A random forest-based prediction model for ionospheric foF2 in China and surrounding regions
-
摘要: 电离层F2层的临界频率(foF2)的平方与峰值电子密度(NmF2)成正比，是影响GNSS性能的关键参数之一，提升电离层foF2的预测精度对于优化GNSS广播电离层模型性能并提升GNSS的定位精度具有重要意义. 本文基于中国及周边区域的18个测高仪台站和COSMIC(constellation observing system for meteorology, ionosphere, and climate)掩星观测数据，综合考虑世界时、年积日、地理位置、太阳和地磁活动等多维特征，利用随机森林(random forest，RF)算法构建了电离层foF2预测模型. 通过与国际参考电离层(international reference ionosphere, IRI)-2020模型对比分析，验证了该模型的预测精度. 研究结果表明，与IRI 国际无线电咨询委员会(International Radio Consultative Committee, CCIR)和IRI 国际无线电科学联盟(International Union of Radio Science, URSI)模型相比，RF模型的平均绝对误差(mean absdute error, MAE)分别降低了14.81%和17.11%，均方根误差(root mean squared error, RMSE)分别降低了11.21%和13.14%. 此外，该模型在不同纬度、地方时、太阳活动和地磁活动条件下，均展现出优于IRI-2020的预测精度. 本研究不仅有效提升了中国及周边区域电离层foF2的预测精度，还为提高GNSS的准确性和可靠性奠定了重要基础.Abstract: The square of the critical frequency of the ionospheric F2 layer (foF2) is proportional to the peak electron density (NmF2) and serves as a crucial parameter affecting the performance of Global Navigation Satellite Systems (GNSS). Enhancing the prediction accuracy of foF2 is essential for optimizing GNSS broadcast ionospheric models, thereby improving the positioning accuracy of GNSS. This study develops an ionospheric foF2 prediction model for China and its surrounding regions using the random forest algorithm, based on data from 18 ionosonde stations of the China Research Institute of Radiowave Propagation and COSMIC occultation observations. The model incorporates multiple features, including Universal Time, day of the year, geographic location, solar, and geomagnetic activities. A comparative analysis with the International Reference Ionosphere (IRI-2020) model validates the prediction accuracy of our model. The results indicate that the random forest model reduces the mean absolute error by 14.81% and 17.11%, and the root mean square error by 11.21% and 13.14%, compared to the IRI CCIR and IRI URSI models, respectively. Additionally, the model exhibits superior prediction accuracy under various latitudes, local times, solar, and geomagnetic activity conditions when compared to IRI-2020. This research not only significantly enhances the foF2 prediction accuracy for China and its surrounding regions but also lays a critical foundation for improving the accuracy and reliability of GNSS globally.
-
Key words:
- ionospheric foF2 /
- random forest /
- ionosonde /
- COSMIC occultation /
- International Reference Ionosphere /
- GNSS
-
表 1 中国区域测高仪台站的详细信息列表
序号 台站名 编号 时间范围 1 海口站 HAIK 2007—2019 2 广州站 GUAN 2007—2019 3 厦门站 XIAM 2016—2019 4 昆明站 KUNM 2007—2019 5 重庆站 CHQN 2007—2019 6 拉萨站 LASH 2007—2019 7 苏州站 SUZH 2009—2019 8 西安站 XIAN 2010—2019 9 新乡站 XINX 2009—2019 10 兰州站 LANZ 2007—2019 11 青岛站 QDAO 2007—2019 12 喀什站 KASH 2013—2019 13 北京站 BJIN 2007—2019 14 伊犁站 YILI 2013—2019 15 乌鲁木齐站 URMQ 2007—2019 16 长春站 CHAN 2007—2019 17 阿勒泰站 ALTI 2012—2019 18 满洲里站 MANZ 2007—2019 
下载: 导出CSV
-
