油莎豆含油率的近红外光谱检测模型研究  

Study on Near Infrared Spectroscopy Detection Model for Oil Content of Cyperus esculentus Tubers

作　　者：魏海峰 时学双 党锡强 米玛顿珠 张梦媛 常唯 赤列措姆 张斌[2,3] 高文伟 Wei Haifeng;Shi Xueshuang;Dang Xiqiang;Mimadunzhu;Zhang Mengyuan;Chang Wei;Tinley Tsomo;Zhang Bin;Gao Wenwei(College of Agriculture,Xinjiang Agricultural University,Urumqi 830000,China;Institute of Crop Germplasm Resources,Shandong Academy of Agricultural Sciences,Jinan 250100,China;Xigaze Agriculture and Animal Husbandry Science Research and Extension Center,Xigaze 857012,China;Qingzhou Bureau of Agriculture and Rural Affairs,Qingzhou 262500,China;Nanmulin County Bureau of Agriculture and Rural Affairs,Xigaze City,Xigaze 857100,China)

机构地区：[1]新疆农业大学农学院,新疆乌鲁木齐830000 [2]山东省农业科学院农作物种质资源研究所,山东济南250100 [3]日喀则市农牧业科学研究推广中心,西藏日喀则857012 [4]青州市农业农村局,山东青州262500 [5]日喀则市南木林县农业农村局,西藏日喀则857100

出　　处：《山东农业科学》2025年第1期166-173,共8页Shandong Agricultural Sciences

基　　金：国家重点研发计划项目(2019YFD1002701);山东省“渤海粮仓”科技示范工程升级版项目(2019BHLC002);2003年日喀则市人才资源开发专项资金资助项目“日喀则市油莎豆新品种引种筛选及配套关键栽培技术研究与示范”。

摘　　要：为建立油莎豆块茎含油率的近红外光谱快速无损检测模型,提高育种材料的早代选择效率,本研究以109份油莎豆块茎样本为实验材料,采集波长范围为950~1650 nm、分辨率为1 nm的近红外光谱,并通过索氏提取法测定块茎粗脂肪含量,剔除异常样本后共得到103份样本,使用SPXY法将其按3∶1的比例划分为校正集与验证集。分别采用标准正态变换、多元散射校正、一阶导、二阶导、SG平滑以及混合方法对原始光谱进行预处理,并基于此建立偏最小二乘回归(PLSR)模型,通过对模型性能的对比分析,筛选出在校正集和验证集上预处理效果均较好的MSC+SG法,用于油莎豆含油率检测模型的构建;然后用竞争性自适应重加权采样(CARS)、无信息变量消除(UVE)算法以及MLP神经网络进行特征波长提取,并构建PLSR模型,结果显示,用CARS和UVE算法分别提取出115个和251个特征波段,建模效果均比全波段建模效果好,其中CARSPLSR模型预测性能最优,校正集交叉验证均方根误差(RMSE_(CV))、决定系数(R_(CV)^(2))分别为1.328、0.903,验证集RMSE_(P)、R_(P)^(2)分别为1.206、0.888,验证集相对分析误差(RPDP)为3.040;而MLP-PLSR模型的预测精度与CARS-PLSR模型接近,RMSE_(CV)、R_(CV)^(2)分别为1.387、0.903,RMSE_(P)、R_(P)^(2)分别为1.207、0.887,RPDP为3.040,但提取的特征波长仅77个,是3种方法中最少的,说明MLP法能够更有效地降低光谱信息重叠,滤除无关信息,MLP-PLSR更适合用于油莎豆含油率检测。综上,本研究初步建立了基于近红外光谱的油莎豆含油率快速无损检测模型,可为提高育种工作中的检测效率提供有效方法,并为油莎豆含油率无损检测提供技术支持。In order to establish a rapid non-destructive detection model of near-infrared spectroscopy for oil content of Cyperus esculentus tubers and to improve the efficiency of early generation selection of breeding materials,109 samples of C.esculentus tubers were used as experimental materials in this study.The near-infrared spectra with a wavelength range from 950 to 1650 nm and a resolution of 1 nm were collected,and the crude fat content of the tubers was determined by Soxhlet extraction method.After eliminating abnormal samples,a total of 103 samples were obtained which were then divided into calibration set and validation set in a ratio of 3∶1 by SPXY method.The original spectra were preprocessed by standard normal transformation,multiple scattering correction,first derivative,second derivative,SG smoothing and their hybrid methods,respectively,to establish the partial least squares regression(PLSR)model.Through comparing and analyzing the performance of the models,the MSC+SG method with better pretreatment effect on both the calibration set and the validation set was selected for the construction of the oil content detection model of C.esculentus.Then,the competitive adaptive reweighted sampling(CARS),uninformative variable elimination(UVE)algorithm and MLP neural network were used to extract the characteristic wavelengths,and the PLSR model was constructed.The results showed that 115 and 251 characteristic bands were extracted by CARS and UVE algorithms,respectively,with the modeling effect better than that of the full-band.The CARS-PLSR model had the best prediction performance with the root mean square error(RMSE)of cross-validation(RMSE_(CV))and coefficient of determination(R_(CV)^(2))of the calibration set were 1.328 and 0.903 respectively,and the RMSE_(P) and R_(P)^(2) of the validation set were 1.206 and 0.888 respectively,and the relative analysis error(RPDP)of the validation set was 3.040.The prediction accuracy of the MLP-PLSR model was close to that of the CARS-PLSR model with RMSE_(CV) and R_(CV)^(

关 键 词：油莎豆 含油率 近红外光谱 偏最小二乘回归(PLSR) MLP神经网络 特征波长提取 

分 类 号：S126[农业科学—农业基础科学] S565.9