融合VMD和XGBoost算法的GNSS高程时间序列预测方法

doi:10.11947/j.AGCS.2023.20220052

测绘学报 ›› 2023, Vol. 52 ›› Issue (8): 1235-1244.doi: 10.11947/j.AGCS.2023.20220052

• 大地测量学与导航 • 下一篇

融合VMD和XGBoost算法的GNSS高程时间序列预测方法

鲁铁定^1,2, 李祯¹, 贺小星³, 周世健⁴

1. 东华理工大学测绘工程学院, 江西南昌 330013;
2. 自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室, 江西南昌 330013;
3. 江西理工大学土木与测绘工程学院, 江西赣州 341000;
4. 南昌航空大学, 江西南昌 330063

收稿日期:2022-01-27 修回日期:2022-11-16 发布日期:2023-09-07
通讯作者: 李祯 E-mail:lizhenhd@163.com
作者简介:鲁铁定(1974-),男,博士,教授,研究方向为测量数据处理。E-mail:tdlu@whu.edu.cn
基金资助:
国家自然科学基金(42061077;42064001;42104023);江西省自然科学基金(20202BABL213033;[JP]20202BAB212010);江西理工大学高层次人才科研启动项目(205200100564);2022年度中国科协科技智库青年人才计划

GNSS vertical time series prediction method integrating VMD and XGBoost algorithms

LU Tieding^1,2, LI Zhen¹, HE Xiaoxing³, ZHOU Shijian⁴

1. School of Geodesy and Geomatics, East China University of Technology, Nanchang 330013, China;
2. Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake, Ministry of Natural Resources, Nanchang 330013, China;
3. School of Civil and Surveying & Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China;
4. Nanchang Hangkong University, Nanchang 330063, China

Received:2022-01-27 Revised:2022-11-16 Published:2023-09-07
Supported by:
The National Natural Science Foundation of China (Nos. 42061077; 42064001; 42104023); The National Natural Science Foundation of Jiangxi, China (Nos. 20202BABL213033; 20202BAB212010); The Jiangxi University of Science and Technology High-level Talent Research Startup Project (No. 205200100564); Youth Talent Plan of Science and Technology Think Tank of China Association for Science and Technology in 2022

摘要/Abstract

摘要： 针对传统GNSS高程时间序列预测模式存在特征选取不完善、稳定性差等问题,本文提出了一种融合VMD和XGBoost算法的预测模型。该模型通过多个VMD子模型得到重构信号,再将其作为特征输入XGBoost模型中进行原始时间序列的预测。为了验证预测模型的性能,试验选取4个观测站高程时间序列数据进行预测试验,试验结果表明,VMD模型能够准确地提取特征信息。与VMD-CNN-LSTM模型相比,VMD-XGBoost模型预测结果的MAE值降低了19.74%~35.90%,RMSE值降低了22.22%~31.14%,预测结果具有更高的稳定性且与原始时间序列呈较强相关性,可以较好地预测出目标时间序列。因此,该预测模型可应用于GNSS高程时间序列预测。

关键词: VMD, XGBoost, GNSS, 时间序列, 预测

Abstract: Aiming at the problems of imperfect feature selection and poor stability in traditional GNSS elevation time series prediction models, a combined forecasting model based on variational mode decomposition (VMD) and extreme gradient boosting (XGBoost) algorithm is proposed. The model obtains the reconstructed signal through multiple VMD sub-models, and inputs it into the XGBoost model as a feature for forecasting of the original time series. To verify the performance of the forecasting model, the experiment selects the vertical time series data of 4 observatories for the forecasting experiment, the experimental results show that the VMD model can accurately extract the features. Compared with the VMD-CNN-LSTM model, the experimental results of VMD-XGBoost show that the MAE values are reduced by 19.74%~35.90% and the RMSE values are reduced by 22.22%~31.14%. The forecasting results have higher stability and are highly correlated to the original time series, which can better predict the Targeted time series. Therefore, the forecasting method can be applied to GNSS vertical time series forecasting.