[1] 韩喜豪, 郑帅勇, 杨建雷, 等. 卫星导航中电离层误差校正技术现状与发展[J]. 全球定位系统, 2024, 49(2): 111-126. DOI: 10.12265/j.gnss.2023105 [2] 刘钝, 李锐. 卫星导航增强中的电离层扰动影响研究——基于系统可靠性工程的视角[J]. 全球定位系统, 2023, 48(1): 3-13. DOI: 10.12265/j.gnss.2022209 [3] BENT R B, LLEWELLYN S K, NESTERCZUK G, et al. The development of a highly-successful worldwide empirical ionospheric model and its use in certain aspects of space communications and worldwide total electron content investigations[C]//Effect of the Ionosphere on Space Systems & Communications, 1975: 12-28. [4] NAVA B, COISSON P, RADICELLA S M. A new version of the NeQuick ionosphere electron density model[J]. Journal of atmospheric and solar-terrestrial physics, 2008, 70(15): 1856-1862. DOI: 10.1016/j.jastp.2008.01.015 [5] BILITZA D, PEZZOPANE M, TRUHILK V, et al. The international reference ionosphere model: a review and description of an ionospheric benchmark[J]. Reviews of geophysics, 2022, 60(4). DOI: 10.1029/2022RG000792 [6] HUANG F, RUAN H B, LEI J H, et al. Empirical models of foF2 and hmF2 reconstituted by global ionosonde and reanalysis data and COSMIC observations[J]. Space weather, 2024, 22(4): e2023SW003848. DOI: 10.1029/2023SW00384 [7] 陈龙江, 甄卫民, 欧明, 等. 一种基于分步线性最优估计的全球中低纬区域电离层foF2重构方法[J]. 电波科学学报, 2021, 36(1): 36-42. [8] JONES W B, GALLET R M. Representation of diurnal and geographic variations of ionospheric data by numerical methods[J]. Journal of research of the national bureau of standards, 1962, 66(D): 419. DOI: 10.6028/jres.066d.043 [9] RUSH C M, POKEMPNER M, AANDERSON D N, et al. Improving ionospheric maps using theoretically derived values of foF2[J]. Radio science, 1983, 18(1): 195-107. DOI: 10.1029/RS018i001p00095 [10] RUSH C M, POKEMPNER M, ANDERSON D N, et al. Maps of foF2 derived from observations and theoretical data[J]. Radio science, 1984, 19(4): 1083-1097. DOI: 10.1029/RS019i004p01083 [11] E. A, ZHANG D H, XIAO Z, et al. Modeling ionospheric foF2 by using empirical orthogonal function analysis[J]. Annales geophysicae, 2011, 29(8): 1501-1515. DOI: 10.5194/ANGEO-29-1501-2011 [12] HOQUE M M, JAKOWSKI N. A new global empirical NmF2 model for operational use in radio systems[J]. Radio science, 2011, 46(6): 1-13. DOI: 10.1029/2011RS004807 [13] 陈林峰, 程云鹏. 基于COSMIC数据开展全球电离层foF2建模及变化特征研究[J]. 科学技术与工程, 2022, 22(34): 15036-15042. DOI: 10.3969/j.issn.1671-1815.2022.34.007 [14] LIU Z D, FANG H X, HOQUE M M, et al. A new empirical model of NmF2 based on CHAMP, GRACE, and COSMIC radio occultation[J]. Remote sensing, 2019, 11(11): 1386. DOI: 10.3390/rs11111386 [15] THEMENS D R, JAYACHANDRAN P T, GALKIN I, et al. The empirical Canadian high arctic ionospheric model (E-CHAIM): NmF2 and hmF2[J]. Journal of geophysical research: space physics, 2017, 122(8): 9015-9031. DOI: 10.1002/2017JA024398 [16] GOWTAM V S, TULASI R S T. An artificial neural network-based ionospheric model to predict NmF2 and hmF2 using long-term data set of FORMOSAT-3/COSMIC radio occultation observations: preliminary results[J]. Journal of geophysical research: space physics, 2017, 122(11): 11743-11755. DOI: 10.1002/2017JA024795 [17] TULASI R S, SAI G V, ARKA M, et al. The improved two-dimensional artificial neural