基于PLSR 的土壤有机碳预测模型中建模组与验证组最优数量关系

doi:10.16389/j.cnki.cn42-1737/n.2018.05.003

江汉大学学报（自然科学版） ›› 2018, Vol. 46 ›› Issue (5): 404-408.doi: 10.16389/j.cnki.cn42-1737/n.2018.05.003

基于PLSR 的土壤有机碳预测模型中建模组与验证组最优数量关系

丁建军^a，章盛^a，孙超^a，米铁^b

江汉大学 a. 物理与信息工程学院；b. 化学与环境工程学院，湖北武汉 430056

出版日期:2018-10-28 发布日期:2018-10-25
作者简介:丁建军（1969—），男，教授，博士，研究方向：检测技术与仪器。
基金资助:
国家科技支撑计划资助项目（2013BAD11B02）；教育局市属高校产学研项目（CXY201803）；湖北省高等学校优秀中青年科技创新团队计划资助项目（T201420）

Optimal Quantity Relationship Between Modeling Group and Prediction Group in Soil Organic Carbon Prediction Model Based on PLSR

DING Jianjun^a，ZHANG Sheng^a，SUN Chao^a，MI Tie^b

a. School of Physics and Information Engineering；b. School of Chemistry and Environmental Engineering，Jianghan University，Wuhan 430056，Hubei，China

Online:2018-10-28 Published:2018-10-25

摘要/Abstract

摘要： 基于土壤有机碳含量现场快速测定技术研究，提出了利用可见-近红外光谱技术对土壤样本进行可见-近红外反射光谱分析的方法，选取400 ～ 1 100 nm 波段光谱经S-G平滑加一阶微分滤波预处理后，利用偏最小二乘回归分析（PLSR）建立土壤有机碳预测模型。结果显示，当建模组样本数与验证组样本数之比为52∶53（约为1∶1）时，决定系数R² =0. 98 ，均方根校正标准偏差RMSEC = 0. 25。这说明将建模组样本与验证组样本的数量关系比设定为1∶1是建立基于PLSR的土壤有机碳预测模型的最优条件。

关键词: 土壤有机碳, 可见-近红外光谱技术, 偏最小二乘回归

Abstract: Based on rapid determination technology research of soil organic carbon content in scene, an analysis method of visible and near infrared reflectance spectroscopy for soil samples was proposed. The 400 ～ 1 100 nm band spectrum was pretreated by S-G smoothing and with first order differential filtering，and the prediction model of soil organic carbon was established by partial least squares regression analysis（PLSR）. The results showed when the ratio of the sample number of the modeling group and the sample number of the predicted group was 52∶53（about 1∶1），the determining coefficient was R² =0. 98, and the standard deviation of the root mean square error of calibration was RMSEC = 0. 25. These results indicate when the ratio of the sample number in the modeling group and in the prediction group is set to 1∶1，it is the best condition to establish the prediction model based on PLSR for soil organic carbon.

Key words: soil organic carbon, visible and near infrared spectroscopy technology, partial least squares regression

中图分类号:

S153.6

丁建军，章盛，孙超，米铁. 基于PLSR 的土壤有机碳预测模型中建模组与验证组最优数量关系[J]. 江汉大学学报（自然科学版）, 2018, 46(5): 404-408.

DING Jianjun，ZHANG Sheng，SUN Chao，MI Tie. Optimal Quantity Relationship Between Modeling Group and Prediction Group in Soil Organic Carbon Prediction Model Based on PLSR[J]. Journal of Jianghan University(Natural Science Edition), 2018, 46(5): 404-408.

基于PLSR 的土壤有机碳预测模型中建模组与验证组最优数量关系

Optimal Quantity Relationship Between Modeling Group and Prediction Group in Soil Organic Carbon Prediction Model Based on PLSR

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价