基于机载高光谱影像的农田尺度土壤有机碳密度制图

刘潜; 王梦迪; 郭龙; 王冉; 贾中甫; 胡献君; 唐乾坤; 石铁柱

doi:10.11834/jrs.20221805

高光谱遥感应用 | 浏览量 : 0 下载量: 182 CSCD: 0 更多指标

R-PDF
PDF
导出
分享
收藏
专辑

基于机载高光谱影像的农田尺度土壤有机碳密度制图
Mapping of soil organic carbon density at farmland scale based on airborne hyperspectral images
2024年28卷第1期页码：293-305
纸质出版日期： 2024-01-07 ，
DOI： 10.11834/jrs.20221805

扫描看全文

刘潜，王梦迪，郭龙，王冉，贾中甫，胡献君，唐乾坤，石铁柱.2024.基于机载高光谱影像的农田尺度土壤有机碳密度制图.遥感学报，28（1）： 293-305

Liu Q，Wang M D，Guo L，Wang R，Jia Z F，Hu X J，Tang Q K and Shi T Z. 2024. Mapping of soil organic carbon density at farmland scale based on airborne hyperspectral images. National Remote Sensing Bulletin， 28（1）：293-305
刘潜，王梦迪，郭龙，王冉，贾中甫，胡献君，唐乾坤，石铁柱.2024.基于机载高光谱影像的农田尺度土壤有机碳密度制图.遥感学报，28（1）： 293-305 DOI： 10.11834/jrs.20221805.

Liu Q，Wang M D，Guo L，Wang R，Jia Z F，Hu X J，Tang Q K and Shi T Z. 2024. Mapping of soil organic carbon density at farmland scale based on airborne hyperspectral images. National Remote Sensing Bulletin， 28（1）：293-305 DOI： 10.11834/jrs.20221805.

摘要

准确监测土壤有机碳密度SOCD（Soil Organic Carbon Density）对调控土壤碳汇、合理利用土壤资源具有重要意义。机载高光谱影像为精细化SOCD制图提供了重要数据源。由于机载高光谱在数据收集过程中易受到外部因素的影响，光谱中存在噪声影响SOCD的估算精度。因此，本研究旨在探究基于机载高光谱影像估算SOCD的技术流程。对原始光谱进行预处理，包括一阶微分FD（First Derivative）和包络线去除CR（Continuum Removal）变换。采用遗传算法GA（Genetic Algorithm）选择特征波段，并结合不同回归方法，如偏最小二乘回归PLSR（Partial Least Square Regression）、多元线性回归MLR（Multiple Linear Regression）、支持向量机SVM（Support Vector Machine）和人工神经网络ANN（Artificial Neural Network）估算SOCD。结果表明，在经过GA特征波段选择后，原始光谱、FD光谱和CR光谱预测SOCD的精度均有所提高。使用原始光谱特征波段，PLSR、MLR、SVM和ANN共4种模型预测SOCD的决定系数R²分别为0.672、0.621、0.551和0.678。使用FD与CR光谱特征波段的R²范围分别在0.452—0.593和0.332—0.602，具有较大的误差。利用原始光谱的特征波段进行SOCD数字制图，不同回归模型预测的SOCD在空间上具有较为相似的变化趋势，与SOCD测量值较为相近，绝对误差较大的点多出现在采样点边缘附近。

Abstract

Accurate monitoring of Soil Organic Carbon Density (SOCD) is important for regulating soil carbon sinks and rationally using soil resources. Airborne hyperspectral images provide important data sources for SOCD mapping. The noise in the spectrum affects the accuracy of SOCD estimation because airborne hyperspectral images are easily affected by external factors during data collection. A set of technical processes that are suitable for airborne hyperspectral data processing is still lacking. Therefore

this study aims to investigate the technical process of SOCD estimation based on airborne hyperspectral images. The original spectra are preprocessed by First Derivative (FD) and Continuum Removal (CR) transform. Genetic Algorithm (GA) was used to select the feature bands. Different regression methods

such as Partial Least-Squares Regression (PLSR)

Multiple Linear Regression (MLR)

Support Vector Machine (SVM)

and Artificial Neural Network (ANN)

were used to estimate SOCD. Results showed that the accuracy of SOCD prediction for original

and CR spectra was improved after feature band selection by GA. With the feature bands of original spectra

the

² of SOCD predicted by PLSR

MLR

SVM

and ANN are 0.672

0.621

0.551

and 0.678

respectively. The range of

² are 0.452—0.593 and 0.332—0.602 with FD and CR feature bands

respectively

which demonstrate large errors. The feature bands of the original spectrum were used in this study for SOCD mapping. The SOCD predicted by four regression models has a highly similar trend in space and is similar to the SOCD measured value. The points with large absolute errors mostly occur near the edges of the sampling points.

