粒子群优化卷积神经网络GNSS-IR土壤湿度反演方法

doi:10.11947/j.AGCS.2023.20220277

测绘学报 ›› 2023, Vol. 52 ›› Issue (8): 1286-1297.doi: 10.11947/j.AGCS.2023.20220277

粒子群优化卷积神经网络GNSS-IR土壤湿度反演方法

何佳星¹, 郑南山^1,2, 丁锐^1,2, 张克非^1,2, 陈天悦¹

1. 中国矿业大学环境与测绘学院, 江苏徐州 221116;
2. 中国矿业大学自然资源部国土环境与灾害监测重点实验室, 江苏徐州 221116

收稿日期:2022-04-26 修回日期:2023-01-31 发布日期:2023-09-07
通讯作者: 郑南山 E-mail:znshcumt@163.com
作者简介:何佳星(1999-),男,硕士生,研究方向为GNSS遥感。E-mail:HEJiaxing@cumt.edu.cn
基金资助:
国家自然科学基金(41974039);国家自然科学基金联合重点(U22A20569);自然资源部国土环境与灾害监测重点实验室开放基金(LEDM2021B11);国家重点研发计划课题(2019YFC1805003);江苏省研究生科研与实践创新计划(KYCX22＿2594);中国矿业大学研究生创新计划(2022WLJCRCZL253)

A GNSS-IR soil moisture inversion method based on the convolutional neural network optimized by particle swarm optimization

HE Jiaxing¹, ZHENG Nanshan^1,2, DING Rui^1,2, ZHANG Kefei^1,2, CHEN Tianyue¹

1. School of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China;
2. MNR Key Laboratory of Land Environment and Disaster Monitoring, China University of Mining and Technology, Xuzhou 221116, China

Received:2022-04-26 Revised:2023-01-31 Published:2023-09-07
Supported by:
The National Natural Science Foundation of China (No. 41974039); The Joint Funds of the National Natural Science Foundation of China (No. U22A20569); The Open Research Fund of Key Laboratory of Land Environment and Disaster Monitoring, Ministry of Natural Resources, China University of [JP5]Mining and Technology (No. LEDM2021B11); The National Key Research and Development Program (No. 2019YFC1805003); The Postgraduate Research & Practice Innovation Program of Jiangsu Province (No. KYCX22＿2594); The Graduate Innovation Program of China University of Mining and Technology (No. 2022WLJCRCZL253)

摘要/Abstract

摘要： 全球卫星导航系统干涉测量法(GNSS-interferometric reflectometry,GNSS-IR)是一种新兴对地观测遥感技术,利用该方法能实现土壤湿度监测,具有很高的应用潜力。针对土壤湿度反演的建模问题,本文构建一种集成粒子群优化算法(particle swarm optimization,PSO)和卷积神经网络(convolutional neural network,CNN)的GNSS-IR土壤湿度反演模型,将多颗GPS卫星两个频点信噪比(signal-to-noise ratio,SNR)观测数据提取的特征参数作为模型输入,通过粒子群算法求解卷积神经网络超参数,对模型进行优化实现高精度反演。以P041站点为例详细描述了模型建立过程,本文方法的均方根误差为0.015 0,相较于基于单星线性、多星线性、未优化CNN和BP神经网络模型分别降低约60%、27%、31%和21%;并通过位于不同地理环境的COPR、P183、P341站点验证模型的可靠性和适用性。试验结果表明,融合多源观测数据建立PSO优化CNN的GNSS-IR土壤湿度反演模型,能有效反演土壤湿度,一定程度上抑制了不同下垫面环境的影响,具有较强的适用性。

关键词: 土壤湿度, GNSS-IR, SNR, 卷积神经网络, 粒子群

Abstract: Global navigation satellite system interferometric reflectometry (GNSS-IR) is an emerging remote sensing technique for earth observation, which can be applied to monitor soil moisture and has a prosperous application prospect. Aiming at the modeling problem of soil moisture inversion, we developed a GNSS-IR soil moisture inversion model integrating particle swarm optimization (PSO) and convolutional neural network (CNN). The metrics extracted from two frequency signal-to-noise ratio (SNR) observation data of GPS satellites were used as the input, and particle swarm optimization algorithm was used to optimize the hyperparameters of the convolutional neural network. Detailed modeling was carried out with the site of P041. Its root mean square error is 0.015 0, which is 60%, 27%, 31% and 21% lower than that based on single satellite linear, multi-satellite linear, conventional CNN and back propagation (BP) models; The applicability of the model was verified by COPR, P183 and P341 sites. The results indicate that the integrated GNSS-IR soil moisture inversion model based on PSO-CNN can effectively restrain the influence of the land surface environmental factors within consideration of multi-source observation data.