Key words: VMD, XGBoost, GNSS, time series, forecasting

中图分类号:

P228

鲁铁定, 李祯, 贺小星, 周世健. 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.

LU Tieding, LI Zhen, HE Xiaoxing, ZHOU Shijian. GNSS vertical time series prediction method integrating VMD and XGBoost algorithms[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(8): 1235-1244.

参考文献

[1] DENG Liansheng, JIANG Weiping, LI Zhao, et al. Assessment of second- and third-order ionospheric effects on regional networks: case study in China with longer CMONOC GPS coordinate time series[J].Journal of Geodesy, 2017, 91(2): 207-227.
[2] WU Weiwei, WU Jicang, MENG Guojie. A study of rank defect and network effect in processing the CMONOC network on Bernese[J]. Remote Sensing, 2018, 10(3): 357.
[3] 姜卫平, 王锴华, 李昭, 等. GNSS坐标时间序列分析理论与方法及展望[J]. 武汉大学学报(信息科学版), 2018, 43(12): 2112-2123. JIANG Weiping, WANG Kaihua, LI Zhao, et al. Prospect and theory of GNSS coordinate time series analysis[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12): 2112-2123.
[4] YAO Yibin, YANG Yuanxi, SUN Heping, et al. Geodesy discipline: progress and perspective[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(4): 1-10.
[5] REN Yingying, LIAN Lizhen, WANG Jiexian. Analysis of seismic deformation from global three-decade GNSS displacements: implications for a three-dimensional earth GNSS velocity field[J]. Remote Sensing, 2021, 13(17): 3369.
[6] 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.
[7] STALLER A, ÁLVAREZ-GÓMEZ J A, LUNA M P, et al. Crustal motion and deformation in Ecuador from cGNSS time series[J]. Journal of South American Earth Sciences, 2018, 86: 94-109.
[8] HOBBS B, ORD A. Nonlinear dynamical analysis of GNSS data: quantification, precursors and synchronisation[J].Progress in Earth and Planetary Science, 2018, 5(1): 1-35.
[9] XU K, HE R, LI K, et al. Secular crustal deformation characteristics prior to the 2011 Tohoku-Oki earthquake detected from GNSS array, 2003—2011[J]. Advances in Space Research, 2021.
[10] XI R, JIANG W, MENG X, et al. Rapid initialization method in real-time deformation monitoring of bridges with triple-frequency BDS and GPS measurements[J]. Advances in Space Research, 2018, 62(5): 976-989.
[11] CHEN Qusen, JIANG Weiping, MENG Xiaolin, et al. Vertical deformation monitoring of the suspension bridge tower using GNSS: a case study of the forth road bridge in the UK[J]. Remote Sensing, 2018, 10(3): 364.
[12] XIN Jingzhou, ZHOU Jianting, YANG S, et al. Bridge structure deformation prediction based on GNSS data using Kalman-ARIMA-GARCH model[J]. Sensors, 2018, 18(1): 298.
[13] ZHANG Ruicheng, GAO Chengfa, PAN Shuguo, et al. Fusion of GNSS and speedometer based on VMD and its application in bridge deformation monitoring[J]. Sensors, 2020, 20(3): 694.
[14] ALTAMIMI Z, REBISCHUNG P, MÉTIVIER L, et al. ITRF2014: a new release of the International Terrestrial Reference Frame modeling nonlinear station motions[J]. Journal of Geophysical Research: Solid Earth, 2016, 121(8): 6109-6131.
[15] LAHTINEN S, JIVALL L, HÄKLI P, et al. Densification of the ITRF2014 position and velocity solution in the Nordic and Baltic countries[J].GPS Solutions, 2019, 23(4): 1-13.
[16] LI Z, CHEN W, DAM T, et al. Comparative analysis of different atmospheric surface pressure models and their impacts on daily ITRF2014 GNSS residual time series[J].Journal of Geodesy, 2020, 94(4): 1-20.
[17] KOWALCZYK K, PAJAK K, WIECZOREK B, et al. An analysis of vertical crustal movements along the European coast from satellite altimetry, tide gauge, GNSS and radar interferometry[J]. Remote Sensing, 2021, 13(11): 2173.