关键词

土壤有机碳密度机载高光谱遗传算法数字土壤制图

Keywords

soil organic carbon densityairborne hyperspectral imagesgenetic algorithmdigital soil mapping

references

Ben-Dor E. 2002. Quantitative remote sensing of soil properties. Advances in Agronomy, 75: 173-243 [DOI: 10.1016/S0065-2113(02)75005-0http://dx.doi.org/10.1016/S0065-2113(02)75005-0]

Besalatpour A A, Ayoubi S, Hajabbasi M A, Mosaddeghi M R and Schulin R. 2013. Estimating wet soil aggregate stability from easily available properties in a highly mountainous watershed. CATENA, 111: 72-79 [DOI: 10.1016/j.catena.2013.07.001http://dx.doi.org/10.1016/j.catena.2013.07.001]

Cai J N, Liu H L, Jiang B, He T H, Chen W J, Feng Z W, Li Z L and Xing Q G. 2020. Using hyperspectral imagery and GA-PLS algorithm to estimate chemical oxygen demand concentration of water in river network. Journal of Irrigation and Drainage, 39(9): 126-131

蔡建楠, 刘海龙, 姜波, 何甜辉, 陈文杰, 冯志伟, 黎倬琳, 邢前国. 2020. 基于GA-PLS算法的河网水体化学需氧量高光谱反演. 灌溉排水学报, 39(9): 126-131 [DOI: 10.13522/j.cnki.ggps. 2020063http://dx.doi.org/10.13522/j.cnki.ggps.2020063]

Castaldi F, Palombo A, Santini F, Pascucci S, Pignatti S and Casa R. 2016. Evaluation of the potential of the current and forthcoming multispectral and hyperspectral imagers to estimate soil texture and organic carbon. Remote Sensing of Environment, 179: 54-65 [DOI: 10.1016/j.rse.2016.03.025http://dx.doi.org/10.1016/j.rse.2016.03.025]

Chen Y Y, Qi T C, Huang Y J, Wan Y, Zhao R Y, Qi L, Zhang C and Fei T. 2017. Optimization method of calibration dataset for VIS-NIR spectral inversion model of soil organic matter content. Transactions of the Chinese Society of Agricultural Engineering, 33(6): 107-114

陈奕云, 齐天赐, 黄颖菁, 万远, 赵瑞瑛, 亓林, 张超, 费腾. 2017. 土壤有机质含量可见-近红外光谱反演模型校正集优选方法. 农业工程学报, 33(6): 107-114 [DOI: 10.11975/j.issn.1002-6819.2017.06.014http://dx.doi.org/10.11975/j.issn.1002-6819.2017.06.014]

Chen Z, Lü C H, Fan L and Wu H. 2011. Effects of land use change on soil organic carbon: a review. Acta Ecologica Sinica, 31(18): 5358-5371

陈朝, 吕昌河, 范兰, 武红. 2011. 土地利用变化对土壤有机碳的影响研究进展. 生态学报, 31(18): 5358-5371

Chu X L, Yuan H F, Wang Y B and Lu W Z. 2001. Variable selection for partial least squares modeling by genetic algorithms. Chinese Journal of Analytical Chemistry, 29(4): 437-442

褚小立, 袁洪福, 王艳斌, 陆婉珍. 2001. 遗传算法用于偏最小二乘方法建模中的变量筛选. 分析化学, 29(4): 437-442 [DOI: 10.3321/j.issn:0253-3820.2001.04.018http://dx.doi.org/10.3321/j.issn:0253-3820.2001.04.018]

Gomez C, Adeline K, Bacha S, Driessen B, Gorretta N, Lagacherie P, Roger J M and Briottet X. 2018. Sensitivity of clay content prediction to spectral configuration of VNIR/SWIR imaging data, from multispectral to hyperspectral scenarios. Remote Sensing of Environment, 204: 18-30 [DOI: 10.1016/j.rse.2017.10.047http://dx.doi.org/10.1016/j.rse.2017.10.047]

Guo L, Fu P, Shi T Z, Chen Y Y, Zhang H T, Meng R and Wang S Q. 2020. Mapping field-scale soil organic carbon with unmanned aircraft system-acquired time series multispectral images. Soil and Tillage Research, 196: 104477 [DOI: 10.1016/j.still.2019.104477http://dx.doi.org/10.1016/j.still.2019.104477]

