结合机器学习的GNSS-IR多卫星双频组合土壤湿度反演

doi:10.13474/j.cnki.11-2246.2023.0302

测绘通报 ›› 2023, Vol. 0 ›› Issue (10): 98-104.doi: 10.13474/j.cnki.11-2246.2023.0302

结合机器学习的GNSS-IR多卫星双频组合土壤湿度反演

聂士海¹, 王龙¹, 王梦柯¹, 李鹏¹, 梁磊¹, 黄丹妮¹, 刘斌²

1. 滁州学院地理信息与旅游学院, 安徽滁州 239000;
2. 南京信息工程大学遥感与测绘工程学院, 江苏南京 210044

收稿日期:2023-06-21 修回日期:2023-08-28 发布日期:2023-10-28
通讯作者: 王梦柯。E-mail:mengkewang@sdust.edu.cn
作者简介:聂士海(1993-),男,硕士,助教,研究方向为GNSS-IR地表参数反演。E-mail:nsh1017@chzu.edu.cn
基金资助:
国家自然科学基金(42204091;42304095);安徽高校自然科学研究重点项目(KJ2021A1077;KJ2021A1084;2023AH051634);安徽省社科规划青年项目(AHSKQ2022D072);安徽省高校自然科学研究一般项目(KJ2021B08;KJ2021B07);滁州学院校级科研项目(2022XJYB03);大学生创新创业训练计划(2023cxxl1949;2023CXXL013)

GNSS-IR multi-satellite dual-frequency combination soil moisture inversion combined with machine learning

NIE Shihai¹, WANG Long¹, WANG Mengke¹, LI Peng¹, LIANG Lei¹, HUANG Danni¹, LIU Bin²

1. School of Geographic Information and Tourism, Chuzhou University, Chuzhou 239000, China;
2. School of Remote Sensing and Surveying and Mapping Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China

Received:2023-06-21 Revised:2023-08-28 Published:2023-10-28

摘要/Abstract

摘要： 为提高土壤湿度反演精度,并克服基于单一卫星、单一频点开展土壤湿度反演存在的不足,本文提出了一种结合机器学习的GNSS-IR多卫星双频组合土壤湿度反演方法,将GNSS卫星L1、L2频点上SNR作为数据源进行土壤湿度反演研究,采用BP和RBF神经网络算法构建土壤湿度预测模型,并与一元线性回归预测模型进行对比分析。试验结果表明:①相对于单卫星而言,多卫星组合的土壤湿度反演增加了有效卫星利用率,并提高了土壤湿度反演的精度;②多星组合的L1、L2双频均值融合延迟相位观测值与土壤湿度的相关系数为0.956,均优于L1、L2频点反演结果;③BP、RBF神经网络模型预测结果精度均优于ULR模型预测结果。

关键词: 多卫星, GNSS-IR, 均值融合, 土壤湿度, 神经网络

Abstract: In order to improve the accuracy of soil moisture inversion and overcome the shortcomings of soil moisture inversion based on single satellite and single frequency point, this paper proposes a soil moisture inversion method based on GNSS-IR multi-satellite dual-frequency combination combined with machine learning. By using the SNR of GNSS satellite L1 and L2 frequency points as the data source, the soil moisture inversion is studied. The BP and RBF neural network algorithms are used to construct the soil moisture prediction model, and compared with the linear regression prediction model. The experimental results show that:①Compared with the single satellite, the soil moisture inversion of multi-satellite combination increases the effective satellite utilization rate and improves the accuracy of soil moisture inversion. ②The correlation coefficient between L1 and L2 dual-frequency mean fusion delay phase observations of multi-satellite combination and soil moisture is 0.956, which is better than the inversion results of L1 and L2 frequency points. ③The prediction accuracy of BP and RBF neural network models is better than that of ULR model.

Key words: multi-satellite, GNSS-IR, mean fusion, soil moisture, neural network

中图分类号:

P237

聂士海, 王龙, 王梦柯, 李鹏, 梁磊, 黄丹妮, 刘斌. 结合机器学习的GNSS-IR多卫星双频组合土壤湿度反演[J]. 测绘通报, 2023, 0(10): 98-104.

NIE Shihai, WANG Long, WANG Mengke, LI Peng, LIANG Lei, HUANG Danni, LIU Bin. GNSS-IR multi-satellite dual-frequency combination soil moisture inversion combined with machine learning[J]. Bulletin of Surveying and Mapping, 2023, 0(10): 98-104.