[18] 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.
[19] LI Zhen, LU Tieding. Prediction of multistation GNSS vertical coordinate time series based on XGBoost algorithm[M]//Lecture notes in electrical engineering. Singapore: Springer Nature Singapore, 2022: 275-286.
[20] LI Wenhao, LI Fei, ZHANG Shengkai, et al. Spatiotemporal filtering and noise analysis for regional GNSS network in Antarctica using independent component analysis[J]. Remote Sensing, 2019, 11(4): 386.
[21] NISTOR S, SUBA N S, MACIUK K, et al. Analysis of noise and velocity in GNSS EPN-repro 2 time series[J]. Remote Sensing, 2021, 13(14): 2783.
[22] 贺小星, 花向红, 鲁铁定, 等. 时间跨度对GPS坐标序列噪声模型及速度估计影响分析[J]. 国防科技大学学报, 2017, 39(6): 12-18. HE Xiaoxing, HUA Xianghong, LU Tieding, et al. Effect of time span on GPS time series noise model and velocity estimation[J]. Journal of National University of Defense Technology, 2017, 39(6): 12-18.
[23] 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.
[24] TAO Rui, LU Tieding, CHENG Yuanming, et al. An improved GNSS vertical time series prediction model using EWT[M]//Lecture notes in electrical engineering. Singapore: Springer Singapore, 2021: 298-313.
[25] XUE Jingming, ZHOU Sihang, LIU Qiang, et al. Financial time series prediction using ℓ2, 1RF-ELM[J]. Neurocomputing, 2018, 277: 176-186.
[26] LIN L, WANG F, XIE X, et al. Random forests-based extreme learning machine ensemble for multi-regime time series prediction[J]. Expert Systems with Applications, 2017, 83: 164-176.
[27] CHEN Tianqi, GUESTRIN C. XGBoost: a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM press, 2016: 785-794.
[28] LIN Mengying, ZHU Xuefen, HUA Teng, et al. Detection of ionospheric scintillation based on XGBoost model improved by SMOTE-ENN technique[J]. Remote Sensing, 2021, 13(13): 2577.
[29] ALIM M, YE Guohua, GUAN Peng, et al. Comparison of ARIMA model and XGBoost model for prediction of human brucellosis in mainland China: a time-series study[J]. BMJ Open, 2020, 10(12): e039676.
[30] 丁武, 马媛, 杜诗蕾, 等. 基于XGBoost算法的多元水文时间序列趋势相似性挖掘[J]. 计算机科学, 2020, 47(S2): 459-463. DING Wu, MA Yuan, DU Shilei, et al. Mining trend similarity of multivariate hydrological time series based on XGBoost algorithm[J]. Computer Science, 2020, 47(S02): 459-463.
[31] 朋子涵,高成发,刘永胜,等.手机GNSS数据质量提取的变分模态分解法[J].测绘学报,2021,50(4):475-486. DOI: 10.11947/j.AGCS.2021.20200258. PENG Zihan, GAO Chengfa, LIU Yongsehng, et al. Variational mode decomposition method for setimation of GNSS data quality from a smartphone[J]. Acta Geodaetica et Cartographica Sinica,2021,50(4): 475-486. DOI: 10.11947/j.AGCS.2021.20200258.
[32] XU Huaqing, LU Tieding, MONTILLET J P, et al. An improved adaptive IVMD-WPT-based noise reduction algorithm on GPS height time series[J]. Sensors, 2021, 21(24): 8295.
[33] JIANG Hui, HE Zheng, YE Gang, et al. Network intrusion detection based on PSO-xgboost model[J]. IEEE Access, 2020, 8: 58392-58401.
[34] LIVIERIS I E, PINTELAS E, PINTELAS P. A CNN-LSTM model for gold price time-series forecasting[J].Neural Computing and Applications, 2020, 32(23): 17351-17360.
[35] MA Lan, TIAN Shan. A hybrid CNN-LSTM model for aircraft 4D trajectory prediction[J]. IEEE Access, 2020, 8: 134668-134680.
[36] XIE Hailun, ZHANG Li, LIM C P. Evolving CNN-LSTM models for time series prediction using enhanced grey wolf optimizer[J]. IEEE Access, 2020, 8: 161519-161541.
[37] 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.