Guo L, Sun X R, Fu P, Shi T Z, Dang L N, Chen Y Y, Linderman M, Zhang G L, Zhang Y, Jiang Q H, Zhang H T and Zeng C. 2021. Mapping soil organic carbon stock by hyperspectral and time-series multispectral remote sensing images in low-relief agricultural areas. Geoderma, 398: 115118 [DOI: 10.1016/J.GEODERMA.2021.115118http://dx.doi.org/10.1016/J.GEODERMA.2021.115118]

Hong Y S, Chen S C, Chen Y Y, Linderman M, Mouazen A M, Liu Y L, Guo L, Yu L, Liu Y F, Cheng H and Liu Y. 2020. Comparing laboratory and airborne hyperspectral data for the estimation and mapping of topsoil organic carbon: feature selection coupled with random forest. Soil and Tillage Research, 199: 104589 [DOI: 10.1016/j.still.2020.104589http://dx.doi.org/10.1016/j.still.2020.104589]

Ji W J, Li X, Li C X, Zhou Y and Shi Z. 2012. Using different data mining algorithms to predict soil organic matter based on visible-near infrared spectroscopy. Spectroscopy and Spectral Analysis, 32(9): 2393-2398, 2408

纪文君, 李曦, 李成学, 周银, 史舟. 2012. 基于全谱数据挖掘技术的土壤有机质高光谱预测建模研究. 光谱学与光谱分析, 32(9): 2393-2398, 2408 [DOI: 10.3964/j.issn.1000-0593(2012)09-2393-06http://dx.doi.org/10.3964/j.issn.1000-0593(2012)09-2393-06]

Knadel M, Viscarra Rossel R A, Deng F, Thomsen A and Greve M H. 2013. Visible-near infrared spectra as a proxy for topsoil texture and glacial boundaries. Soil Science Society of America Journal, 77(2): 568-579 [DOI: 10.2136/sssaj2012.0093http://dx.doi.org/10.2136/sssaj2012.0093]

Lal R. 2004. Soil carbon sequestration impacts on global climate change and food security. Science, 304(5677): 1623-1627 [DOI: 10.1126/science.1097396http://dx.doi.org/10.1126/science.1097396]

Leardi R, Boggia R and Terrile M. 1992. Genetic algorithms as a strategy for feature selection. Journal of Chemometrics, 6(5): 267-281 [DOI: 10.1002/cem.1180060506http://dx.doi.org/10.1002/cem.1180060506]

Li L, Ustin S L and Riano D. 2007. Retrieval of fresh leaf fuel moisture content using genetic algorithm partial least squares (GA-PLS) modeling. IEEE Geoscience and Remote Sensing Letters, 4(2): 216-220 [DOI: 10.1109/LGRS.2006.888847http://dx.doi.org/10.1109/LGRS.2006.888847]

Liu H J, Zhang Y Z and Zhang B. 2009. Novel hyperspectral reflectance models for estimating black-soil organic matter in Northeast China. Environmental Monitoring and Assessment, 154(1/4): 147-154 [DOI: 10.1007/s10661-008-0385-4http://dx.doi.org/10.1007/s10661-008-0385-4]

Liu Y F, Song Y L, Guo L, Chen Y Y, Lu Y N and Liu Y. 2017. Geostatistical models of soil organic carbon density prediction based on soil hyperspectral reflectance. Transactions of the Chinese Society of Agricultural Engineering, 33(2): 183-191

刘艳芳, 宋玉玲, 郭龙, 陈奕云, 卢延年, 刘以. 2017. 结合高光谱信息的土壤有机碳密度地统计模型. 农业工程学报, 33(2): 183-191 [DOI: 10.11975/j.issn.1002-6819.2017.02.025http://dx.doi.org/10.11975/j.issn.1002-6819.2017.02.025]

Lu Y N, Liu Y F, Chen Y Y and Jiang Q H. 2014. Optimization of the hyperspectral prediction model of soil organic carbon contents of Jianghan plain. Chinese Agricultural Science Bulletin, 30(26): 127-133

卢延年, 刘艳芳, 陈奕云, 姜庆虎. 2014. 江汉平原土壤有机碳含量高光谱预测模型优选. 中国农学通报, 30(26): 127-133 [DOI: 10.11924/j.issn.1000-6850.2014-0439http://dx.doi.org/10.11924/j.issn.1000-6850.2014-0439]

Luo M, Guo L, Zhang H T, Wang S Q and Liang P. 2020. Characterization of spatial distribution of soil organic carbon in China based on environmental variables. Acta Pedologica Sinica, 57(1): 48-59

