediction of GPS Precipitable Water Vapor Based on Wavelet Decomposition and GA-LSSVM [J]. jgg, 2019, 39(5): 487-491.
[4]
DONG Mingxu,LI Jiancheng,HUA Liangchun,JIANG Weiping,YIN Haohua,AO Minsi,ZENG Xiangqiang. Hunan 2017 GNSS Gravity Quasi-Geoid Model and Its Precision Analysis [J]. jgg, 2019, 39(1): 66-71.
[5]
LI Jun,OUYANG Mingda,LI Qi. Refinement of Regional Quasi-Geoid Using the EGM2008+DTM2006.0 Model [J]. jgg, 2018, 38(3): 244-248.
[6]
XIE Yangyang,WU Dapeng,FU Chao,ZHOU Jie,SHI Yijun. Research on Deformation Prediction Model of FOA-GLSSVM Deep Foundation Pit Based on Phase Space Reconstruction [J]. jgg, 2018, 38(10): 1048-1052.
[7]
LI Feng,ZHANG Shuhong,WANG Hongfei,QUAN Wei. Quasi-Geoid Refinement Algorithm Based on Coons Surface [J]. jgg, 2016, 36(12): 1109-1111.
[8]
ZHAI Changzhi,YAO Yibin,YUE Shun. Geoid Refinement Method Based on the Regional EGM2008
and the Remaining Terrain Model [J]. jgg, 2015, 35(6): 941-944.
[9]
REN Chao,LIANG Yueji,PANG Guangfeng,LAN Lan. Dam Deformation Prediction Based on Grey Least Square
Support Vector Machines [J]. jgg, 2015, 35(4): 608-612.
[10]
Xu Xinqiang, Zhao Dejun,Lou Nan. A GEOID TO QUASIGEOID SEPARATION CONSIDERING
SECOND ORDER HEIGHT TERMS [J]. jgg, 2013, 33(5): 75-78.
[11]
Li Mingfeng,Li Chunjin,Wang Yongming, Zhu Liqiang. GPS HEIGHT CONVERSION BASED ON SVM PARAMETER
OPTIMIZATION METHOD [J]. jgg, 2013, 33(3): 48-51.
[12]
Ding Haiyong,Sun Jingling. RESEARCH ON TOTAL LEASTSQUARES METHODS FOR
TRANSFORMATION OF GPS ELEVATION [J]. jgg, 2013, 33(3): 52-55.
[13]
Lei Yu,Zhao Danning. CLOCK ERROR PREDICTION USING LEAST SQUARES SUPPORT VECTOR MACHINES [J]. jgg, 2013, 33(2): 91-95.
[14]
Guo Chunxi;Nie Jianliang;Wang Bin;and Jiang Guangwei. METHODS FOR FITTING LOCAL QUASIGEOID AND THEIR APPLICABILITY ANALYSIS [J]. , 2013, 33(1): 103-107.
[15]
Peng Xiangguo;Wan Xianbin;and Wang Hailong. RESEARCH ON REFINEMENT OF REGIONAL QUASI-GEOID OF POYANG LAKE [J]. , 2013, 33(1): 150-152.