顾及地球物理效应的GNSS高程时间序列AdaBoost预测和插值方法

doi:10.11947/j.AGCS.2024.20230434

摘要/Abstract

摘要：

传统的GNSS高程时间序列预测和插值方法仅考虑时间变量，具有明显的局限性。本文顾及地球物理效应的影响，通过温度、大气压强、极移等数据和GNSS高程时间序列数据构建回归问题，使用自适应提升（AdaBoost）算法建模。为了验证模型的预测和插值性能，试验选取4个GNSS站的高程时间序列进行分析。建模试验表明，相较于Prophet模型，AdaBoost模型的拟合精度提升了约35%；预测结果表明，在12个月的预测周期内，AdaBoost模型在4个GNSS站的MAE值为4.0~4.5 mm，RMSE值约为5.0~6.0 mm；插值试验表明，相较于三次样条插值方法，AdaBoost插值模型的精度约提升了15%~28%。预测和插值试验表明，顾及地球物理效应的AdaBoost模型可以应用于GNSS高程时间序列预测与插值。

关键词: GNSS高程时间序列, 地球物理效应, 预测, 插值, 自适应提升算法

Abstract:

Traditional GNSS vertical time series prediction and interpolation methods only consider time variables and have obvious limitations. This study takes into account the impact of geophysical effects and constructs a regression problem using temperature, atmospheric pressure, polar motion, and GNSS vertical time series data, uses the adaptive boost (AdaBoost) algorithm for modeling. To verify the prediction and interpolation performance of the model, the vertical time series from 4 GNSS stations were selected for analysis. The modeling experiment shows that compared to the Prophet model, the fitting accuracy of AdaBoost model has been improved by 35%. The prediction results indicate that within a 12 month prediction period, the MAE values of the AdaBoost model at four GNSS stations are approximately 4.0~4.5 mm, and the RMSE values are approximately 5.0~6.0 mm. The interpolation experiment shows that compared to the cubic spline interpolation method, the accuracy of AdaBoost interpolation model has been improved by about 15%~28%. Our experiments have shown that the AdaBoost model considering geophysical effects can be applied to the prediction and interpolation of GNSS vertical time series.

Key words: GNSS vertical time series, geophysical effects, prediction, interpolation, adaptive boosting algorithm

中图分类号:

P228

鲁铁定, 李祯. 顾及地球物理效应的GNSS高程时间序列AdaBoost预测和插值方法[J]. 测绘学报, 2024, 53(6): 1077-1085.

Tieding LU, Zhen LI. Prediction and interpolation of GNSS vertical time series based on the AdaBoost method considering geophysical effects[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(6): 1077-1085.