Key words: soil moisture, GNSS-IR, SNR, convolutional neural network, particle swarm optimization

中图分类号:

P227

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.

HE Jiaxing, ZHENG Nanshan, DING Rui, ZHANG Kefei, CHEN Tianyue. A GNSS-IR soil moisture inversion method based on the convolutional neural network optimized by particle swarm optimization[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(8): 1286-1297.

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] EDOKOSSI K, CALABIA A, JIN Shuanggen, et al. GNSS-reflectometry and remote sensing of soil moisture: a review of measurement techniques, methods, and applications[J]. Remote Sensing, 2020, 12(4): 614.
[3] ADELI S, SALEHI B, MAHDIANPARI M, et al. Wetland monitoring using SAR data: a meta-analysis and comprehensive review[J]. Remote Sensing, 2020, 12(14): 2190.
[4] MARTIN-NEIRA M. A passive reflectometry and interferometry system (PARIS): application to ocean altimetry[J]. ESA Journal, 1993, 17(4): 331-355.
[5] RODRIGUEZ-ALVAREZ N, BOSCH-LLUIS X, CAMPS A, et al. Soil moisture retrieval using GNSS-R techniques: experimental results over a bare soil field[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(11): 3616-3624.
[6] LARSON K M. A new way to detect volcanic plumes[J]. Geophysical Research Letters, 2013, 40(11): 2657-2660.
[7] SCHIAVULLI D, GHAVIDEL A, CAMPS A, et al. GNSS-R wind-dependent polarimetric signature over the ocean[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(12): 2374-2378.
[8] WANG Wang, HE Xiufeng, ZHANG Zhang, et al. Angle dependence analysis method to determine SNR arc applied to GNSS-MR sea level retrieval[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(2)14-26.
[9] HOLDEN L D, LARSON K M. Ten years of Lake Taupō surface height estimates using the GNSS interferometric reflectometry[J].Journal of Geodesy, 2021, 95(7): 74.
[10] 边少锋, 周威, 刘立龙, 等. 小波变换与滑动窗口相结合的GNSS-IR雪深估测模型[J]. 测绘学报, 2020, 49(9): 1179-1188.DOI: 10.11947/j.AGCS.2020.20200268. BIAN Shaofeng, ZHOU Wei, LIU Lilong, et al. GNSS-IR model of snow depth estimation combining wavelet transform with sliding window[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(9)1179-1188.DOI: 10.11947/j.AGCS.2020.20200268.
[11] 刘经南, 邵连军, 张训械. GNSS-R研究进展及其关键技术[J]. 武汉大学学报(信息科学版), 2007, 32(11):955-960. LIU Jingnan, SHAO Lianjun, ZHANG Xunxie. Advances in GNSS-R studies and key technologies[J]. Geomatics and Information Science of Wunan University, 2007, 32(11):955-96.
[12] 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.
[13] 裴悦琨, 韩心新. GNSS-R探测土壤湿度综述[J]. 大地测量与地球动力学, 2021, 41(2):140-144. PEI Yuekun, HAN Xinxin. Overview of GNSS-R technique for soil moisture detection[J]. Journal of Geodesy and Geodynamics, 2021, 41(2):140-144.
[14] 金双根, 张勤耘, 钱晓东. 全球导航卫星系统反射测量(GNSS+R)最新进展与应用前景[J]. 测绘学报, 2017, 46(10):1389-1398. DOI: 10.11947/j.AGCS.2017.20170282. JIN Shuanggen, ZHANG Qinyun, QIAN Xiaodong. New progress and application prospects of global navigation satellite system reflectometry (GNSS+R)[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1389-1398. DOI: 10.11947/j.AGCS.2017.20170282.
[15] 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.
[16] VEY S, GVNTNER A, WICKERT J, et al. Long-term soil moisture dynamics derived from GNSS interferometric reflectometry: a case study for Sutherland, South Africa[J]. GPS Solutions, 2016, 20(4): 641-654.
[17] HAN Mutian, ZHU Yunlong, YANG Dongkai, et al. A semi-empirical SNR model for soil moisture retrieval using GNSS SNR data[J]. Remote Sensing, 2018, 10(2): 280.
[18] 荆丽丽, 杨磊, 汉牟田, 等. GNSS-IR双频数据融合的土壤湿度反演方法[J]. 北京航空航天大学学报, 2019, 45(6): 1248-1255. JING Lili, YANG Lei, HAN Moutian,et al. Soil moisture inversion method based on GNSS-IR dual frequency data fusion[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(6): 1248-1255.
