[1]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):1341-1348.[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,(06):1341-1348.[doi:doi:10.3969/j.issn.1000-4440.2023.06.009]
点击复制

湖滨绿洲棕漠土有机碳含量高光谱估算()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年06期
页码:
1341-1348
栏目:
农业信息工程
出版日期:
2023-09-30

文章信息/Info

Title:
Hyperspectral prediction of organic carbon content of brown desert soil in the lakeside oasis
作者:
樊泳灼1; 2; 李新国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):
FAN Yong-zhuo1; 2; LI Xin-guo1; 2
(1.College of Geographical Sciences and Tourism, Xinjiang Normal University, Urumqi 830054, China;2.Xinjiang Key Laboratory of Lake Environment and Resources in Arid Regions, Urumqi 830054, China)
关键词:
土壤有机碳含量; 棕漠土; 高光谱; 竞争性自适应重加权采样-连续投影算法(CARS-SPA); 随机森林
Keywords:
soil organic carbon content; brown desert soil; hyperspectral; competitive adaptive reweighted sampling-successive projection algorithm (CARS-SPA); random forest
分类号:
S127
DOI:
doi:10.3969/j.issn.1000-4440.2023.06.009
文献标志码:
A
摘要:
以博斯腾湖湖滨绿洲为研究区，利用实测棕漠土有机碳含量与高光谱(350～2 500 nm)数据，应用竞争性自适应重加权采样算法(CARS)、连续投影算法(SPA)、竞争性自适应重加权采样-连续投影算法(CARS-SPA)筛选棕漠土有机碳含量响应的高光谱特征波段，分别采用全波段和特征波段结合随机森林(RF)模型构建棕漠土有机碳含量估算模型。结果表明:博斯腾湖湖滨绿洲棕漠土0～50.0 cm土层有机碳含量为1.40～40.92 g/kg，平均值为14.20 g/kg，变异系数为55.54%，呈中等变异水平。CARS、SPA、CARS-SPA等算法筛选出的棕漠土有机碳含量响应特征波段分别为122个、11个和10个。基于CARS-SPA算法筛选出的特征波段数据输入RF模型估算效果最好，验证集检验的决定系数(R2)、相对分析误差(RPD)、均方根误差(RMSE)分别为0.85、2.59和2.72 g/kg，该方法能有效减少光谱数据冗余、提高模型估算精度和运行效率。本研究结果为研究区棕漠土有机碳含量的估算提供参考。
Abstract:
Using the measured organic carbon content of brown desert soil and hyperspectral (350-2 500 nm) data acquired from the lakeside oasis of Bosten Lake, competitive adaptive reweighted sampling (CARS), successive projection algorithm (SPA) and competitive adaptive reweighted sampling-successive projection algorithm (CARS-SPA) were used to screen the characteristic bands of organic carbon content response in brown desert soil. The prediction model of organic carbon content in brown desert soil was constructed by using full band and characteristic band combined with random forest (RF) model. The results showed that the organic carbon content in the 0-50.0 cm soil layer of the brown desert soil in the lakeside oasis of Bosten Lake was 1.40-40.92 g/kg, with an average of 14.20 g/kg, and the coefficient of variation was 55.54%, showing a moderate variation level. The response characteristic bands of brown desert soil organic carbon content screened by CARS, SPA and CARS-SPA were 122, 11 and 10, respectively. The best prediction effect was obtained when the characteristic band data selected by the CARS-SPA algorithm were input into the RF model. The determination coefficient (R2), relative percentage difference (RPD) and root mean square error (RMSE) of the validation set test were 0.85, 2.59 and 2.72 g/kg, respectively. This method could effectively reduce the redundancy of spectral data and improve the prediction accuracy and operation efficiency of the model. The results of this study provided a reference for the prediction of organic carbon content in brown desert soil in the lakeside oasis of Bosten Lake.