图/表 11

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

图10

参考文献 30

[1]	余建胜, 赵斌, 谭凯, 等. 汶川地震震后GNSS形变分析[J]. 测绘学报, 2018, 47(9):1196-1206.DOI:10.11947/j.AGCS.2018.20170434.
	YU Jiansheng, ZHAO Bin, TAN Kai, et al. Analysis of GNSS postseismic deformation of Wenchuan Earthquake [J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(9):1196-1206.DOI:10.11947/j.AGCS.2018.20170434.
[2]	SAKAUE H, NISHIMURA T, FUKUDA J, et al. Spatiotemporal evolution of long- and short-term slow slip events in the tokai region, central Japan, estimated from a very dense GNSS network during 2013—2016[J]. Journal of Geophysical Research: Solid Earth, 2019, 124(12):13207-13226.
[3]	YAO Y, YANG Y, SUN H, et al. Geodesy discipline: progress and perspective[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(4):1-10.
[4]	苏小宁, 石睿娟, 鲍庆华, 等. GNSS连续观测站构造运动变化特征自适应提取方法[J]. 测绘学报, 2023, 52(8):1245-1254.DOI:10.11947/j.AGCS.2023.20220675.
	SU Xiaoning, SHI Ruijuan, BAO Qinghua, et al. Self-adaptive extraction method of tectonic movement change recorded by GNSS continuous observations[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(8):1245-1254.DOI:10.11947/j.AGCS.2023.20220675.
[5]	DANG Y, WANG H, SUN F, et al. Maintenance of millimeter-level geodetic reference framework[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(3):9-18.
[6]	李威, 鲁铁定, 贺小星, 等. 基于Prophet-RF模型的GNSS高程坐标时间序列预测分析[J]. 大地测量与地球动力学, 2021, 41(2):116-121.
	LI Wei, LU Tieding, HE Xiaoxing, et al. Prediction and analysis of GNSS vertical coordinate time series based on prophet-RF model[J]. Journal of Geodesy and Geodynamics, 2021, 41(2):116-121.
[7]	WANG Jian, JIANG Weiping, LI Zhao, et al. A new multi-scale sliding window LSTM framework (MSSW-LSTM): a case study for GNSS time-series prediction[J]. Remote Sensing, 2021, 13(16):3328.
[8]	TAO Rui, LU Tieding, CHENG Yuanming, et al. An improved GNSS vertical time series prediction model using EWT[C]//Proceedings of 2021 China Satellite Navigation Conference. Singapore: Springer, 2021: 298-313.
[9]	鲁铁定, 李祯. 基于Prophet-XGBoost模型的GNSS高程时间序列预测[J]. 大地测量与地球动力学, 2022, 42(9):898-903.
	LU Tieding, LI Zhen. Prediction of GNSS vertical coordinate time series based on Prophet-XGBoost model[J]. Journal of Geodesy and Geodynamics, 2022, 42(9):898-903.
[10]	鲁铁定, 李祯, 贺小星, 等. 融合VMD和XGBoost算法的GNSS高程时间序列预测方法[J]. 测绘学报, 2023, 52(8):1235-1244.DOI:10.11947/j.AGCS.2023.20220052.
	LU Tieding, LI Zhen, HE Xiaoxing, et al. GNSS vertical time series prediction method integrating VMD and XGBoost algorithms[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(8):1235-1244. DOI:10.11947/j.AGCS.2023.20220052.
[11]	ALEVIZAKOU E G, SIOLAS G, PANTAZIS G. Short-term and long-term forecasting for the 3D point position changing by using artificial neural networks[J]. ISPRS International Journal of Geo-Information, 2018, 7(3):86.
[12]	GAO Wenzong, LI Zhao, CHEN Qusen, et al. Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches[J]. Journal of Geodesy, 2022, 96(10):71.
[13]	LI Zhuguo, LU Tieding, HE Xiaoxing, et al. An improved cyclic multi model-extreme gradient boosting (CMM-XGBoost) forecasting algorithm on the GNSS vertical time series[J]. Advances in Space Research, 2023, 71(1):912-935.
[14]	WANG X, CHENG Y, WU S, et al. An effective toolkit for the interpolation and gross error detection of GPS time series[J]. Survey Review, 2016, 48(348):202-211.
[15]	王方超, 吕志平, 吕浩, 等. 基于RegEM算法的GPS坐标时间序列插值应用分析[J]. 大地测量与地球动力学, 2020, 40(1):45-50.
	WANG Fangchao, LÜ Zhiping, LÜ Hao, et al. Application analysis of GPS coordinate time series interpolation based on RegEM algorithm[J]. Journal of Geodesy and Geodynamics, 2020, 40(1):45-50.
[16]	谢春桥, 匡翠林. 顾及空间相关性的GNSS坐标序列插值比较[J]. 导航定位学报, 2020, 8(4):85-92.
