[1]江远东,李新国,杨涵.基于连续小波变换的表层土壤有机碳含量的高光谱估算[J].江苏农业学报,2023,(01):118-125.[doi:doi:10.3969/j.issn.1000-4440.2023.01.014]
　JIANG Yuan-dong,LI Xin-guo,YANG Han.Hyperspectral estimation of organic carbon content in surface soils based on continuous wavelet transform[J].,2023,(01):118-125.[doi:doi:10.3969/j.issn.1000-4440.2023.01.014]
点击复制

基于连续小波变换的表层土壤有机碳含量的高光谱估算()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年01期
页码:
118-125
栏目:
农业信息工程
出版日期:
2023-02-28

文章信息/Info

Title:
Hyperspectral estimation of organic carbon content in surface soils based on continuous wavelet transform
作者:
江远东1; 2; 李新国1; 2; 杨涵1; 2
(1.新疆师范大学地理科学与旅游学院,新疆乌鲁木齐830054；2.新疆干旱区湖泊环境与资源实验室,新疆乌鲁木齐830054）
Author(s):
JIANG Yuan-dong1; 2; LI Xin-guo1; 2; YANG Han1; 2
(1.College of Geographic Science and Tourism, Xinjiang Normal University, Urumqi 830054, China;2.Xinjiang Key Laboratory of Lake Environment and Resource in Arid Zone, Urumqi 830054, China)
关键词:
土壤有机碳含量; 高光谱反射率; 一阶微分变换; 连续小波变换; 支持向量机; 湖滨绿洲
Keywords:
soil organic carbon content; hyperspectral reflectance; first order differential transformation; continuous wavelet transform; support vector machine; lakeside oasis
分类号:
S127
DOI:
doi:10.3969/j.issn.1000-4440.2023.01.014
文献标志码:
A
摘要:
土壤有机碳含量的高光谱估算,可快速、准确监测土壤肥力,为农业生产进行合理施肥提供科学依据。以博斯腾湖西岸湖滨绿洲为研究区,应用ASD FieldSpec3光谱仪测定表层土壤的高光谱反射率,采用重铬酸钾-外加热法测定表层土壤有机碳（SOC）含量；运用连续小波变换（CWT）分别对土壤高光谱反射率（R）及其一阶微分变换（R′）进行尺度分解,分析不同尺度分解后的数据与表层SOC含量的相关性,筛选敏感波段,分别建立偏最小二乘回归（PLSR）、随机森林（RF）和支持向量机（SVM）3种模型估算表层SOC含量。研究结果表明,土壤高光谱反射率与SOC含量呈负相关,经过一阶微分变换后,通过极显著性检验（P<0.01）的波段数由1 689个降低为227个,最大相关系数绝对值（|r|）由0.39提高至0.54；土壤高光谱数据CWT处理后,与表层SOC含量的相关性随分解尺度的增加呈现先增后降的趋势。R′-CWT-SVM模型估算效果最优,建模集和验证集R2分别为0.83和0.80,RMSE分别为5.24和3.56,RPD值为2.12,能够有效估算研究区表层SOC含量。
Abstract:
Hyperspectral estimation of soil organic carbon content can rapidly and accurately monitor soil fertility and provide scientific basis for rational fertilization in agricultural production. Taking the west lakeside oasis of Bosten Lake as the study area, the ASD FieldSpec3 spectrometer was applied to collect hyperspectral reflectance of surface soil samples, and the organic carbon (SOC) content of surface soil was determined by the potassium dichromate-external heating method. The continuous wavelet transform (CWT) was used to decompose the soil reflectance (R) and its first-order differential transform (R′) respectively, and the data after decomposition at different scales were analyzed and correlated with the surface SOC content. The correlation between the decomposed data and the surface SOC content was analyzed using the continuous wavelet transform, and three models, namely partial least squares regression (PLSR), random forest (RF) and support vector machine (SVM), were developed to estimate the surface SOC content. The results showed that soil hyperspectral reflectance was negatively correlated with surface SOC content. After the first-order differential transformation, the number of bands passing the highly significant test （P<0.01） decreased from 1 689 to 227, and the absolute value of maximum correlation coefficient increased from 0.39 to 0.54. After continuous wavelet transform, the correlation between soil hyperspectral data and surface SOC content increased first and then decreased with the increase of decomposition scale. The R′-CWT-SVM model had the best estimation effect, the R2 of the modeling set and validation set were 0.83 and 0.80, the RMSE were 5.24 and 3.56, and the RPD value was 2.12, which could effectively estimate the surface soil organic carbon content in the study area.

