ON SRTM VOID AREA DATA FILLING METHOD BASED ON BP NETWORK
Zhang Shoujian 1) ; Li Jiancheng 1) ; Wang Zhengtao 1) ;and Xing Lelin 1,2)
1) School of Geodesy and Geomatics, Wuhan University, Wuhan 4300792) Institute of Seismology,CEA, Wuhan 430071
Abstract Owing to the nonlinear characteristic of the topographic data, the interpolation method with linear function such as TIN can not reach high accuracy. We analyzed the interpolated accuracy with the neural network method in the SRTM void data filling, thus any nonlinear function can be approached more precisely. The analysis demonstrates that the accuracy of the neural network improves 6.3 m as comparing to the TIN method, and the contour line trends with the neural network method are smoother than that with the TIN method.
Key words ：
SRTM
DEM
neural network
TIN
interpolation
Received: 01 January 1900
Cite this article:
Zhang Shoujian ,Li Jiancheng ,Wang Zhengtao et al. ON SRTM VOID AREA DATA FILLING METHOD BASED ON BP NETWORK[J]. , 2008, 28(5): 96-99.
Zhang Shoujian ,Li Jiancheng ,Wang Zhengtao et al. ON SRTM VOID AREA DATA FILLING METHOD BASED ON BP NETWORK[J]. jgg, 2008, 28(5): 96-99.
URL:
http://www.jgg09.com/EN/ OR http://www.jgg09.com/EN/Y2008/V28/I5/96
[1]
SUN Wei,ZHU Mingchen. Study on Modeling of Tropospheric Zenith Delay in China with BP-Adaboost Strong Predictor
[2]
ZHANG Shuangcheng,XU Qiang,LUO Yong,LEI Kunchao,NIU Yufen,PANG Xiaoguang. Temporal and Spatial Variation of Land Subsidence in Beijing from 2017 to 2020 Interpreted by Time Series InSAR
[3]
YANG Xing,XIAO Huaiqian,HOU Miao,MIAO Rongrong,WENG Songgan,ZHANG Zexiong. Feasibility Study on the Vertical Displacement Monitoring Method of Jiangsu Sluice Based on InSAR
[4]
TANG Jun,LI Yinjian,ZHONG Zhengyu,GAO Xin. Prediction Model of Ionospheric TEC by EOF and LSTM Neural Network
[5]
XUAN Jianhao,CHEN Zhiwei,ZHANG Xingfu,LIANG Chenghao,WU Bo. Combining GRACE and GRACE-FO to Derive Terrestrial Water Storage Changes in the Yangtze River Basin from 2002 to 2020
[6]
ZHOU Yang. Seismic Data Prediction Based on Regression Model of Nuclear Mixed Effects
[7]
HUANG Jiawei，LU Tieding，HE Xiaoxing，LI Wei. Short Term Prediction Model of Ionospheric TEC Based on Residual Correction of Prophet-Elman
[8]
LU Tieding,HUANG Jiawei,HE Xiaoxing,Lü Kaiyun. Short-Term Ionospheric TEC Prediction Using EWT-Elman Combination Model
[9]
PENG Zhao,SHAO Yongqian,LI He,LIU Lintao. Research on Seismic Detection Based on Machine Learning with Small Sample
[10]
LI Wei，LU Tieding，HE Xiaoxing，LIU Rui. Interpolation Analysis of Prophet Model in GNSS Coordinate Time Series
[11]
FU Bolin，XIE Shuyu，LI Tao，LI Hao，ZUO Pingping，GAO Ertao. Comparative Study of Landslide Remote Sensing Monitoring Based on SBAS/PS-InSAR Technology
[12]
XU Rugang, LIANG Xiao, SUN Hongbo, CHU Fei. The Effects of Expanding Edge Length in the Processing of Gravity Anomalies Separation: An Example of Interpolation Cut Method
[13]
LU Zhaoxing, Lü Zhifeng, LI Ting, ZHANG Jinsheng, YAO Yao. Forecasting of the Variable Geomagnetic Field Based on BP Neural Network
[14]
SHE Yawen, FU Guangyu. Estimation of Gravity Anomaly Data Based on Recurrent Neural Network
[15]
HUANG Wenxi, ZHU Fuying, ZHAI Dulin, LIN Jian, QING Yun, LI Xinxing, YANG Jian. Comparative Analysis of BP Neural Network and ARMA Model in Short-Term Prediction of Mid-Latitude TEC