融合VMD和XGBoost算法的GNSS高程时间序列预测方法

GNSS vertical time series prediction method integrating VMD and XGBoost algorithms

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	苏小宁, 石睿娟, 鲍庆华, 朱庆, 孟国杰, 闫浩文. 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.
[2]	何佳星, 郑南山, 丁锐, 张克非, 陈天悦. 粒子群优化卷积神经网络GNSS-IR土壤湿度反演方法[J]. 测绘学报, 2023, 52(8): 1286-1297.
[3]	王梓豪, 唐炉亮, 杨雪, 戴领, 李朝奎. 利用车载GNSS轨迹大数据的U-Turn道路结构信息获取方法[J]. 测绘学报, 2023, 52(8): 1330-1341.
[4]	宋敏峰, 何秀凤, 王笑蕾, 肖儒雅, 贾东振, 李伟强. 顾及地球曲率及椭球高的GNSS-R几何计算方法[J]. 测绘学报, 2023, 52(6): 884-894.
[5]	王培晓, 张彤, 聂士超, 杨瑾萱, 王天骄. 顾及缺失值的因果图时空预测网络[J]. 测绘学报, 2023, 52(5): 818-830.
[6]	陈冠旭, 高柯夫, 赵建虎, 刘经南, 刘焱雄, 刘杨, 李梦昊. GNSS-声学位置服务中声速误差修正方法[J]. 测绘学报, 2023, 52(4): 536-549.
[7]	邝英才, 吕志平, 李林阳, 王方超, 许国昌. GNSS-A水下定位的动态非线性Gauss-Helmert模型及其抗差总体卡尔曼滤波算法[J]. 测绘学报, 2023, 52(4): 559-570.
[8]	赵春梅, 王磊, 何正斌. 卫星激光测距站分级与GNSS卫星轨道精度校核[J]. 测绘学报, 2023, 52(3): 357-366.
[9]	侯鹏宇, 张宝成, 刘腾, 查九平. CDMA+FDMA非差非组合区域PPP-RTK[J]. 测绘学报, 2023, 52(2): 183-194.
[10]	谢劭峰, 王义杰, 黄良珂, 彭华, 黎峻宇, 刘立龙. 中国区域大气加权平均温度垂直递减率格网模型[J]. 测绘学报, 2023, 52(2): 206-217.
[11]	王浩岩, 刘远刚, 李少华, 梁博, 何宗宜. GNSS高采样率路径增量地图匹配方法[J]. 测绘学报, 2023, 52(2): 329-340.
[12]	王笑蕾, 牛紫瑾, 何秀凤, 李润川. 沿海沉降变化GNSS定位及GNSS-IR组合监测[J]. 测绘学报, 2023, 52(1): 32-40.
[13]	赵爽, 王振杰, 聂志喜, 贺凯飞, 刘慧敏, 孙振. 顾及声速结构时域变化的海底基准站高精度定位方法[J]. 测绘学报, 2023, 52(1): 41-50.
[14]	舒宝, 刘晖, 王利, 张勤, 黄观文. 区域参考站网支撑的PPP和RTK一体化服务及其性能[J]. 测绘学报, 2022, 51(9): 1870-1880.
[15]	杨兵, 杨志强, 田镇, 陈祥. 联合EMD-HD和小波分解的GNSS坐标时间序列降噪分析[J]. 测绘学报, 2022, 51(9): 1881-1889.