Inversion of soil moisture in bare soil based on multispectral remote sensing
-
摘要: 矿区排土场的土壤含水量监测研究在矿产资源开发、生态恢复及干旱预警等方面具有重要意义。以我国东部草原区胜利露天矿北排土场土壤为试验材料,使用Spequoia多光谱相机和ECH2O土壤水分传感器对4种不同深度(1 cm、3 cm、5 cm、10 cm)的土柱样本每天10:00至14:00持续监测,采集到4个波段(550 nm、660 nm、735 nm、790 nm)处的土壤光谱反射率和土壤含水量数据,分别使用偏最小二乘回归法、岭回归法、反向传播(BP)神经网络三种方法建立单波段或多波段光谱反射率组合作为反演因子的土壤含水量反演模型。结果表明,偏最小二乘回归法、岭回归法反演精度较低,R2最高仅为0606。以绿(550 nm)、红边(735 nm)、近红外 (790 nm)三波段组合作为反演因子的反向传播神经网络(G-R-N-BP)模型反演效果最佳,其对1 cm、3 cm、5 cm、10 cm深度土壤含水量反演模型的决定系数(R2)分别为0866、0800、0975、0911,均方根误差(RMSE)分别为0333、0361、0103、0315,最佳反演深度为5 cm。本研究为矿区地表水分监测提供了重要的理论依据与实践应用价值。Abstract: The monitoring of soil water content in the dumping area of mining area is of great significance to the development of mineral resources,ecological restoration and early warning of drought in ChinaIn this paper,four different depths(1cm,3 cm,5 cm,10 cm) of soil samples were continuously monitored from 10:00 to 14:00 using Spequoia multispectral camera and ECH2O soil moisture sensorSoil spectral reflectance of four bands(550 nm,660 nm,735 nm,790 nm) and soil water content data were collectedThe soil water content inversion model with singleband or multiband spectral reflectance combination as the inversion factor was established by using the methods of partial least squares regression,ridge regression and back propagation(BP) neural networkThe results show that the inversion accuracy of the two regression methods is low,and the highest R2 is only 0606The GRNBP model with the combination of green(550 nm),red edge(735 nm) and nearinfrared(790 nm) as the inversion factor has the best inversion effect,corresponding to the soil water content inversion model of 1 cm,3 cm,5 cm and 10 cm depthThe coefficient of determination(R2) is 0866,08,0975,0911,and the root mean square error(RMSE) is 0333,0361,0103,0315In our research,a variety of methods are used to invert the soil water content at different depthsThe optimal inversion model is GRNBP modelThe best inversion depth is 5 cmThe method has high precision and can further develop the surface moisture monitoring of the mining area
-
Key words:
- mining area /
- multispectrum /
- soil water content /
- BP neural network
-
[1] 汪志农灌溉排水工程学[M]. 北京:中国农业出版社,2010 [2] 隋涛,肖武,王党朝,等基于无人机摄影测量的露天矿排土场三维模型构建[J]. 金属矿山,2018(5):135-142Sui Tao,Xiao Wu,Wang Dangchao,et al. Establishment of the 3D model of openpit mine dump based on UAV photogrammetry [J]. Metal Mine,2018(5):135-142 [3] Derksen CThe contribution of AMSRE 187 and 107 GHz measurements to improved boreal forest snow water equivalent retrievals [J]. Remote Sensing of Environment,2008,112(5):2701-2710 [4] Sadeghi M,Jones S B,Philpot W DA linear physicallybased model for remote sensing of soil moisture using short wave infrared bands[J]. Remote Sensing of Environment,2015,164:66-76 [5] 张智韬,李援农,杨江涛,等遥感监测土壤含水率模型及精度分析[J]. 农业工程学报,2008,24(8):152-156,315Zhang Zhitao,Li Yuannong,Yang Jiangtao,et al. Model for monitoring soil moisture using remote sensing and its accuracy analysis [J]. Transactions of the CSAE,2008,24(8):152-156,315 [6] Petropoulos G P,Ireland G,Barrett BSurface soil moisture retrievals from remote sensing:Current status,products & future trends [J]. Physics and Chemistry of the Earth,2015,83:36-56 [7] Hatanaka T,Nishimune A,Nira R,et al. Estimation of available moisture holding capacity of upland soils using landsat TM data [J]. Soil Science and Plant Nutrition,1995,41(3):577-586 [8] Cashion J,Lakshmi V,Bosch D D,et al. Microwave remote sensing of soil moisture:evaluation of the TRMM microwave imager(TMI) satellite for the Little River Watershed Tifton,Georgia [J]. Journal of Hydrology,2005,307(1):242-253 [9] Kang J,Jin R,Li X,et al. High spatiotemporal resolution mapping of soil moisture by integrating wireless sensor network observations and MODIS apparent thermal inertia in the Babao River Basin,China [J]. Remote Sensing of Environment,2017,191:232-245 [10] Metin Sezen S,Yazar A,Dasgan Y,et al. Evaluation of crop water stress index(CWSI) for red pepper with drip and furrow irrigation under varying irrigation regimes [J]. Agricultural Water Management,2014,143(143):59-70 [11] He L,Qin Q M,Panciera R,et al. An extension of the alpha approximation method for soil moisture estimation using timeseries SAR data over bare soil surfaces [J]. IEEE Geoscience and Remote Sensing Letters,2017,14(8):1328-1332 [12] 齐述华,王长耀,牛铮利用温度植被旱情指数(TVDI)进行全国旱情监测研究[J]. 遥感学报,2003,7(5):420-427,436Qi Shuhua,Wang Changyao,Niu ZhengEvaluating soil moisture status in China using the temperature/vegetation dryness index(TVDI) [J]. Journal of Remote Sensing,2003,7(5):420-427,436 [13] 徐霞,孙文彬,王振基于TVDI的布尔台矿区土壤湿度变化分析[J]. 矿业科学学报,2019,4(4):285-291Xu Xia,Sun Wenbin,Wang ZhenAnalysis of soil moisture changes of the Buertai mining area based on TVDI [J]. Journal of Mining Science and Technology,2019,4(4):285-291 [14] 郑小坡,孙越君,秦其明,等基于可见光-短波红外波谱反射率的裸土土壤含水量反演建模[J]. 光谱学与光谱分析,2015,35(8):2113-2118Zheng Xiaopo,Sun Yuejun,Qin Qiming,et al. Bare soil moisture inversion model based on visibleshortwave infrared reflectance [J]. Spectroscopy and Spectral Analysis,2015,35(8):2113-2118 [15] 张智韬,王海峰,韩文霆,等基于无人机多光谱遥感的土壤含水率反演研究[J]. 农业机械学报,2018,49(2):173-181Zhang Zhitao,Wang Haifeng,Han Wenting,et al. Inversion of soil moisture content based on multispectral remote sensing of UAVs [J]. Transactions of the Chinese Society for Agricultural Machinery,2018,49(2):173-181 [16] Sorensen L K,Dalsgaard SDetermination of clay and other soil properties by near infrared spectroscopy [J]. Soil Science Society of America Journal,2005,69(1):159-167 [17] 蒋福坤,刘正春,柴惠文多维随机变量的线性相关性[J]. 数理统计与管理,2008,27(1):96-99Jiang Fukun,Liu Zhengchun,Chai HuiwenThe linear correlation of multidimensional random vector [J]. Application of Statistics and Management,2008,27(1):96-99 [18] 高惠璇处理多元线性回归中自变量共线性的几种方法:SAS/STAT软件(612)中REG等过程增强功能的使用[J]. 数理统计与管理,2000,19(5):49-55Gao Hui xuanSome method on treating the collinearity of independent variables in multiple linear regression [J]. Application of Statistics and Management,2000,19(5):49-55 [19] 杨楠岭回归分析在解决多重共线性问题中的独特作用[J]. 统计与决策,2004(3):14-15Yang NanThe unique role of ridge regression analysis in solving multicollinearity problems[J]. Statistics & Decision,2004(3):14-15 [20] 张曼,刘旭华,何雄奎,等岭回归在近红外光谱定量分析及最优波长选择中的应用研究[J]. 光谱学与光谱分析,2010,30(5):1214-1217Zhang Man,Liu Xuhua,He Xiongkui,et al. Study on the application of ridge regression to nearinfrared spectroscopy quantitative analysis and optimum wavelength selection [J]. Spectroscopy and Spectral Analysis,2010,30(5):1214-1217 [21] 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):283-288Yu Fan,Zhao Yingshi,Li HaitaoSoil moisture retrieval based on GABP neural networks algorithm [J]. Journal of Infrared and Millimeter Waves,2012,31(3):283-288 [22] 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
点击查看大图
计量
- 文章访问数: 654
- HTML全文浏览量: 149
- PDF下载量: 107
- 被引次数: 0