Establishment and Accuracy Analysis of BP Neural for Troposphere Atmospheric Refractivity
Abstract From the observation data of 96 sounding stations in China, we use 1 887 313 sets of data from 2016 to 2018 as the training set, and 635 337 sets of data in 2019 as the test set. We conduct the comparison test with the exponential, ITU-R exponential, dual-exponential and Hopfield models. The results show that the BP model, which takes the surface meteorological information and the spatial location of the fixed point as input features, achieves the best effect by fully taking into account the various possible influencing factors of the refractivity. Compared with the exponential, ITU-R exponential, double exponential and Hopfield models, the RMSE of the best BP model is decreased by 69.8%, 33.1%, 31.9% and 16.8%, respectively. The BP model not only outperforms the traditional models in overall accuracy, but also has a more uniform distribution of errors in geospatial and longitudinal profiles.
Key words :
atmospheric refractivity
BP neural network
sounding station
Cite this article:
ZHENG Yaohang,ZHANG Di. Establishment and Accuracy Analysis of BP Neural for Troposphere Atmospheric Refractivity[J]. jgg, 2023, 43(6): 600-605.
ZHENG Yaohang,ZHANG Di. Establishment and Accuracy Analysis of BP Neural for Troposphere Atmospheric Refractivity[J]. jgg, 2023, 43(6): 600-605.
URL:
http://www.jgg09.com/EN/ OR http://www.jgg09.com/EN/Y2023/V43/I6/600
[1]
YUAN Xitun, WEN Yongxiao, CHEN Xinyu. Prediction Method and Applicability of Mining Area Surface Subsidence Based on Multi-Model Fusion [J]. jgg, 2023, 43(3): 232-238.
[2]
MENG Caixia,WU Di,LEI Yu. BP Neural Network for Satellite Clock Bias Prediction Based on Sparrow Search Algorithm [J]. jgg, 2022, 42(2): 125-131.
[3]
MENG Jinlong,TANG Shihua,ZHANG Yan,HE Guanghuan,LIU Yintao. GNSS Height Anomaly Fitting Method Based on MVO Optimized Neural Network [J]. jgg, 2022, 42(12): 1233-1238.
[4]
LU Zhaoxing, Lü Zhifeng, LI Ting, ZHANG Jinsheng, YAO Yao. Forecasting of the Variable Geomagnetic Field Based on BP Neural Network [J]. jgg, 2021, 41(3): 229-233.
[5]
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 [J]. jgg, 2021, 41(3): 262-267.
[6]
CHEN Xingda,YU Xuexiang,CHI Shengsheng,JIANG Chuang,ZHAO Xiangshuo. Surface Subsidence Prediction Model of BP StrongPredictor Fusing Chaos Residuals
[J]. jgg, 2020, 40(9): 913-917.
[7]
. [J]. jgg, 2019, 39(增2): 124-126.
[8]
ZHOU Yongjiang;YAO Yibin;YAN Xiao;ZHAO Cunjie. Study on Haze Prediction of BP Neural Network Incorporating GNSS Meteorological Parameters [J]. jgg, 2019, 39(11): 1148-1152.
[9]
DU Sunwen,ZHANG Jin,DENG Zengbing,LI Jingtao. GB-SAR Monitoring Effectiveness Analysis Using Genetic Algorithm Optimized BP Neural Network [J]. jgg, 2017, 37(8): 876-880.
[10]
. [J]. jgg, 2016, 36(增2): 75-.
[11]
HE Linbang,FENG Jie. The Key Technology of Seabed Sediment Classification
System based on Echo Intensity [J]. jgg, 2015, 35(1): 140-144.
[12]
Hu Jiyuan,Wen Hongyan,Zhou Lü,Chen Guanyu. STUDY ON DAM PREDICTION AND INVERSION WITH MULTI-SOURCE
MONITORING DATA BASED ON IPSO-BP MODEL [J]. jgg, 2014, 34(4): 67-70.
[13]
Chen Peng, Chen Jiajun. ESTABLISHMENT OF GLOBAL ATMOSPHERIC WEIGHTED AVERAGE
TEMPERATURE MODEL USING NCEP REANALYSIS DATA [J]. jgg, 2014, 34(3): 133-136.
[14]
Zhu Chengguang, Guo Tangyong, Zou Tong, Li Shipeng, Lin Qiang,Wang Yajie. APPLICATION OF BP NEURAL NETWORK IN POINTING ERROR
MODELING OF SATELLITE LASER RANGING TELESCOPE [J]. jgg, 2013, 33(5): 150-153.
[15]
Liu Yanping, Zhang Lihui, Zhang Feilian. ESTIMATION OF GPS ZENITH TROPOSPHERIC DELAY BASED ON
TERRAIN AND METEOROLOGICAL ELEMENTS [J]. jgg, 2013, 33(3): 59-63.