提取土壤碱解氮特征光谱是利用高光谱数据进行其含量估测的关键。对山东省典型潮土土壤样本测试高光谱并进行变换；采用遗传算法（GA）结合偏最小二乘法（PLS），在筛选潮土碱解氮含量特征谱区的基础上，构建潮土碱解氮含量偏最小二乘（PLS）回归估测模型；优选最佳模型并与相关分析、逐步回归分析和单纯偏最小二乘回归分析的模型进行比较。结果表明：潮土碱解氮特征波段为449~469nm，988~1001nm，1065~1078nm，1716~1736nm，1912~1925nm，2213~2233nm，2262~2275nm；基于各输入光谱特征谱区构建的估测模型决定系数R2均较高，其中基于反射率一阶导数光谱筛选的特征谱区，构建的模型精度最高，数据点（147个）为原始全谱的7.17%，建模R2达到0.97，均方根误差RMSE为4.78mg/kg，验证R2为0.95，RMSE为5.49mg/kg，对潮土碱解氮含量具有较好的预测准确性；在光谱变换形式中，反射率的一阶导数表现最佳；方法比较显示采用遗传算法结合偏最小二乘（GA-PLS）获得较高预测精度的同时，可简化模型。说明遗传算法结合偏最小二乘法（GA-PLS），可有效筛选土壤碱解氮的特征波段，减少模型参与变量，提高估测精度。
Abstract
Extracting the characteristic spectra is the key of estimating soil alkali hydrolysable nitrogen content based on hyperspectra. This article was carried out to detect and transform the hyperspectra reflectance of the soil samples collected from the fluvo-aquic soil areas in Shandong Province. The characteristic wave bands of fluvo-aquic soil alkali hydrolysable nitrogen were filtered using genetic algorithms and partial least squares method. Then, the partial least squares regression estimation models of fluvo-aquic soil alkali hydrolysable nitrogen content were constructed. The best model was selected and compared with the models based on correlation analysis, stepwise linear and partial least squares regression directly. The results showed that the characteristic wave bands of fluvo-aquic soil alkali hydrolysable nitrogen were 449-469 nm, 988-1001 nm, 1065-1078 nm,1716-1736 nm, 1912-1925 nm, 2213-2233 nm and 2262-2275 nm, the modeling coefficient of determination(R2) based on characteristic wave bands of different input spectra was generally high, the model based on the characteristic wave bands of the first derivative of reflectance had the highest precise, with the 147 data points as 7.17% of the original spectrum, the model building R2 to 0.97, RMSE as 4.78 mg/kg, the validated R2 to 0.95, RMSE as 5.49 mg/kg, the model had good prediction accuracy of fluvo-aquic soil alkali hydrolysable nitrogen content. The comparison of methods showed that the genetic algorithms combined with partial least squares regression could not only obtain higher prediction accuracy, but also simplify models. Therefore, the genetic algorithms combined with partial least squares regression method may effectively select the characteristic wave bands of soil alkali hydrolysable nitrogen, reduce the model variables and improve the estimation accuracy.
关键词
土壤碱解氮；高光谱；遗传算法；偏最小二乘回归
{{custom_keyword}} /
Key words
soil alkali hydrolysable nitrogen; hyperspectra; genetic algorithm; partial least squares regression
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Yang N F, Eash N S, Lee J, et al. Multivariate analysis of laser-induced breakdown spectroscopy spectra of soil samples[J]. Soil Science,2010,175(9):447-452.
[2] Sullivan D G, Shaw J N, Rickman D, et al. Using remote sensing data to evaluate surface soil properties in Alabama ultisols[J]. Soil Science,2005,70(12):954-968.
[3] 张雪莲,李晓娜,武菊英,等.不同类型土壤总氮的近红外光谱技术测定研究[J].光谱学与光谱分析,2010,30(4):906-910.
[4] 张娟娟,田永超,姚霞,等.基于近红外光谱的土壤全氮含量估算模型[J].农业工程学报,2012,28(12):183-188.
[5] 卢艳丽,白由路,王磊,等.黑土土壤中全氮含量的高光谱预测分析[J].农业工程学报,2010,26(1):256-261.
[6] Salati S, Adani F, Cosentino C, et al. Studying soil organic matter using 13C CP-MAS NMR: The effect of soil chemical pre-treatments on spectra quality and representativity[J]. Chemosphere,2008,70(11):2092-2098.
[7] Weng Y L, Gong P, Zhu Z L. A spectral index for estimating soil salinity in the Yellow River delta region of China using EO-1 hyperion data[J]. Pedosphere,2010,20(3):378-388.
[8] 彭杰,向红英,周清,等.不同类型土壤全氮含量的高光谱预测研究[J].中国农学通报,2013,29(9):105-111.
[9] 陈红艳,赵庚星,李希灿,等.基于小波变换的土壤有机质含量高光谱估测[J].应用生态学报,2011,22(11):2935-2942.
[10] Elliott G N, Worgan H, Broadhurst D, et al. Soil differentiation using fingerprint Fourier transform infrared spectroscopy, chemometrics and genetic algorithm-based feature selection[J]. Soil Biology & Biochemistry,2007,39(11):2888-2896.
[11] Michael F, Julio C, Leyden F, et al. Genetic algorithm optimization in drug design QSAR: Bayesian-regularized genetic neural networks (BRGNN) and genetic algorithm-optimized support vectors machines (GA-SVM)[J]. Molecular Diversity,2011,15(1):269-289.
[12] Devos O, Duponchel L. Parallel genetic algorithm co-optimization of spectral pre-processing and wavelength selection for PLS regression[J]. Chemometrics and Intelligent Laboratory Systems,2011,107(1):50-58.
[13] 温健婷,张霞,张兵,等.土壤铅含量高光谱遥感反演中波段选择方法研究[J].地球科学进展,2010,25(6):625-629.
[14] 刘雪梅,章海亮.基于遗传算法近红外光谱检测土壤养分的研究[J].灌溉排水学报,2013,32(2):138-141.
[15] 陈红艳,赵庚星,李希灿,等.小波分析用于土壤速效钾含量高光谱估测研究[J].中国农业科学,2012,45(7):1425-1431.
[16] 陈红艳.土壤主要养分含量的高光谱估测研究[D].泰安:山东农业大学,2012:35-65.
[17] 屠振华,籍保平,孟超英,等.基于遗传算法和间隔偏最小二乘的苹果硬度特征波长分析研究[J].光谱学与光谱分析,2009,29(10):2760-2764.
[18] Omar D, Mohammad G. Exploring QSARs for inhibitory activity of non-peptide HIV-1 protease inhibitors by GA-PLS and GA-SVM[J]. Chemical Biology & Drug Design,2010,75(5):506-514.
[19] 黄昌勇.土壤学[M].北京:中国农业出版社,2002:212-216.
[20] Viscarra Rossel R A, Behrens T. Using data mining to model and interpret soil diffuse reflectance spectra[J]. Geoderma,2010,158(1/2):46-54.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(542 KB)
