基于高光谱特征与人工神经网络模型对土壤含水量估算

摘要

Soil water content (θ) is an important factor for the crop growth and crop production .The objectives of this study were to (i) test various regression models for estimating θ based on spectral feature parameters,and (ii) compare the performance of the proposed models by using artificial neural networks (ANN) and spectral feature parameters .The θ data of sand and loam and concurrent spectral parameters were acquired at the laboratory experiment in 2014 .The results showed that: (1) the maximum reflectance with 900～970 nm and the sum reflectance within 900～970 nm estimate θ had the significant,when sand bulk density was 140 g·cm-3; the maximum reflectance with blue edge and the s um reflectance within 900～970 nm had the best correlation (R2＞070) when s and bulk density was 150 g·cm-3; while soil bulk density was 160 g·cm-3,the sum reflectance within 780～970 nm and normalized absorption depth in 560～760 nm reached a significant (R2＞090); when soil bulk density was 170 g·cm-3,the maximum reflectance with 900～970 nm and the sum reflectance within 900～970 nm had the best correlation estimate θ (R2＞088) .2) When the soil type was loam,the maximum reflectance with 900～970 nm and the sum reflectance within 900～970 nm had a best correlation estimate θ .The spectral feature parameters the sum reflectance within blue edge (R2=026 and RMSE=009 m3·m-3) and 780～970 nm absorption depth (R2=032 and RMSE=0 .10 m3·m-3) were best correlated with θ in the sand .The θ model based on maximum reflectance with 900～970 nm (R2=092 and RMSE=005 m3·m-3) and the sum reflectance within 900～970 nm had a high correlation (R2=092 and RMSE=004 m3·m-3) in the loam .The BP-ANN model presented a better estimation accuracy of θ (R2=087 and RMSE=005 m3·m-3) in two soils .Thus,the ANN model has great potential for estimating θ .Thus,the BP-ANN model has great potential for θ estimation .%土壤含水量(θ)是影响作物生长和作物产量的主要因素之一.旨在评估基于光谱特征参数的各种回归模型估算土壤含水量的精度,并比较人工神经网络(BP-ANN)和光谱特征参数模型的性能.2014年在室内获取砂土和壤土的土壤含水量和光谱反射率数据.结果表明:(1)当砂土容重为140 g·cm-3时,900～970 nm最大反射率和900～970 nm反射率总和估算θ达到极显著水平(R2超过090);容重为150 g·cm-3时,用蓝边最大反射率和900～970 nm反射率总和估算θ相关性最好(超过070);容重为160 g·cm-3时,780～970 nm反射率总和与560～760 nm归一化吸收深度的R2均超过090,达到极显著水平;容重为170 g·cm-3时,900～970 nm最大反射率和900～970 nm反射率总和的R2为088,呈极显著水平.(2)当土壤类型为壤土时,用900～970 nm最大反射率和900～970 nm反射率总和估算θ相关性最好.(3)蓝边反射率总和(R2=026和RMSE=009 m3·m-3)和780～970 nm吸收深度(R2=032和RMSE=010 m3·m-3)估算砂土的含水量相关性最好.在估算壤土的含水量时,900～970 nm最大反射率(R2=092和R MSE=005 m3·m-3)与900～970 nm反射率总和估算模型的精度最高(R2=0 92和RMSE=004 m3·m-3).(4)用人工神经网络模型能够更好地估算两种土壤的含水量(R2=087和RMSE=005 m3·m-3).因此,人工神经网络模型对θ估算具有巨大的潜力.