ZHENG Jianle,ZHANG Jiazhen,LIU Wei,et al.Study on Quantitative Inversion of Soil Organic Matter Content by Hyperspectral[J].Northern Horticulture,2022,(16):83-91.[doi:10.11937/bfyy.20220460]
土壤有机质含量高光谱定量反演研究
- Title:
- Study on Quantitative Inversion of Soil Organic Matter Content by Hyperspectral
- Keywords:
- hyperspectral remote sensing; soil organic matter; multiple linear regression; random forest regression; inversion accuracy
- 文献标志码:
- A
- 摘要:
- 以太行山区北流河流域为研究对象，采用多元线性回归和随机森林回归构建土壤有机质反演模型，对表层土壤有机质含量进行反演估测，以期得出太行山区表层土壤有机质遥感定量反演的建模方式与相应技术参数。结果表明：1）Savitzky-Golay（SG）平滑和小波包分析等方法可以提高土壤光谱与土壤有机质含量的相关性。2）随机森林模型在反演土壤有机质含量研究中，模型精度与效果均优于多元线性回归模型，利用小波包分解得到的低频分量构建的随机森林模型在SOM含量反演中效果最好，R2为0812，实现了对土壤有机质的有效估算。3）影响土壤有机质含量反演模型精度的因素较多，在未来研究中需要从光谱数据源质量、光谱数据处理方式及建模方式等方面进行深入研究，进一步完善土壤有机质含量反演技术体系，提高土壤有机质含量反演精度。
- Abstract:
- Taking Beiliu River Basin in the Taihang Mountains as the research object,multiple linear regression and random forest regression were used to construct a soil organic matter inversion model to invert and estimate the surface soil organic matter content，in order to obtain the quantitative inversion and corresponding technical parameters of the surface soil organic matter in the Taihang Mountains.The results showed that，1) methods such as Savitzky-Golay (SG) smoothing and wavelet packet analysis could improve the correlation between soil spectra and soil organic matter content.2) In the research on inversion of soil organic matter content，the random forest model had better model accuracy and effect than the multiple linear regression model.The random forest model constructed by using the low-frequency components obtained by the wavelet packet decomposition had the best effect in the inversion of SOM content，and R2 was 0812，achieving an effective estimation of soil organic matter.3) There were many factors that affect the accuracy of the soil organic matter content inversion model.In the future research，in-depth research on the quality of spectral data sources，spectral data processing methods and modeling methods was needed to further complete the soil organic matter content inversion technology system and improve the inversion accuracy of soil organic matter content.
参考文献/References:
[1]JING T，LU S，FAN M，et al.Labile soil organic matter fractions as influenced by non-flooded mulching cultivation and cropping season in rice-wheat rotation[J].European Journal of Soil Biology，2013，56:19-25.[2]刘焕军，赵春江，王纪华,等.黑土典型区土壤有机质遥感反演[J].农业工程学报，2011，27(8):5.[3]WANG Y Q，SHAO M A.Spatial varibility of soil physical properties in a region of the loess plateau of pr China subject to wind and water erosion[J].Land Degradation & Development，2013，24(3):296-304.[5]叶勤，姜雪芹，李西灿,等.基于高光谱数据的土壤有机质含量反演模型比较[J].农业机械学报，2017，48(3):9.[6]赵小敏，杨梅花.江西省红壤地区主要土壤类型的高光谱特性研究[J].土壤学报，2018，55(1):12.[7]SONG Y，LI F，YANG Z，et al.Diffuse reflectance spectroscopy for monitoring potentially toxic elements in the agricultural soils of Changjiang River Delta，China[J].Applied Clay Science，2012，64:75-83.[8]CONFORTI M，BUTTAFUCO G，LEONE A P，et al.Studying the relationship between water-induced soil erosion and soil organic matter using Vis-NIR spectroscopy and geomorphological analysis：A case study in southern Italy[J].Catena，2013，110:44-58.[9]ROSSEL R，CATTE S R，ORTEGA A，et al.In situ measurements of soil colour，mineral composition and clay content by vis-NIR spectroscopy[J].Geoderma，2009，150(3/4):253-266.[10]史舟，王乾龙，彭杰,等.中国主要土壤高光谱反射特性分类与有机质光谱预测模型[J].中国科学·地球科学，2014(5):11.[11]WANG C，PAN X.Estimation of clay and soil organic marbon using visible and near-infrared spectroscopy and unground samples[J].Soil Science Society of America Journal，2016，80(5):56-64.[12]YANG H Q，KUANG B Y，MOUAZEN A M.Prediction of soil TN and TC at a farm-scale using VIS-NIR spectroscopy[J].Advanced Materials Research，2011，225:1258-1261.[13]PRIORI S，FANTAPPIE M，BIANCONI N，et al.Field-Scale mapping of soil carbon stock with limited sampling by coupling gamma-ray and vis-nir spectroscopy[J].Soil Science Society of America Journal，2016，80(4):234-239.[14]潘润秋，马小淞，刘珺.