	XIE Chunqiao, KUANG Cuilin. Comparison of interpolation methods for GNSS coordinate time series considering spatial correlation[J]. Journal of Navigation and Positioning, 2020, 8(4):85-92.
[17]	ZHANG Shengkai, GONG Li, ZENG Qi, et al. Imputation of GPS coordinate time series using MissForest[J]. Remote Sensing, 2021, 13(12):2312.
[18]	QIU Xiaomeng. Iteration empirical mode decomposition method for filling the missing data of GNSS position time series[J]. Acta Geodynamica et Geomaterialia, 2022:271-279.
[19]	LIU Ning, DAI Wujiao, SANTERRE R, et al. A Matlab-based Kriged Kalman filter software for interpolating missing data in GNSS coordinate time series[J]. GPS Solutions, 2017, 22(1):25.
[20]	BAO Zhi, CHANG Guobin, ZHANG Laihong, et al. Filling missing values of multi-station GNSS coordinate time series based on matrix completion[J]. Measurement, 2021, 183:109862.
[21]	LI Zhen, LU Tieding, YU Kegen, et al. Interpolation of GNSS position time series using GBDT, XGBoost, and RF machine learning algorithms and models error analysis[J]. Remote Sensing, 2023, 15(18):4374.
[22]	姜卫平, 李昭, 魏娜, 等. 大地测量坐标框架建立的进展与思考[J]. 测绘学报, 2022, 51(7):1259-1270.DOI:10.11947/j.AGCS.2022.20220232.
	JIANG Weiping, LI Zhao, WEI Na, et al. Progress and thoughts on establishment of geodetic coordinate frame[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7):1259-1270. DOI:10.11947/j.AGCS.2022.20220232.
[23]	陈军, 刘万增, 武昊, 等. 智能化测绘的基本问题与发展方向[J]. 测绘学报, 2021, 50(8):995-1005. DOI:10.11947/j.AGCS.2021.20210235.
	CHEN Jun, LIU Wanzeng, WU Hao, et al. Smart surveying and mapping: fundamental issues and research agenda[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):995-1005.DOI:10.11947/j.AGCS.2021.20210235.
[24]	史文中, 张敏. 人工智能用于遥感目标可靠性识别：总体框架设计、现状分析及展望[J]. 测绘学报, 2021, 50(8):1049-1058.DOI:10.11947/j.AGCS.2021.20210095.
	SHI Wenzhong, ZHANG Min. Artificial intelligence for reliable object recognition from remotely sensed data: overall framework design, review and prospect[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):1049-1058. DOI:10.11947/j.AGCS.2021.20210095.
[25]	陈军, 艾廷华, 闫利, 等. 智能化测绘的混合计算范式与方法研究 [J/OL]. 测绘学报: 1-19 [2024-05-18].http://kns.cnki.net/kcms/detail/11.2089.P.20240415.1049.002.html.
	CHEN Jun, AI Tinghua, YAN Li, et al. Hybrid computational paradigm and methods for intelligentized surveying and mapping[J/OL]. Acta Geodaetica et Cartographica Sinica: 1-19 [2024-05-18]. http://kns.cnki.net/kcms/detail/11.2089.P.20240415.1049.002.html.
[26]	SCHAPIRE R E. Explaining AdaBoost[M]//SCHÖLKOPF B, LUO Zhiyuan, VOVK V, et al. Empirical inference. Berlin: Springer, 2013: 37-52.
[27]	NATRAS R, SOJA B, SCHMIDT M. Ensemble machine learning of random forest, AdaBoost and XGBoost for vertical total electron content forecasting[J]. Remote Sensing, 2022, 14(15):3547.
[28]	ALTUNTAS C, IBAN M C, ŞENTÜRK E, et al. Machine learning-based snow depth retrieval using GNSS signal-to-noise ratio data[J]. GPS Solutions, 2022, 26(4):117.
[29]	孙为, 朱明晨. 中国区域BP-Adaboost强预测器对流层天顶延迟建模研究[J]. 大地测量与地球动力学, 2022, 42(1):35-40.
	SUN Wei, ZHU Mingchen. Study on modeling of tropospheric zenith delay in China with BP-AdaBoost strong predictor[J]. Journal of Geodesy and Geodynamics, 2022, 42(1):35-40.
[30]	鲁铁定, 陶蕊, 贺小星, 等. 顾及噪声影响的GNSS高程序列预测Prophet方法[J]. 国防科技大学学报, 2023, 45(2):121-130.
	LU Tieding, TAO Rui, HE Xiaoxing, et al. Prophet method of GNSS vertical time series prediction considering the influence of noise[J]. Journal of National University of Defense Technology, 2023, 45(2):121-130.

GNSS站	插值模型	MAE/mm	RMSE/mm
BJFS	AdaBoost	3.20	4.19
BJFS	三次样条	3.78	4.89
CHAN	AdaBoost	2.62	3.45
CHAN	三次样条	3.60	4.64
LHAZ	AdaBoost	3.25	4.15
LHAZ	三次样条	4.52	5.83
URUM	AdaBoost	3.02	3.71
URUM	三次样条	3.72	4.80