参考文献

[1] SENEVIRATNE S I,CORTI T,DAVIN E L,et al. Investigating soil moisture-climate interactions in a changing climate: a review[J]. Earth-Science Reviews,2010,99(3/4): 125-161.
[2] LARSON K M. GPS interferometric reflectometry: applications to surface soil moisture,snow depth,and vegetation water content in the western United States[J]. Wiley Interdisciplinary Reviews: Water,2016,3(6): 775-787.
[3] 张双成,戴凯阳,南阳,等. GNSS-MR技术用于雪深探测的初步研究[J]. 武汉大学学报(信息科学版),2018,43(2): 234-240.
[4] 吴学睿,金双根,宋叶志,等. GNSS-R/IR土壤水分遥感研究现状[J]. 大地测量与地球动力学,2019,39(12): 1277-1282.
[5] LARSON K M,SMALL E E,GUTMANN E,et al. Using GPS multipath to measure soil moisture fluctuations: initial results[J]. GPS Solutions,2008,12(3): 173-177.
[6] 孙波,梁勇,汉牟田,等. 基于GA-SVM的GNSS-IR土壤湿度反演方法[J]. 北京航空航天大学学报,2019,45(3): 486-492.
[7] 陈堃,沈飞,曹新运,等. 基于深度置信网络的GNSS-IR土壤湿度反演[J]. 测绘通报,2020(9): 100-105.
[8] 杨磊,吴秋兰,张波,等. SVRM辅助的北斗GEO卫星反射信号土壤湿度反演方法[J]. 北京航空航天大学学报,2016,42(6): 1134-1141.
[9] 尹子明,孟凡玉,陈明剑,等. 卫星导航数据质量分析[J]. 全球定位系统,2016,41(1): 54-59.
[10] 吴丹,王利,张勤,等. GNSS数据质量评估软件的实现及验证分析[J]. 测绘科学技术学报,2015,32(4): 344-348.
[11] 李婷,张显云,邓小东,等. 顾及多径环境差异和粗差的GNSS-MR土壤湿度反演[J]. 遥感学报,2021,25(6): 1324-1337.
[12] ROUSSEL N,FRAPPART F,RAMILLIEN G,et al. Detection of soil moisture variations using GPS and GLONASS SNR data for elevation angles ranging from 2° to 70°[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(10): 4781-4794.
[13] ZHANG Xianyun,NIE Shihai,ZHANG Chunkang,et al. Soil moisture estimation based on triple-frequency multipath error[J]. International Journal of Remote Sensing,2021,42(15): 5953-5968.
[14] YU Kegen,LI Yunwei,CHANG Xin. Snow depth estimation based on combination of pseudorange and carrier phase of GNSS dual-frequency signals[J]. IEEE Transactions on Geoscience and Remote Sensing,2019,57(3): 1817-1828.
[15] CHEW C,SMALL E E,LARSON K M. An algorithm for soil moisture estimation using GPS-interferometric reflectometry for bare and vegetated soil[J]. GPS Solutions,2016,20(3): 525-537.

结合机器学习的GNSS-IR多卫星双频组合土壤湿度反演

GNSS-IR multi-satellite dual-frequency combination soil moisture inversion combined with machine learning

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]	刘银涛, 任超, 王俊男, 张炎, 何广焕. RSA-BP组合模型在GNSS高程拟合中的应用[J]. 测绘通报, 2023, 0(9): 46-51.
[2]	魏德宏, 禤键豪, 杨嘉伟, 张兴福, 余旭. 基于深度BP/ELMAN神经网络的山区GNSS高程转换精度分析[J]. 测绘通报, 2023, 0(9): 113-116,143.
[3]	姚春静, 余正, 王洁, 钱琛, 徐俊豪. 海底底质分类支持下的WorldView-3多光谱影像浅海海域水深反演[J]. 测绘通报, 2023, 0(7): 25-31.
[4]	张清波, 严加栋. 融合自适应最优邻域和卷积神经网络的三维点云分类[J]. 测绘通报, 2023, 0(7): 177-182.
[5]	沈鑫甦, 嵇灵. 面向遥感地类变化检测的U型深度学习神经网络改进方法[J]. 测绘通报, 2023, 0(6): 93-97,103.
[6]	王丽梅, 王延正. 基于高分辨率遥感影像的建筑物提取[J]. 测绘通报, 2023, 0(6): 180-183.
[7]	杜宇峰, 黄亮, 赵子龙, 李国柱. 基于DETR的高分辨率遥感影像滑坡体识别与检测[J]. 测绘通报, 2023, 0(5): 16-20.
[8]	曹小燕, 满新耀, 汪继平, 麦荣章, 郭云开. 基于鸟群优化BP神经网络的滑坡处治后变形预测[J]. 测绘通报, 2023, 0(5): 27-31.
[9]	姚萌萌, 李晓明, 王伟玺, 谢林甫, 黄俊杰, 黄鸿盛, 汤圣君. 几何特征与神经网络联合优化的室内三维点云语义分割方法[J]. 测绘通报, 2023, 0(5): 56-61.
[10]	张全旺, 郭辉. 采煤拉张裂隙区土壤有机质高光谱反演[J]. 测绘通报, 2023, 0(5): 78-83,134.
[11]	黄桦, 葛为燎, 刘微微, 钱荣荣, 李杰. 利用倾斜影像重建点云的建筑物变化检测[J]. 测绘通报, 2023, 0(5): 125-129.
[12]	吕富强, 唐诗华, 张炎, 宋晓辉, 胡鹏程, 李翥. SSA-BP神经网络在无人机点云孔洞修补的应用[J]. 测绘通报, 2023, 0(5): 130-134.
[13]	齐建伟, 王伟峰, 张乐, 王光彦. 基于改进DeepLabV3+算法的遥感影像建筑物变化检测[J]. 测绘通报, 2023, 0(4): 145-149.
[14]	李子彧, 周维勋, 耿万轩. 联合类别筛选与重排序的交叉视角图像地理定位[J]. 测绘通报, 2023, 0(2): 40-45.
[15]	张永彬, 刘雅辉, 刘明月, 满卫东, 宋唐雷, 李春雨. 基于Relief F与卷积神经网络的湿地植物群落精细分类[J]. 测绘通报, 2023, 0(2): 58-64.