[19] 梁月吉, 任超, 黄仪邦, 等. 利用GPS-IR监测土壤湿度的多星线性回归反演模型[J]. 测绘学报, 2020, 49(7):833-842. DOI: 10.11947/j.AGCS.2020.20190095. LIANG Yueji, REN Chao, HUANG Yibang, et al. Multi-star linear regression retrieval model for monitoring soil moisture using GPS-IR[J].Acta Geodaetica et Cartographica Sinica,2020, 49(7):833-842. DOI: 10.11947/j.AGCS.2020.20190095.
[20] REN Chao, LIANG Yueji, LU Xianjian, et al. Research on the soil moisture sliding estimation method using the LS-SVM based on multi-satellite fusion[J]. International Journal of Remote Sensing, 2019, 40(5-6): 2104-2119.
[21] CHEW C, SMALL EE, 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.
[22] 梁勇, 杨磊, 吴秋兰, 等. 地表粗糙度影响下的GNSS-R土壤湿度反演仿真分析[J]. 武汉大学学报(信息科学版), 2018, 43(10): 1546-1552. LIANG Yong, YANG Lei, WU Qiulan, et al. Simulation of soil roughness impact in GNSS-R soil moisture retrieval[J]. Geomatics and Information Science of Wuhan University, 2018, 43(10): 1546-1552.
[23] 郑南山, 丰秋林, 刘晨, 等. GPS反射信号信噪比与NDVI相关性研究[J]. 武汉大学学报(信息科学版), 2019, 44(10): 1423-1429. ZHENG Nanshan, FENG Qiulin, LIU Chen, et al. Relationship analysis between GPS reflection signal SNR and NDVI[J]. Geomatics and Information Science of Wuhan University, 2019, 44(10): 1423-1429.
[24] LI Xiaohui,YANG Dongkai,YANG Jingsong, et al. Analysis of coastal wind speed retrieval from CYGNSS mission using artificial neural network[J]. Remote Sensing of Environment, 2021, 260: 112454.
[25] EROGLU O, KURUM M, BOYD D, et al. Highspatio-temporal resolution CYGNSS soil moisture estimates using artificial neural networks[J]. Remote Sensing, 2019, 11(19): 2272.
[26] WAN Wei, LARSON K M, SMALL E E, et al. Using geodetic GPS receivers to measure vegetation water content[J].GPS Solutions, 2015, 19(2): 237-248.
[27] LARSON K M, SMALL E E, GUTMANN E D, et al. Use of GPS receivers as a soil moisture network for water cycle studies[J]. Geophysical Research Letters, 2008, 35(24): L24405.
[28] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[29] POLI R, KENNEDY J, BLACKWELL T. Particle swarmoptimization[J].Swarm Intelligence, 2007,1: 33-57.
[30] CHEW C C, SMALL E E, LARSON K M, et al. Effects of near-surface soil moisture on GPS SNR data: development of a retrieval algorithm for soil moisture[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1): 537-543.
[31] CHEW C C, SMALL E E, LARSON K M, et al. Vegetation sensing using GPS-interferometric reflectometry: theoretical effects of canopy parameters on signal-to-noise ratio data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(5): 2755-2764.
[32] RAN Qishun, ZHANG Bao, YAO Yibin, et al. Editing arcs to improve the capacity of GNSS-IR for soil moisture retrieval in undulating terrains[J].GPS Solutions, 2022, 26(1): 1-11.
[33] WANG Xiaolei, HE Xiufeng, ZHANG Qin, et al.The preliminary discussion of the potential of GNSS-IR technology for terrain retrievals[J].Journal of Geodesy and Geoinformation Science, 2021, 4(2): 79-88.
[34] CLERC M. The swarm and the queen: towards a deterministic and adaptive particle swarm optimization[C]//Proceedings of the 1999 Congress on Evolutionary Computation-CEC99. Washington. DC: IEEE, 2002: 1951-1957.
[35] TUPPADUNG Y, KURUTACH W. Comparing nonlinear inertia weights and constriction factors in particle swarmoptimization[J]. International Journal of Knowledge-Based and Intelligent Engineering Systems, 2011, 15(2): 65-70.
[36] LARSON K M, BRAUN J J, SMALL E E, et al. GPS multipath and its relation to near-surface soil moisture content[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2010, 3(1): 91-99.