罗梅, 郭龙, 张海涛, 汪善勤, 梁攀. 2020. 基于环境变量的中国土壤有机碳空间分布特征. 土壤学报, 57(1): 48-59 [DOI: 10.11766/trxb201812110454http://dx.doi.org/10.11766/trxb201812110454]

Nie Z, Li X F, Lv J X and Zheng X. 2019. Hyperspectral retrieval of surface soil organic matter content in a typical black soil region of northeast China. Chinese Journal of Soil Science, 50(6): 1285-1293

聂哲, 李秀芬, 吕家欣, 郑晓. 2019. 东北典型黑土区表层土壤有机质含量高光谱反演研究. 土壤通报, 50(6): 1285-1293 [DOI: 10.19336/j.cnki.trtb.2019.06.04http://dx.doi.org/10.19336/j.cnki.trtb.2019.06.04]

Nouri M, Gomez C, Gorretta N and Roger J M. 2017. Clay content mapping from airborne hyperspectral Vis-NIR data by transferring a laboratory regression model. Geoderma, 298: 54-66 [DOI: 10.1016/j.geoderma.2017.03.011http://dx.doi.org/10.1016/j.geoderma.2017.03.011]

Peng J, Li X, Zhou Q, Shi Z, Ji W J and Wang J Q. 2013. Influence of iron oxide on the spectral characteristics of organic matter. Journal of Remote Sensing, 17(6): 1396-1412

彭杰, 李曦, 周清, 史舟, 纪文君, 王家强. 2013. 氧化铁对有机质光谱特性的影响分析. 遥感学报, 17(6): 1396-1412 [DOI: 10.11834/jrs.20132273http://dx.doi.org/10.11834/jrs.20132273]

Qiao T, Lv C W, Xiao W P, Lv K and Shui H W. 2018. Hyperspectral prediction modeling of soil texture based on genetic algorithm. Chinese Journal of Soil Science, 49(4): 773-778

乔天, 吕成文, 肖文凭, 吕凯, 水宏伟. 2018. 基于遗传算法的土壤质地高光谱预测模型研究. 土壤通报, 49(4): 773-778 [DOI: 10.19336/j.cnki.trtb.2018.04.03http://dx.doi.org/10.19336/j.cnki.trtb.2018.04.03]

Reda R, Saffaj T, Derrouz H, Itqiq S E, Bouzida I, Saidi O, Lakssir B and El Hadrami E M. 2021. Comparing CalReg performance with other multivariate methods for estimating selected soil properties from Moroccan agricultural regions using NIR spectroscopy. Chemometrics and Intelligent Laboratory Systems, 211: 104277 [DOI: 10.1016/j.chemolab.2021.104277http://dx.doi.org/10.1016/j.chemolab.2021.104277]

Shi T Z, Chen Y Y, Liu H Z, Wang J J and Wu G F. 2014. Soil organic carbon content estimation with laboratory-based visible-near-infrared reflectance spectroscopy: feature selection. Applied Spectroscopy, 68(8): 831-837 [DOI: 10.1366/13-07294http://dx.doi.org/10.1366/13-07294]

Shi Z, Guo Y, Jin X and Wu H X. 2011. Advancement in study on proximal soil sensing. Acta Pedologica Sinica, 48(6): 1274-1281

史舟, 郭燕, 金希, 吴豪翔. 2011. 土壤近地传感器研究进展. 土壤学报, 48(6): 1274-1281 [DOI: 10.11766/trxb201012070517http://dx.doi.org/10.11766/trxb201012070517]

Shi Z, Liang Z Z, Yang Y Y and Guo Y. 2015. Status and prospect of agricultural remote sensing. Transactions of the Chinese Society for Agricultural Machinery, 46(2): 247-260

史舟, 梁宗正, 杨媛媛, 郭燕. 2015. 农业遥感研究现状与展望. 农业机械学报, 46(2): 247-260 [DOI: 10.6041/j.issn.1000-1298.2015.02.037http://dx.doi.org/10.6041/j.issn.1000-1298.2015.02.037]

Shi Z, Xu D Y, Teng H F, Hu Y M, Pan X Z and Zhang G L. 2018. Soil information acquisition based on remote sensing and proximal soil sensing: current status and prospect. Progress in Geography, 37(1): 79-92

史舟, 徐冬云, 滕洪芬, 胡月明, 潘贤章, 张甘霖. 2018. 土壤星地传感技术现状与发展趋势. 地理科学进展, 37(1): 79-92 [DOI: 10.18306/dlkxjz.2018.01.009http://dx.doi.org/10.18306/dlkxjz.2018.01.009]

