摘要
为快速反演较高精度土壤水分,提出用遗传算法优化后的神经网络辅以多源遥感数据的方法进行地表土壤水分反演。首先建立4层神经网络并用遗传算法优化此网络,之后以雷达数据不同极化(VV、VH、VH/VV)的后向散射系数、雷达入射角、光学数据的归一化植被指数(NDVI)、以及高程数据作为网络的输入,土壤水分数据为输出,对网络进行训练与仿真,再运用地表实际测量数据与反演数据做对比验证。结果表明:反演结果与实际测量数据相关性良好,R2可达0. 79。采用遗传算法对神经网络优化的土壤水分反演方法可行,且添加光学数据等辅助数据后土壤水分反演效果更优,为多源遥感土壤水分的协同反演研究提供新思路。
In order to quickly invert higher precision soil moisture,this paper used the genetic algorithm optimized neural network and multi-source remote sensing data to invert the surface soil moisture. First,a four-layer neural network was established and the network was optimized by genetic algorithm. Then,we used the backscattering coefficient of radar data with different polarizations( VV,VH,VH/VV),radar incident angle,normalized vegetation index( NDVI) of optical data,and elevation data as input to neural network,the soil moisture data as the output to train and simulate the network. Finally,the inversion data was verified by the actual measured data of the surface. The results showed that the correlation between the inversion data and the measured data is high( R2= 0. 79). The method of genetic algorithm optimized neural network is feasible to calculate soil moisture content,and the soil water inversion effect is better after adding auxiliary data such as optical data. This study provides a new idea for the collaborative inversion of soil moisture in the multi-source remote sensing.
引文
[1]BARRETT B,WHELAN P,DWYER E. Detecting changes in surface soil moisture content using differential SAR interferometry[J]. International Journal for Remote Sensing,2013,34(20):7091-7112.
[2]姜良美.基于微波遥感农田土壤水分反演研究[D].湘潭:湖南科技大学,2012.
[3]王大龙,舒英格.土壤含水量测定方法研究进展[J].山地农业生物学报,2017,36(2):61-65.
[4]高峰,王介民,孙成权,等.微波遥感土壤湿度研究进展[J].遥感技术与应用,2001,16(2):97-102.
[5]孔金玲,甄珮珮,李菁菁,等.基于新的组合粗糙度参数的土壤水分微波遥感反演[J].地理与地理信息科学,2016,32(3):34-38.
[6]余凡,赵英时.合成孔径雷达反演裸露地表土壤水分的新方法[J].武汉大学学报(信息科学版),2010,35(3):317-321.
[7]韩玲,秦小宝,陈鲁皖.双极化SA R数据反演裸露地表土壤水分[J].测绘工程,2018,27(2):7-12.
[8]BAGHDADI N,CRESSON R,HAJJ M E,et al. Estimation of soil parameters over bare agriculture areas from Cband polarimetric SAR data using neural networks[J]. Hydrology&Earth System Sciences Discussions,2012,9(3):1607-1621.
[9]SANTI E,PALOSCIA S,PETTINATO S,et al. Comparison between SAR soil moisture estimates and hydrological model simulations over the scrivia test site[J]. Remote Sensing,2013,5(10):4961-4976.
[10]WANG Xin,GE Lingling,LI Xiaojing. Evaluation of filters for envisat asar speckle suppression in pasture area[J]. ISPRS Annals of the Photogrammetry,Remote Sensing and Spatial Information Sciences,2012,I-7:341-346.
[11]HOSSAIN A K M,EASSON G. Soil moisture estimation in South-Eastern New Mexico using high resolution synthetic aperture radar(SAR)data[J]. Geosciences,2016,6(1):1.
[12]余凡,赵英时,李海涛.基于遗传BP神经网络的主被动遥感协同反演土壤水分[J].红外与毫米波学报,2012,31(3):283-288.
[13]谢小山.基于遗传算法和BP神经网络的铁路客运量预测研究[D].成都:西南交通大学,2010.
[14]刘浩然,赵翠香,李轩,等.一种基于改进遗传算法的神经网络优化算法研究[J].仪器仪表学报,2016,37(7):1573-1580.
[15]哈斯巴干,马建文,周自江,等.基于气象数据与AVHRR热红外数据的人工神经网络分类方法[J].中国科学院大学学报,2003,20(3):328-333.
[16]刘丽娜.基于遗传优化BP神经网络算法的土壤含水量反演研究[D].成都:电子科技大学,2011.
[17]刘伟,施建成,余琴,等.地表土壤水分与雷达后向散射系数及入射角之间关系研究[J].国土资源遥感,2004(3):14-17.