粒子群优化卷积神经网络GNSS-IR土壤湿度反演方法

A GNSS-IR soil moisture inversion method based on the convolutional neural network optimized by particle swarm optimization

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]	张蒙蒙, 李伟, 刘欢, 赵旭东, 陶然. 基于形态变换与空间逻辑聚合的高光谱森林树种分类[J]. 测绘学报, 2023, 52(7): 1202-1211.
[2]	顾小虎, 李正军, 缪健豪, 李星华, 沈焕锋. 高分遥感影像双通道并行混合卷积分类方法[J]. 测绘学报, 2023, 52(5): 798-807.
[3]	赵冰冰, 谭骁勇, 杨学习, 石岩, 邓敏. 融合地理条件驱动效应和图卷积的土地利用演化模拟CA模型[J]. 测绘学报, 2023, 52(5): 831-842.
[4]	余东行, 徐青, 赵传, 郭海涛, 卢俊, 林雨准, 刘相云. 注意力引导特征融合与联合学习的遥感影像场景分类[J]. 测绘学报, 2023, 52(4): 624-637.
[5]	张永显, 马国锐, 崔志祥, 张志军. 面向大视角差的无人机影像序列学习型特征匹配[J]. 测绘学报, 2023, 52(2): 230-243.
[6]	孙根云, 王鑫, 安娜, 张爱竹. 基于多源遥感的大尺度高分辨率不透水面深度学习提取方法[J]. 测绘学报, 2023, 52(2): 272-282.
[7]	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.
[8]	张广斌, 高贤君, 冉树浩, 杨元维, 李丽珊, 张妍. 高分遥感影像云雪共存区轻量云高精度检测方法[J]. 测绘学报, 2023, 52(1): 93-107.
[9]	杨敏, 陈果, 李连营, 黄浩然, 苗静, 晏雄锋. 序列卷积神经网络支持下线状地图目标的分段方法[J]. 测绘学报, 2023, 52(1): 108-116.
[10]	张爽, 陈西宏, 刘强, 刘赞, 王庆力. 耦合PSO与扩展RBF神经网络估计NWM模型ZTD计算精度[J]. 测绘学报, 2022, 51(9): 1911-1919.
[11]	陶庭叶, 李江洋, 朱勇超, 汪俊涛, 陈皓, 时梦杰. 阶段模型修正的星载GNSS-R土壤湿度反演方法[J]. 测绘学报, 2022, 51(9): 1942-1950.
[12]	孙和平, 周江存, 徐建桥. SNREI地球形变理论模拟研究进展[J]. 测绘学报, 2022, 51(7): 1119-1129.
[13]	王洁, 王娜子, 徐天河, 高凡, 贺匀峤. 组合GNSS观测值反演海面高度[J]. 测绘学报, 2022, 51(2): 201-211.
[14]	郝雨时, 孙剑伟, 隋心, 徐爱功, 施闯. 顾及ISB/IFB的多GNSS RTK/INS紧组合导航方法[J]. 测绘学报, 2022, 51(11): 2265-2272.
[15]	王笑蕾, 何秀凤, 宋敏峰, 陈殊, 牛紫瑾. 多模多频GNSS-IR水位反演中的频间偏差分析及改正[J]. 测绘学报, 2022, 51(11): 2328-2338.