参考文献/References:

[1]胡莹洁,孔祥斌,姚静韬.北京市平原区土壤有机碳垂直分布特征[J].生态学报,2019,39(2):561-570.
[2]BURAKA T, ELIAS E, LELAGO A. Soil organic carbon and its’ stock potential in different land-use types along slope position in Coka watershed, Southern Ethiopia[J]. Heliyon, 2022, 8(8):e10261.
[3]周倩倩,丁建丽,黄帅. 干旱区绿洲土壤有机碳高光谱估测及其影响因子分析[J].干旱地区农业研究,2018,36(5):200-206,214.
[4]贡璐,朱美玲,刘曾媛,等. 塔里木盆地南缘典型绿洲土壤有机碳、无机碳与环境因子的相关性[J].环境科学,2016,37(4):1516-1522.
[5]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.
[6]吴俊,郭大千,李果,等. 基于CARS-BPNN的江西省土壤有机碳含量高光谱预测[J].中国农业科学,2022,55(19):3738-3750.
[7]钟翔君,杨丽,张东兴,等. 砂壤潮土有机质含量可见-近红外光谱预测[J].光谱学与光谱分析,2022,42(9):2924-2930.
[8]LAAMRANI A, BERG A A, VORONEY P, et al. Ensemble identification of spectral bands related to soil organic carbon levels over an agricultural field in southern Ontario, Canada[J]. Remote Sensing， 2019, 11(11):1298.
[9]唐海涛,孟祥添,苏循新,等. 基于CARS算法的不同类型土壤有机质高光谱预测[J].农业工程学报,2021,37(2):105-113.
[10]章海亮,罗微,刘雪梅,等. 应用遗传算法结合连续投影算法近红外光谱检测土壤有机质研究[J].光谱学与光谱分析,2017,37(2):584-587.
[11]WANG S, CHEN Y, WANG M, et al. SPA-based methods for the quantitative estimation of the soil salt content in saline-alkali land from field spectroscopy data: A case study from the Yellow River irrigation regions[J]. Remote Sensing, 2019,11(8):967.
[12]LIU J B, DONG Z Y, XIA J S, et al. Estimation of soil organic matter content based on CARS algorithm coupled with random forest[J]. Spectrochimica Acta, Part A: Molecular and Biomolecular Spectroscopy,2021,258: 119823.
[13]CHENG H, WANG J, DU Y. Combining multivariate method and spectral variable selection for soil total nitrogen estimation by Vis-NIR spectroscopy[J]. Archives of Agronomy and Soil Science, 2021, 67(12): 1665-1678.
[14]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.
[15]赵慧,李新国,靳万贵,等. 基于地理加权回归模型的博斯腾湖湖滨绿洲土壤盐分离子含量高光谱估算[J].土壤,2021,53(3):646-653.
[16]肖云飞,高小红,李冠稳. 土壤有机质可见光-近红外光谱预测样本优化选择[J].土壤,2020,52(2):404-413.
[17]CLOUTIS E A. Hyperspectral geological remote sensing: evaluation of analytical techniques[J]. International Journal of Remote Sensing,1996,17(12): 2215-2242.
[18]DING J, YANG A, WANG J, et al. Machine-learning-based quantitative estimation of soil organic carbon content by VIS/NIR spectroscopy[J]. Peer J, 2018, 6: e5714.
[19]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.
[20]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):135-141.
[21]XU S, ZHAO Y, WANG M, et al. Comparison of multivariate methods for estimating selected soil properties from intact soil cores of paddy fields by VIS-NIR spectroscopy[J]. Geoderma,2018, 310: 29-43.
[22]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.
[23]马利芳,熊黑钢,张芳. 基于野外VIS-NIR光谱的土壤盐分主要离子预测[J].土壤,2020,52(1):188-194.

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(06):414.[doi:doi:10.3969/j.issn.1000-4440.2022.02.015]
[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,(06):118.[doi:doi:10.3969/j.issn.1000-4440.2023.01.014]

备注/Memo

备注/Memo:
收稿日期:2023-01-18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(41661047)作者简介:樊泳灼(1999-)，女，新疆塔城人，硕士研究生，主要从事干旱区土壤资源变化及遥感应用研究。(E-mail)yongzhuofan@sina.com通讯作者:李新国，(E-mail)onlinelxg@sina.com
更新日期/Last Update: 2023-11-17