基于粒子群优化BP神经网络的耕地自然质量分计算模型[J].地理与地理信息科学，2014，30(5):5.[15]FRANCESCHIN M，JAM D，TERRA F S，et al.Prediction of soil properties using imaging spectroscopy：Considering fractional vegetation cover to improve accuracy[J].International Journal of Applied Earth Observation and Geoinformation，2015，38:358-370.[16]VAUDOUR E，GILLIOT J M，BEL L，et al.Regional prediction of soil organic carbon content over croplands using airborne hyperspectral data[J].EGU General Assembly Conference Abstracts，2015(11):123-132.[17]赵瑞，崔希民，刘超.GF-5高光谱遥感影像的土壤有机质含量反演估算研究[J].中国环境科学，2020，40(8):7.[18]张智韬，劳聪聪，王海峰,等.基于FOD和SVMDA-RF的土壤有机质含量高光谱预测[J].农业机械学报，2020，51(1):12.[19]张娟娟，席磊，杨向阳,等.砂姜黑土有机质含量高光谱估测模型构建[J].农业工程学报，2020，36(17):7.[20]ROSSEL V.Robust modelling of soil diffuse reflectance spectra by bagging-partial least squares regression[J].Journal of Near Infrared Spectroscopy，2007，15(2):39-47.[21]VACCARO S，SOBIECKA E，CONTINI S，et al.The application of positive matrix factorization in the analysis，characterisation and detection of contaminated soils[J].Chemosphere，2007，69(7):1055-1063.[22]HABSHAH M，NORAZAN M R，IMON A.The performance of diagnostic-robust generalized potentials for the identification of multiple high leverage points in linear regression[J].Journal of Applied Statistics，2009，36(5/6):507-520.[23]罗德芳，柳维扬，彭杰，等.土壤水分去除算法的田间原位光谱反演棉田有机质[J].光谱学与光谱分析，2022，42(1):7.[24]杨长保，李东辉，刘津怿,等.小波包分析在Hyperion数据提取农田土壤有机质含量中的应用研究[J].应用基础与工程科学学报，2017，25(5):11.[25]AMOOZAD-KHALILI M，ROSTAMIAN R，ESMAEILPOUR-TROUJENI M，et al.Economic modeling of mechanized and semi-mechanized rainfed wheat production systems using multiple linear regression model[J].Information Processing in Agriculture，2019，7(1):107-120.[26]刘焕军，张柏，赵军,等.黑土有机质含量高光谱模型研究[J].土壤学报，2007，44(1):6.[27]孙浩然,赵志根,赵佳星,等.珠海一号高光谱遥感的表层土壤有机质含量反演方法[J].遥感信息，2020，35(4):7.
相似文献/References:
[1]李 华,王 英,马雪峰,等.宁夏灵武长枣示范园区土壤养分调查与分析[J].北方园艺,2013,37(17):178.
LI Hua,WANG Ying,MA Xue-feng,et al.Investigation and Analysis of Soil Nutrient in Lingwuchangzao Demonstration Garden in Ningxia[J].Northern Horticulture,2013,37(16):178.
[2]周俊国,杨鹏鸣.不同肥料对菜地土壤有机质和全氮含量的影响[J].北方园艺,2012,36(08):152.
ZHOU Jun-guo,YANG Peng-ming.Effects of Different Fertilizer on Soil Organic Matter and Soil Total Nitrogen Content[J].Northern Horticulture,2012,36(16):152.
[3]夏燕飞,张文会,沈向,等.有机质对苹果园土壤改良及对果实产量品质的影响[J].北方园艺,2012,36(21):177.
XIA Yan-fei,ZHANG Wen-hui,SHEN Xiang,et al.Effects of Soil Organic Matter on Soil Characteristics and Fruit Production and Quality in Apple Orchard[J].Northern Horticulture,2012,36(16):177.
[4]杨燕,姚云峰,秦富仓,等.砒砂岩区沙棘不同平茬方式与土壤氮、磷、钾含量的研究[J].北方园艺,2012,36(14):147.
YANG Yan,YAO Yun-feng,QIN Fu-cang,et al.Study on Sandstone of Hippophae rhamnoides on Different Stubble Soil N，P，K Content[J].Northern Horticulture,2012,36(16):147.
[5]樊建琼,王延平,韩明玉,等.土壤管理方式对苹果园土壤有机质含量和酶活性及微生物数量的影响[J].北方园艺,2013,37(24):172.
FAN Jian-qiong,WANG Yan-ping,HAN Ming-yu,et al.Effects of Soil Management Ways on Soil Organic Matters Content，Enzyme Activities and Microbes Number of the Apple Orchard[J].Northern Horticulture,2013,37(16):172.
[6]寇建村,杨文权,李尚玮,等.我国果园土壤有机质研究进展[J].北方园艺,2016,40(04):185.[doi:10.11937/bfyy.201604045]
KOU Jiancun,YANG Wenquan,LI Shangwei,et al.Research Advance on Soil Organic Matter of Orchard in China[J].Northern Horticulture,2016,40(16):185.[doi:10.11937/bfyy.201604045]
[7]焦 蕊,于 丽 辰,贺 丽 敏,等.土壤有机质对“ 红富士” 苹果产量和品质的影响[J].北方园艺,2011,35(14):0.[doi:10.11937/bfyy.2011014006]
JIAO Rui,YU Li-chen,HE Li -min,et al.Effect of Soil Organic Matter on Yield and Quality of`Fuji’ Apple[J].Northern Horticulture,2011,35(16):0.[doi:10.11937/bfyy.2011014006]
[8]李增亮,任晶,梁鑫宇,等.七种植物秸秆对连作番茄苗生长及土壤酶活性的影响[J].北方园艺,2019,43(20):17.[doi:10.11937/bfyy.20190798]
LI Zengliang,REN Jing,LIANG Xinyu,et al.Effect of Seven Plant Straws on the Growth of Continuous Cropping Tomato and the Activity of Soil Enzyme[J].Northern Horticulture,2019,43(16):17.[doi:10.11937/bfyy.20190798]
备注/Memo
第一作者简介：郑建乐（1997-），男，硕士研究生，研究方向为土壤与土地资源可持续利用。E-mail：1053984562@qq.com.责任作者：王树涛（1978-），男，博士，教授，现主要从事土壤与土地资源可持续利用等研究工作。E-mail：55381040@qq.com.基金项目：国家自然科学基金资助项目（42077369）；河北省重点研发资助项目（21373807D）。收稿日期：2022-02-10