Vapnik V N. 1998. Statistical Learning Theory. New York: John Wiley & Sons

Vaudour E, Gilliot J M, Bel L, Lefevre J and Chehdi K. 2016. Regional prediction of soil organic carbon content over temperate croplands using visible near-infrared airborne hyperspectral imagery and synchronous field spectra. International Journal of Applied Earth Observation and Geoinformation, 49: 24-38 [DOI: 10.1016/j.jag.2016.01.005http://dx.doi.org/10.1016/j.jag.2016.01.005]

Viscarra Rossel R A and Behrens T. 2010. Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma, 158(1/2): 46-54 [DOI: 10.1016/j.geoderma.2009.12.025http://dx.doi.org/10.1016/j.geoderma.2009.12.025]

Wen F P, Zhao W, Hu L, Xu H X and Cui Q. 2021. SMAP passive microwave soil moisture spatial downscaling based on optical remote sensing data: a case study in Shandian river basin. National Remote Sensing Bulletin, 25(4): 962-973

文凤平, 赵伟, 胡路, 徐红新, 崔倩. 2021. 耦合MODIS数据的SMAP被动微波土壤水分空间降尺度研究——以闪电河流域为例. 遥感学报, 25(4): 962-973 [DOI: 10.11834/jrs.20219393http://dx.doi.org/10.11834/jrs.20219393]

Wold H. 1966. Nonlinear estimation by iterative least squares procedures//David F N and Neyman J, eds. Research Papers in Statistics, Festschrift for J. Neyman. New York: Wiley: 441-444

Xie X F, Wu T, Zhu M, Jiang G J, Xu Y, Wang X H and Pu L J. 2021. Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land. Ecological Indicators, 120: 106925 [DOI: 10.1016/j.ecolind.2020.106925http://dx.doi.org/10.1016/j.ecolind.2020.106925]

Yu L, Hong Y S, Zhou Y, Zhu Q, Xu L, Li J Y and Nie Y. 2016. Wavelength variable selection methods for estimation of soil organic matter content using hyperspectral technique. Transactions of the Chinese Society of Agricultural Engineering, 32(13): 95-102

于雷, 洪永胜, 周勇, 朱强, 徐良, 李冀云, 聂艳. 2016. 高光谱估算土壤有机质含量的波长变量筛选方法. 农业工程学报, 32(13): 95-102 [DOI: 10.11975/j.issn.1002-6819.2016.13.014http://dx.doi.org/10.11975/j.issn.1002-6819.2016.13.014]

Zhan B S, Ni J H and Li J. 2014. Hyperspectral technology combined with CARS algorithm to quantitatively determine the SSC in Korla fragrant pear. Spectroscopy and Spectral Analysis, 34(10): 2752-2757

詹白勺, 倪君辉, 李军. 2014. 高光谱技术结合CARS算法的库尔勒香梨可溶性固形物定量测定. 光谱学与光谱分析, 34(10): 2752-2757 [DOI: 10.3964/j.issn.1000-0593(2014)10-2752-06http://dx.doi.org/10.3964/j.issn.1000-0593(2014)10-2752-06]

Zheng G H, Wang M J, Jiao C X and Sun D M. 2013. Review on prediction of soil organic matter with reflectance spectroscopy. Journal of Nanjing University of Information Science and Technology (Natural Science Edition), 5(6): 481-486

郑光辉, 王明江, 焦彩霞, 孙东敏. 2013. 土壤有机质高光谱估算研究进展. 南京信息工程大学学报(自然科学版), 5(6): 481-486 [DOI: 10.13878/j.cnki.jnuist.2013.06.001http://dx.doi.org/10.13878/j.cnki.jnuist.2013.06.001]

Zou X B and Zhao J J. 2007. Methods of characteristic wavelength region and wavelength selection based on genetic algorithm. Acta Optica Sinica, 27(7): 1316-1321

邹小波, 赵杰文. 2007. 用遗传算法快速提取近红外光谱特征区域和特征波长. 光学学报, 27(7): 1316-1321 [DOI: 10.3321/j.issn:0253-2239.2007.07.032http://dx.doi.org/10.3321/j.issn:0253-2239.2007.07.032]

文章被引用时，请邮件提醒。

提交

基于改进遗传算法的SAR多星协同复杂区域观测规划

基于星地传感技术的土壤盐渍化监测：进展与展望

基于遗传算法局部方向梯度的古墓葬圆形土壤标志检测(英文)

面向遥感目标识别耦合GA与SVM的特征优选方法