[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):414-421.[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(02):414-421.[doi:doi:10.3969/j.issn.1000-4440.2022.02.015]
点击复制

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()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
38
期数:
2022年02期
页码:
414-421
栏目:
农业信息工程
出版日期:
2022-04-30

文章信息/Info

Title:
Estimation model of soil organic carbon content in lakeside oasis on the west coast of Bosten Lake based on spectral index
作者:
牛芳鹏1; 2; 李新国1; 2; 麦麦提吐尔逊·艾则孜1; 2; 赵慧1; 2; 江远东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):
NIU Fang-peng1; 2; LI Xin-guo1; 2; MAMATTURSUN·Eziz1; 2; ZHAO Hui1; 2; JIANG Yuan-dong1; 2
(1.College of Geographic Sciences and Tourism, Xinjiang Normal University, Urumqi 830054, China;2.Xinjiang Laboratory of Lake Environment and Resources in Arid Zone, Urumqi 830054, China)
关键词:
土壤有机碳含量; 估算模型; 光谱指数; 随机森林; 湖滨绿洲
Keywords:
soil organic carbon content; estimation model; spectral index; random forest; lakeside oasis
分类号:
S153.6
DOI:
doi:10.3969/j.issn.1000-4440.2022.02.015
文献标志码:
A
摘要:
以博斯腾湖西岸湖滨绿洲为研究区，将野外原位高光谱实测数据和土壤有机碳（SOC）含量作为基础数据，通过对原始光谱进行4种数学变换，探索不同光谱变换形式下的弓曲差（C）、差值光谱指数（DSI）、简单比值土壤指数（RSI）、亮度光谱指数（BSI）、归一化土壤指数（NDSI）与SOC含量的关系，并建立基于随机森林法（RF）的SOC含量估算模型。结果表明：（1）研究区SOC含量主要集中在5.25～78.76 g/kg，平均值为21.82 g/kg，变异系数为69.11%，呈中等变异性；（2）在光谱数据lgR下，SOC含量与DIS指数相关系数最高，相关系数为0.80，最佳组合波段为（1 758 nm，1 752 nm）；（3）基于不同光谱指数与弓曲差（C）建立的模型验证集精度R2和RMSE分别介于0.67～0.84和5.85～8.45 g/kg，模型的RPD均在1.66以上；在基于光谱数据lg(1/R)变换下，模型的验证集R2=0.82、RMSE=3.52 g/kg、RPD=3.99，可以较好地估算研究区SOC含量，为干旱半干旱地区湖滨绿洲SOC含量反演提供依据和参考。
Abstract:
Taking the lakeside oasis on the west coast of Bosten Lake as the study area, and the in situ hyperspectral data and soil organic carbon (SOC) content were taken as the basic data. Four mathematical transformations were performed on the original spectrum to explore the relationships between bow curvature difference (C), difference spectral index (DSI), simple ratio soil index (RSI), brightness spectral index (BSI), normalized soil index (NDSI) and SOC content. A SOC content estimation model based on random forest method was established. The results indicated that the content of SOC was mainly concentrated in 5.25-78.76 g/kg, the average value was 21.82 g/kg, the coefficient of variation was 69.11%, showing moderate variability. Under the spectral data lgR, the correlation coefficient between SOC content and DIS index was the highest, the correlation coefficient was 0.80, and the best combination band was (1 758 nm, 1 752 nm). The R2 and RMSE of the model validation set based on different spectral indices and C were 0.67-0.84 and 5.85-8.45 g/kg, respectively, and the RPD of the model was above 1.66. Based on the transformation of spectral data lg(1/R), the R2, RMSE and RPD of the model validation set were 0.82, 3.52 g/kg and 3.99, respectively. The model can better estimate the SOC content in the study area, and the research results can provide the basis and reference for the inversion of SOC content in lakeside oasis in arid and semi-arid regions.

参考文献/References:

[1]SHI Z, JI W, VISCARRA ROSSEL R A, et al. Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis-NIR spectral library[J]. European Journal of Soil Science,2015,66(4):679-687.
[2]ALLEN R M, LAIRD D A. Quantitative prediction of biochar soil amendments by near-infrared reflectance spectroscopy[J]. Soil Science Society of America Journal,2013,77(5):1784-1794.
[3]WARD K J, CHARBRILLAT S, NEUMANN C, et al. A remote sensing adapted approach for soil organic carbon prediction based on the spectrally clustered LUCAS soil database[J]. Geoderma,2019, 353: 297-307.
[4]林鹏达,佟志军,张继权,等. 基于CWT的黑土有机质含量野外高光谱反演模型[J].水土保持研究,2018,25(2):46-52,57.
[5]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):31-42.
[6]GUNSAULIS F R, KOCHER M F, GRIFFIS C L. Surface structure effects on close-range reflectance as a function of soil organic matter content[J]. American Society of Agricultural Engineer,1991,34(2):641-649.
[7]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.
[8]AMIN I, FIKRAT F, MAMMADOV E, et al. Soil organic carbon prediction by Vis-NIR spectroscopy: case study the Kur-Aras plain, Azerbaijan[J]. Communications in Soil Science and Plant Analysis,2020,51(6):726-734.
[9]ZHENG G H, RYU D, JIAO C X, et al. Estimation of organic matter content in coastal soil using reflectance spectroscopy[J]. Pedosphere,2016,26(1):130-136.
[10]王海峰,张智韬,ARNON K,等. 基于灰度关联-岭回归的荒漠土壤有机质含量高光谱估算[J].农业工程学报,2018,34(14):124-131.
[11]赵明松,谢毅,陆龙妹,等. 基于高光谱特征指数的土壤有机质含量建模[J].土壤学报,2021,58(1):42-54.
[12]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.
[13]HONG Y, CHEN S, CHEN Y, et al. Comparing laboratory and airborne hyperspectral data for the estimation and mapping of topsoil organic carbon: Feature selection coupled with random forest[J]. Soil and Tillage Research,2020,199:104589.
[14]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):156-167.
[15]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.
[16]牛芳鹏,李新国,靳万贵,等. 博斯腾湖西岸湖滨绿洲土壤盐分特征[J].中国土壤与肥料,2020(3):8-15.
[17]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.
[18]何挺,程烨,王静. 野外地物光谱测量技术及方法[J].中国土地科学,2002(5):30-36.
[19]张子鹏,丁建丽,王敬哲. 基于谐波分析算法的干旱区绿洲土壤光谱特性研究[J].光学学报,2019,39(2):391-401.
[20]朱建伟,刘玉学,吴超凡,等. 施用生物炭后土壤有机碳的近红外光谱模型研究与应用[J].生态学报,2020,40(20):7430-7440.
[21]徐彬彬. 土壤剖面的反射光谱研究[J].土壤,2000(6):281-287.
[22]ALLBED A, KUMAR L, SINHA P. Soil salinity and vegetation cover change detection from multi-temporal remotely sensed imagery in Al Hassa Oasis in Saudi Arabia[J]. Geocarto International,2018,33(8):830-846.
[23]李哲,张飞,冯海宽,等. 基于波段组合的植被叶片盐离子估算研究[J].光学学报,2017,37(11):325-339.
[24]王李娟,孔钰如,杨小冬,等. 基于特征优选随机森林算法的农耕区土地利用分类[J].农业工程学报,2020,36(4):244-250.
[25]包青岭,丁建丽,王敬哲,等. 基于随机森林算法的土壤有机质含量高光谱检测[J].干旱区地理,2019,42(6):1404-1414.
[26]张锐,李兆富,潘剑君. 小波包-局部最相关算法提高土壤有机碳含量高光谱预测精度[J].农业工程学报,2017,33(1):175-181.
[27]张娟娟,田永超,姚霞,等. 同时估测土壤全氮、有机质和速效氮含量的光谱指数研究[J].土壤学报,2012,49(1):50-59.
[28]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.
[29]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.
[30]曹肖奕,丁建丽,葛翔宇,等. 基于光谱指数与机器学习算法的土壤电导率估算研究[J].土壤学报,2020,57(4):867-877.
[31]WANG J Z, DING J L, ABULIMITI A, et al. Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared（VIS-NIR）spectroscopy, Ebinur Lake Wetland, Northwest China[J]. PeerJ,2018,6: e4703.

相似文献/References:

[1]郑曼迪,熊黑钢,乔娟峰,等.基于综合光谱指数的不同程度人类干扰下土壤有机质含量预测[J].江苏农业学报,2018,(05):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]
　ZHENG Man-di,XIONG Hei-gang,QIAO Juan-feng,et al.Prediction of soil organic matter content based on comprehensive spectral index at different levels of human disturbance[J].,2018,(02):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]
[2]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.[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,(02):118.[doi:doi:10.3969/j.issn.1000-4440.2023.01.014]
[3]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,(02):1341.[doi:doi:10.3969/j.issn.1000-4440.2023.06.009]

备注/Memo

备注/Memo:
收稿日期：2021-07-11基金项目：国家自然科学基金项目（41661047、U2003301）；新疆维吾尔自治区重点实验室开放课题（2018D04026）作者简介：牛芳鹏（1995-），男，甘肃庄浪人，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研究。（E-mail）niufp0225@163.com通讯作者：李新国，（E-mail）onlinelxg@sina.com
更新日期/Last Update: 2022-05-07