参考文献/References:

[1]WANG J P, WANG X J, ZHANG J, et al. Soil organic and inorganic carbon and stable carbon isotopes in the Yanqi Basin of northwestern China[J]. European Journal of Soil Science, 2015,66:95-103.
[2]张鹏鹏,濮晓珍,张旺锋. 干旱区绿洲农田不同种植模式和秸秆管理下土壤质量评价[J].应用生态学报,2018,29(3):839-849.
[3]赵明松,张甘霖,李德成,等. 江苏省土壤有机质变异及其主要影响因素[J].生态学报,2013,33(16):5058-5066.
[4]童庆禧,张 兵,张立福. 中国高光谱遥感的前沿进展[J]. 遥感学报,2016,20(5):689-707.
[5]谢文,赵小敏,郭熙,等. 基于RBF组合模型的山地红壤有机质含量光谱估测[J].林业科学,2018,54(6):16-23.
[6]祝元丽,王冬艳,张鹤,等. 采用无人机载高分辨率光谱仪反演土壤有机碳含量[J].农业工程学报,2021,37(6):66-72.
[7]纪文君,史舟,周清,等. 几种不同类型土壤的VIS-NIR光谱特性及有机质响应波段[J].红外与毫米波学报,2012,31(3):277-282.
[8]张森,卢霞,聂格格,等. SVM和BP检测滨海湿地土壤有机质[J].光谱学与光谱分析,2020,40(2):556-561.
[9]聂哲,李秀芬,吕家欣,等. 东北典型黑土区表层土壤有机质含量高光谱反演研究[J].土壤通报,2019,50(6):1285-1293.
[10]王敬哲,丁建丽,张东,等. 基于分数阶微分预处理高光谱数据的荒漠土壤有机碳含量估算[J]. 农业工程学报, 2016, 32(21):161-169.
[11]洪永胜,朱亚星,苏学平,等. 高光谱技术联合归一化光谱指数估算土壤有机质含量[J].光谱学与光谱分析,2017,37(11):3537-3542.
[12]张东辉,赵英俊,秦凯,等. 光谱变换方法对黑土养分含量高光谱遥感反演精度的影响[J].农业工程学报,2018,34(20):141-147.
[13]周伟,谢利娟,杨晗,等. 基于高光谱的三江源区土壤有机质含量反演[J].土壤通报,2021,52(3):564-574.
[14]王延仓,杨贵军,朱金山,等. 基于小波变换与偏最小二乘耦合模型估测北方潮土有机质含量[J].光谱学与光谱分析,2014,34(7):1922-1926.
[15]肖艳,辛洪波,王斌,等. 基于小波变换和连续投影算法的黑土有机质含量高光谱估测[J].国土资源遥感,2021,33(2):33-39.
[16]王延仓,金永涛,王晓宁,等. 传统光谱变换与连续小波耦合定量反演潮土有机质含量[J].光谱学与光谱分析,2018,38(8):2571-2577.
[17]谭先明,王仲林,张佳伟,等. 基于连续小波变换的干旱胁迫下玉米冠层叶绿素密度估测[J].干旱地区农业研究,2021,39(4):155-161.
[18]彭咏石,陈水森,陈金月,等. 基于连续小波系数的叶绿素a浓度估测模型[J].激光与光电子学进展,2021,58(8):431-439.
[19]束美艳,顾晓鹤,孙林,等. 倒伏胁迫下的玉米冠层结构特征变化与光谱响应解析[J].光谱学与光谱分析,2019,39(11):3553-3559.
[20]李志,李新国,毛东雷,等. 博斯腾湖西岸湖滨带不同植被类型土壤剖面盐分特征分析[J].西北农业学报,2018,27(2):260-268.
[21]牛芳鹏,李新国,麦麦提吐尔逊·艾则孜,等. 基于连续投影算法的博斯腾湖西岸湖滨绿洲土壤有机碳含量的高光谱估算[J].浙江大学学报(农业与生命科学版),2021,47(5):673-682.
[22]吴才武,夏建新,段峥嵘. 土壤有机质测定方法述评与展望[J].土壤,2015,47(3):453-460.
[23]刘克,赵文吉,郭逍宇,等. 基于地面实测光谱的湿地植物全氮含量估算研究[J].光谱学与光谱分析,2012,32(2):465-471.
[24]张贤龙,张飞,张海威,等. 基于光谱变换的高光谱指数土壤盐分反演模型优选[J].农业工程学报,2018,34（1）: 110-117.
[25]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):164-172.
[26]CHENG T, RIVARD B, SANCHEZ-AZOFEIFA G A, et al. Continuous wavelet analysis for the detection of green attack damage due to mountain pine beetle infestation[J]. Remote Sensing of Environment: An Interdisciplinary Journal,2010,114(4):899-910.
[27]XU S X, SHI X Z, WANG M Y, et al. Effects of subsetting by parent materials on prediction of soil organic matter content in a hilly area using Vis-NIR spectroscopy[J]. PLoS One, 2016, 11(3): e0151536.
[28]于雷,洪永胜,耿雷,等. 基于偏最小二乘回归的土壤有机质含量高光谱估算[J].农业工程学报,2015,31(14):103-109.
[29]BREIMAN L. Random forests[ J]. Machine Learning, 2001,45(1):5-32.
[30]CHANG C C, LIN C J. Training v-support vector regression: theory and algorithms[J]. Neural Computation,2002,14(8):1959-1977.
[31]SHAHRAIYNI H, GHAFOURI M, SHOURAKI S, et al. Comparison between active learning method and support vector machine for runoff modeling[J]. Journal of Hydrology & Hydromechanics, 2012, 60(1):16-32.
[32]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):480-490
[33]刘焕军,张新乐,郑树峰,等. 黑土有机质含量野外高光谱预测模型[J].光谱学与光谱分析,2010,30(12):3355-3358.
[34]杨栋淏,李亚强,刀剑,等. 基于无人机多光谱与地面高光谱遥感的土壤主要养分含量估测[J].江苏农业科学,2022,50(2):178-186.
[35]金宇豪,石楠,文双雅,等. 菜油兼用型油菜籽粒油酸含量的高光谱模型构建[J].南方农业学报,2021,52(6):1674-1682.
[36]张先洁,孙国祥,汪小旵,等. 基于超像素特征向量的果树冠层分割方法[J].江苏农业学报,2021,37(3):724-730.
[37]单慧勇,李晨阳,张程皓,等. 有限二氧化碳资源条件下的温室光气耦合优化调控模型[J].江苏农业学报,2021,37(2):471-479.
[38]沈广辉,曹瑶瑶,刘馨,等. 近红外高光谱成像结合特征波长筛选识别小麦赤霉病瘪粒[J].江苏农业学报,2021,37(2):509-516.
[39]杨爱霞,丁建丽. 新疆艾比湖湿地土壤有机碳含量的光谱测定方法对比[J]. 农业工程学报,2015,31(18):162-168.
[40]尼加提·卡斯木,茹克亚·萨吾提,师庆东,等. 基于优化光谱指数的土壤有机质含量估算[J].农业机械学报,2018,49(11):155-163.
[41]焦彩霞,郑光辉,解宪丽,等. 可见-短近红外成像光谱数据的土壤有机质含量估算[J].光谱学与光谱分析,2020,40(10):3277-3281.
[42]曾胤,陆宇振,杜昌文,等. 应用红外光声光谱技术及支持向量机模型测定土壤有机质含量[J].土壤学报,2014,51(6):1262-1269.
[43]张子鹏,丁建丽,王敬哲,等. 利用三维光谱指数定量估算土壤有机质含量:以新疆艾比湖流域为例[J].光谱学与光谱分析,2020,40(5):1514-1522.

