中文摘要：

应用可见／近红外光谱技术实现了油菜叶片中乙酰乳酸合成酶（ALS）的快速无损检测。对99个油菜样本进行光谱扫描，经过平滑、变量标准化、一阶求导等预处理后，应用偏最小二乘法（PLS）建立了ALS的预测模型。同时提取有效特征变量，作为反向传输人工神经网络（BPNN）和最小二乘一支持向量机（LS-SVM）的输入值，并建立相应的模型。用66个样本建模，33个样本验证。结果表明，LS-SVM模型能够获得最优的预测结果，预测集样本的相关系数（r）、预测标准差（RMSEP）和偏差（Bias）分别为0．998、0．715和0．079，获得了满意的预测精度。结果表明，应用可见／近红外光谱技术结合LS-SVM检测油菜中乙酰乳酸合成酶是可行的，并能获得满意的预测精度，为进一步应用光谱技术进行油菜生长状况的大田监测奠定了基础。

英文摘要：

Visible and near infrared （Vis/NIR） spectroscopy was applied for the fast and nondestructive determination of acetolactate synthase （ALS） in oilseed rape leaves. Ninety-nine samples were collected for Vis/NIR spectral scanning. Smoothing way of Savitzky-Golay with 9 segments, standard normal variate （SNV） and first derivative were used as preprocessing methods of spectral data before the calibration stage. Partial least squares （PLS） analysis was applied as calibration method as well as a way to extract the new eigenvectors which could be used to represent the most useful information of original spectra and compress the spectral dimensionality. The selected new eigenvectors were used as the input data matrix of back propagation neural network （BPNN） and least squares-support vector machine （LS-SVM） to develop the BPNN and LS-SVM models. The calibration set was composed of 66 samples, whereas 33 samples in the validation set. The results indicated that LS-SVM model achieved the best prediction performance, and LS-SVM model outperformed PLS and BPNN models. The correlation coefficients （r）, root mean square error of prediction （RMSEP） and bias by LS-SVM model were 0. 998, 0.715 and 0. 079, respectively. An excellent prediction precision and results were achieved by LS-SVM model. The overall results demonstrated that Vis/NIR spectroscopy combined with LS-SVM model could be successfully applied for the fast and nondestructive determination of acetolactate synthase （ALS） in oilseed rape leaves. This result was very helpful for further studies on the on-field monitoring of growing states and other biochemical parameters of oilseed rape using visible and near infrared spectroscopy.