首页|一种土地类型标签精细化的GNSS-R 土壤湿度反演方法

一种土地类型标签精细化的GNSS-R 土壤湿度反演方法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
针对传统的星基全球导航卫星系统反射测量(global navigation satellite system-reflectometry,GNSS-R)技术在土壤湿度反演中对土地覆盖类型信息利用不全面的问题,引入基于国际地圈生物圈计划(international geosphere bio-sphere programme,IGBP)分类的土地覆盖类型数据,考虑不同土地类型间的相似性和差异性,根据语义关系设计了精细化的特征标签,并将其加入BP(back propagation)神经网络中构建土壤湿度反演模型.利用该方法得到的土壤湿度与参考值的相关系数为0.85,均方根误差为0.060 cm3/cm3,相比于已有的IGBP编号标签法,反演精度提升了 7.7％.结果表明,精细化土地覆盖类型标签法可以更大程度地利用土地覆盖信息,不依赖植被、地表粗糙度等辅助数据,有效实现土壤湿度反演.
A Refined Land Type Digitization Method of GNSS-R Soil Moisture Inversion
Objectives:Global navigation satellite system-reflectometry(GNSS-R)is a new method for measuring soil moisture with rich signal sources,which utilizes GNSS reflected signals for detecting the physical parameters of the reflector with cheap cost and high spatial resolution.Methods:Considering the fact that in the traditional GNSS-R soil moisture retrieval,the data of land cover types is ignored or simpli-fied,this paper makes detailed labels about the land cover types based on the definition of international geo-sphere biosphere programme(IGBP)considering the similarities and differences between different land cover types,and uses back propagation(BP)neural network to establish soil moisture inversion models.The main work is to replace the IGBP number labels with refined feature labels.After the extraction,matching and quality control of cyclone global navigation satellite system(CYGNSS)and soil moisture active passive(SMAP)data,the dataset is randomly divided into training set and testing set.Then BP algorithm is used for training neural networks to establish soil moisture retrieval model.Results:The correlation coefficient between retrieved soil moisture and reference value is 0.85,and the root mean square error(RMSE)is 0.060 cm3/cm3.Meanwhile,the soil moisture obtained by CYGNSS and SMAP have good spatial and tem-poral consistency,but the inversion performance varies on the different land cover types.On the barren or sparsely vegetated land type,the RMSE is smallest and on the evergreen ncedlcleaf forest land type,the RMSE is largest.Meanwhile on the shrublands,grasslands and croplands land types,the inversion effect is better than permanent wetlands,urban/built-up and cropland/natural vegetation mosaic land types.Com-pared with the existing IGBP numbering and labeling method,the accuracy has been improved by 7.7％.The precision improvement of deciduous broadleaf forest,closed shrublands and woody savannas types is significant.Conclusions:The proposed method of refined land type digitization can effectively retrieve soil moisture without relying on other auxiliary data such as vegetation opacity and surface roughness,and it is feasible and effective.

global navigation satellite system-reflectometry(GNSS-R)soil moistureIGBP land cover typesrefined land type digitizationback propagation neural network

郭斐、董桂芳、朱逸凡、张小红

展开 >

武汉大学测绘学院,湖北 武汉,430079

GNSS反射测量技术 土壤湿度 IGBP 土地覆盖类型 标签精细化 BP神经网络

国家自然科学基金湖北省自然科学基金湖北省重点研发计划

420740292021CFA0392022BAA054

2024

10.13203/j.whugis20220803

武汉大学学报(信息科学版)
武汉大学

武汉大学学报(信息科学版)

CSTPCD北大核心
影响因子：1.072
ISSN：1671-8860
年,卷(期)：2024.49(1)
  • 2
  • 5