network-based ionospheric model (ANNIM)[J]. Journal of geophysical research: space physics, 2018, 123(7): 5807-5820. DOI: 10.1029/2018JA025559 [18] LI W, HE C C, HU A D, et al. A new method for improving the performance of an ionospheric model developed by multi-instrument measurements based on artificial neural network[J]. Advances in space research, 2021, 67(1): 20-34. DOI: 10.1016/j.asr.2020.07.032 [19] WANG R P, ZHOU C, DENG Z X, et al. Predicting foF2 in the China region using the neural networks improved by the genetic algorithm[J]. Journal of atmospheric and solar-terrestrial physics, 2013(92): 7-17. DOI: 10.1016/j.jastp.2012.09.010 [20] 宋锐. 中国区域电离层foF2建模及其应用研究[D]. 北京: 中国地震局地震预测研究所, 2018. [21] GOWTAM V S, THLASI R S, RENINISCH B, et al. A new artificial neural network-based global three-dimensional ionospheric model (ANNIM-3D) using long-term ionospheric observations: preliminary results[J]. Journal of geophysical research: space physics, 2019, 124(6): 4639-4657. DOI: 10.1029/2019JA026540 [22] LI W, ZHAO D S, HE C Y, et al. Application of a multi-layer artificial neural network in a 3-D global electron density model using the long-term observations of COSMIC, Fengyun-3C, and digisonde[J]. Space weather, 2021, 19(3). DOI: 10.1029/2020sw002605 [23] HABARULEMA J B, OKOH D, BURESOVA D, et al. A global 3-D electron density reconstruction model based on radio occultation data and neural networks[J]. Journal of atmospheric and solar-terrestrial physics. 2021, 221(1): 105702. DOI: 10.1016/j.jastp.2021.105702 [24] YANG D, FANG H X. A low-latitude three-dimensional ionospheric electron density model based on radio occultation data using artificial neural networks with prior knowledge[J]. Space weather, 2023, 21(1). DOI: 10.1029/2022sw003299 [25] HABARULEMA J B, OKOH D, BURESOVA D, et al. A storm-time global electron density reconstruction model in three-dimensions based on artificial neural networks[J]. Advances in space research, 2024. DOI: 10.1016/j.asr.2024.02.014 [26] ZHOU Y, LIU J, LI S H, et al. Ionospheric TEC prediction based on ensemble learning models[J]. Space weather, 2024, 22(3): e2023SW003790. DOI: 10.1029/2023SW003790 [27] LINTY N, FARASIN A , FAVENZA A, et al. Detection of GNSS ionospheric scintillations based on machine learning decision tree[J]. IEEE transactions on aerospace and electronic systems, 2018, 55(1): 303-317. DOI: 10.1109/TAES.2018.2850385 [28] YANG K F, CHU Y H, SU C L, et al. An examination of FORMOSAT-3/COSMIC ionospheric electron density profile: Data quality criteria and comparisons with the IRI model[J]. Terrestrial, atmospheric and oceanic sciences, 2009, 20(1): 193-206. DOI: 10.3319/TAO.2007.10.05.01(F3C [29] BREIMAN L. Random forests[J]. Machine learning, 2001(45): 5-32. DOI: 10.1023/A:1010933404324 [30] WILLISCROFT L A, POOLE A W V. Neural networks, foF2, sunspot number and magnetic activity[J]. Geophysical research letters, 1996, 23(24): 3659-3662. DOI: 10.1029/96GL03472 -
点击查看大图
图(8) / 表(2)
计量
- 文章访问数: 32
- HTML全文浏览量: 13
- PDF下载量: 2
- 被引次数: 0
