基于可见-近红外光谱预处理建模的土壤速效氮含量预测

doi:10.3969/j.issn.1004-1524.2019.09.17

浙江农业学报 ›› 2019, Vol. 31 ›› Issue (9): 1523-1530.DOI: 10.3969/j.issn.1004-1524.2019.09.17

基于可见-近红外光谱预处理建模的土壤速效氮含量预测

方向, 金秀, 朱娟娟, 李绍稳^*

安徽农业大学信息与计算机学院,智慧农业技术与装备安徽省重点实验室,安徽合肥 230036

收稿日期:2019-04-28 出版日期:2019-09-25 发布日期:2019-10-11
通讯作者: *李绍稳,E-mail: shwli@ahau.edu.cn
作者简介:方向(1995—),男,安徽舒城人,硕士研究生,主要从事土壤速效养分高光谱检测研究。E-mail: 2928676905@qq.com
基金资助:
农业部948项目(2015-Z44,2016-X34)

Prediction of soil available nitrogen content based on visible and near infrared spectroscopy preprocess and modeling

FANG Xiang, JIN Xiu, ZHU Juanjuan, LI Shaowen^*

Anhui Province Key Laboratory of Intelligent Agriculture Technology and Equipment, School of Information & Computer, Anhui Agricultural University, Hefei 230036, China

Received:2019-04-28 Online:2019-09-25 Published:2019-10-11

摘要/Abstract

摘要： 以皖南地区采集的188份黄红壤样本为研究对象,利用地物非成像光谱仪获取原始光谱数据。首先,分析样本在350~1 657 nm波段经过预处理变换的平均光谱反射率曲线特征,再基于原始光谱,以及经29种预处理变换后的光谱,分别结合偏最小二乘回归(PLSR)和径向基核函数(RBF)-PLSR算法,建立60个针对土壤速效氮含量的预测模型,并进行模型优化;然后,以模型的决定系数(R²)和相对分析误差(RPD)来评价模型性能。结果显示,基于Savitaky-Golay卷积平滑和对数变换预处理的光谱,用PLSR建立的模型最适用于土壤速效氮含量的校正预测,其在建模集中R²=0.94、RPD=3.88,预测集中R²=0.91、RPD=3.38。该模型达到A类预测精度,可实现对土壤速效氮含量的定量估测。

关键词: 高光谱分析, 土壤速效氮, 预处理, 模型

Abstract: In the present study, 188 yellow-red loam soil samples were collected in Southern Anhui, and the original spectrum was obtained by non-imaging spectrometer. Firstly, the characteristics of the average spectral reflectance curve at 350-1 657 nm were analyzed after preprocessing. Based on the original spectrum and spectra after 29 preprocesses, a total of 60 models were constructed either by partial least squares regression (PLSR) or radial basis function (RBF)-PLSR, and the constructed models were optimized and evaluated by the models' decision coefficient (R²) and relative percent deviation (RPD). It was shown that the PLSR model constructed on spectra after Savitaky-Golay filtering and log transformation (SG+LG/PLSR model) was most suitable for the prediction of soil available nitrogen content. Its R² and RPD were 0.94 and 3.88 in calibration set and were 0.91 and 3.38 in prediction set, which belonged to A level, and indicated that this model was feasible for soil available nitrogen content prediction.

Key words: hyperspectral analysis, soil available nitrogen, preprocessing, model

中图分类号:

S153.6

方向, 金秀, 朱娟娟, 李绍稳. 基于可见-近红外光谱预处理建模的土壤速效氮含量预测[J]. 浙江农业学报, 2019, 31(9): 1523-1530.

FANG Xiang, JIN Xiu, ZHU Juanjuan, LI Shaowen. Prediction of soil available nitrogen content based on visible and near infrared spectroscopy preprocess and modeling[J]. , 2019, 31(9): 1523-1530.