相似文献/References:

[1]牛芳鹏,李新国,麦麦提吐尔逊·艾则孜,等.基于光谱指数的博斯腾湖西岸湖滨绿洲土壤有机碳含量估算模型[J].江苏农业学报,2022,38(02):414.[doi:doi:10.3969/j.issn.1000-4440.2022.02.015]
　NIU Fang-peng,LI Xin-guo,MAMATTURSUN·Eziz,et al.Estimation model of soil organic carbon content in lakeside oasis on the west coast of Bosten Lake based on spectral index[J].,2022,38(01):414.[doi:doi:10.3969/j.issn.1000-4440.2022.02.015]
[2]樊泳灼,李新国.湖滨绿洲棕漠土有机碳含量高光谱估算[J].江苏农业学报,2023,(06):1341.[doi:doi:10.3969/j.issn.1000-4440.2023.06.009]
　FAN Yong-zhuo,LI Xin-guo.Hyperspectral prediction of organic carbon content of brown desert soil in the lakeside oasis[J].,2023,(01):1341.[doi:doi:10.3969/j.issn.1000-4440.2023.06.009]

备注/Memo

备注/Memo:
收稿日期：2022-01-24基金项目：新疆维吾尔自治区自然科学基金项目（2022D01A214）;国家自然科学基金项目（42061007）；新疆维吾尔自治区研究生创新项目（XJ2021G256）作者简介：江远东（1996-）,男,广东五华人,硕士研究生,研究方向为干旱区土壤资源变化及其遥感应用。（E-mail）17875510420@163.com通讯作者：李新国,（E-mail）onlinelxg@163.com
更新日期/Last Update: 2023-03-21