参考文献

[1] 张娟娟. 土壤养分信息的光谱估测研究[D]. 南京: 南京农业大学, 2009.
ZHANG J J.Estimating soil nutrient information based on spectral analysis technology[D]. Nanjing: Nanjing Agricultural University, 2009.(in Chinese with English abstract)
[2] 汪懋华. “精细农业”发展与工程技术创新[J]. 农业工程学报, 1999, 15(1): 1-8.
WANG M H.Development of precision agriculture and innovation of engineering technologies[J]. Transactions of the CSAE, 1999, 15(1): 1-8.(in Chinese with English abstract)
[3] 赵春江, 杨信廷, 李斌, 等. 中国农业信息技术发展回顾及展望[J]. 农学学报, 2018, 8(1): 172-178.
ZHAO C J, YANG X T, LI B, et al.The retrospect and prospect of agricultural information technology in China[J]. Journal of Agriculture, 2018, 8(1): 172-178.(in Chinese with English abstract)
[4] 刘勋, 李长春, 李双权, 等. 高光谱遥感技术在土壤研究应用中的进展[J]. 安徽农业科学, 2019, 47(8): 18-21.
LIU X, LI C C, LI S Q, et al.Application progress of hyperspectral remote sensing technology in soil research[J]. Journal of Anhui Agricultural Sciences, 2019, 47(8): 18-21.(in Chinese with English abstract)
[5] SHAO Y N, HE Y.Nitrogen, phosphorus, and potassium prediction in soils, using infrared spectroscopy[J]. Soil Research, 2011, 49(2): 166.
[6] 刘雪梅, 柳建设. 基于MC-UVE的土壤碱解氮和速效钾近红外光谱检测[J]. 农业机械学报, 2013, 44(3): 88-91.
LIU X M, LIU J S.Near-infrared spectroscopy determination of soil available N and available K based on MC-UVE method[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(3): 88-91.(in Chinese with English abstract)
[7] KODAIRA M, SHIBUSAWA S.Using a mobile real-time soil visible-near infrared sensor for high resolution soil property mapping[J]. Geoderma, 2013, 199: 64-79.
[8] 齐海军, ARNON K, 李绍稳. Y-梯度广义最小二乘加权校正的土壤速效氮野外原位光谱预测[J]. 光谱学与光谱分析, 2018, 38(1): 171-175.
QI H J, ARNON K, LI S W.Predicting soil available nitrogen with field spectra corrected by Y-gradient general least square weighting[J]. Spectroscopy and Spectral Analysis, 2018, 38(1): 171-175.(in Chinese with English abstract)
[9] SAMPAIO P S, SOARES A, CASTANHO A, et al.Optimization of rice amylose determination by NIR-spectroscopy using PLS chemometrics algorithms[J]. Food Chemistry, 2018, 242: 196-204.
[10] NIE P C, WU D, YANG Y, et al.Fast determination of boiling time of yardlong bean using visible and near infrared spectroscopy and chemometrics[J]. Journal of Food Engineering, 2012, 109(1): 155-161.
[11] YU X, LIU Q, WANG Y B, et al.Evaluation of MLSR and PLSR for estimating soil element contents using visible/near-infrared spectroscopy in apple orchards on the Jiaodong peninsula[J]. Catena, 2016, 137: 340-349.
[12] CHANG C W, LAIRD D A, MAUSBACH M J, et al.Near-infrared reflectance spectroscopy-principal components regression analyses of soil properties[J]. Soil Science Society of America Journal, 2001, 65(2): 480.
[13] 褚小立, 袁洪福, 陆婉珍. 近红外分析中光谱预处理及波长选择方法进展与应用[J]. 化学进展, 2004, 16(4): 528-542.
CHU X L, YUAN H F, LU W Z.Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique[J]. Progress in Chemistry, 2004, 16(4): 528-542.(in Chinese with English abstract)
[14] 章海亮. 基于光谱和高光谱成像技术的土壤养分及类型检测与仪器开发[D]. 杭州: 浙江大学, 2015.
ZHANG H L.Soil nutrition content and type measurement based on NIR spectrum and hyper spectra image technology and design portable instrument[D]. Hangzhou: Zhejiang University, 2015.(in Chinese with English abstract)
[15] 纪文君. 基于野外vis-NIR高光谱的土壤属性预测及田间水分影响去除研究[D]. 杭州: 浙江大学, 2014.
JI W J.Removing the effects of soil water and the environment from in situ recorded visible and near-infrared spectra for the prediction of key soil properties in paddy soils[D]. Hangzhou: Zhejiang University, 2014. (in Chinese with English abstract)
[16] GRAS J, BARTHÈS B G, MAHAUT B, et al. Best practices for obtaining and processing field visible and near infrared (VNIR) spectra of topsoils[J]. Geoderma, 2014, 214/215: 126-134.

基于可见-近红外光谱预处理建模的土壤速效氮含量预测

Prediction of soil available nitrogen content based on visible and near infrared spectroscopy preprocess and modeling

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	金俪雯, 刘增金, 刘爱军. 猪肉销售商可追溯体系参与行为及其影响因素——基于北京、上海、济南3市636位销售商的实证分析[J]. 浙江农业学报, 2021, 33(3): 541-552.
[2]	张莎莎, 郑循刚, 张必忠. 交通基础设施、空间溢出与农村减贫——基于面板数据的实证研究[J]. 浙江农业学报, 2021, 33(3): 553-564.
[3]	富丽莎, 秦涛, 潘焕学, 邓晶. 森林保险保费补贴政策的林业产出规模效应实证分析——基于双重差分模型与事件研究模型[J]. 浙江农业学报, 2021, 33(2): 355-368.
[4]	刘姣姣, 张钢仁, 高群. 基于VEC-BEKK-GARCH和溢出指数模型的畜产品价格联动效应研究[J]. 浙江农业学报, 2020, 32(9): 1711-1721.
[5]	卢牧原, 刘源, 刘桂建. 基于组合模型的黑土区土壤有机质含量预测分析[J]. 浙江农业学报, 2020, 32(8): 1427-1436.
[6]	钱家炜, 刘晓青, 张静静, 周卫红, 李建龙. 张家港市农田土壤重金属含量高光谱遥感监测模型构建[J]. 浙江农业学报, 2020, 32(8): 1437-1445.
[7]	孟司奇, 丁高蓝, 肖兴宁, 肖英平, 杨华, 汪雯. 巴氏杀菌乳中金黄色葡萄球菌的生长预测模型构建[J]. 浙江农业学报, 2020, 32(7): 1281-1288.
[8]	陈铭儒, 胡军国, 崔武峰, 俞平. 基于Maxwell-Stefan扩散模型的土壤碳通量计算方法研究[J]. 浙江农业学报, 2020, 32(6): 1029-1038.
[9]	尹林江, 周忠发, 黄登红, 尚梦佳. 基于无人机影像匹配点云数据的喀斯特峡谷区火龙果单株提取研究[J]. 浙江农业学报, 2020, 32(6): 1092-1102.
[10]	樊慧丽, 付文阁. 基于局部均衡模型的中国羊肉市场供需变动分析[J]. 浙江农业学报, 2020, 32(6): 1123-1132.
[11]	许建民, 史和娣, 史培华, 张泽洋, 徐志刚. 不同光质条件下马铃薯光响应曲线拟合模型的比较[J]. 浙江农业学报, 2020, 32(5): 753-761.
[12]	李子琳, 韩逸, 郭熙, 国佳欣, 林雯璐. 基于结构方程模型的高安市耕地产能影响因素研究[J]. 浙江农业学报, 2020, 32(5): 866-877.
[13]	周贝宁, 芦建国, 花壮壮. 基于i-Tree模型的城市绿道生态服务效益研究[J]. 浙江农业学报, 2020, 32(12): 2201-2210.
[14]	周贝宁, 芦建国, 花壮壮. 基于i-Tree模型的城市绿道生态服务效益研究[J]. 浙江农业学报, 2020, 32(12): 2201-2210.
[15]	李梦璐, 张社梅. 媒体负面报道对蜂蜜消费预期变动的影响[J]. 浙江农业学报, 2020, 32(12): 2282-2290.