Please wait a minute...
 
Remote Sensing for Natural Resources    2024, Vol. 36 Issue (3) : 225-232     DOI: 10.6046/zrzyyg.2023068
|
A method for hyperspectral inversion of element contents for soil-quality evaluation of cultivated land
YI Zifang1,2(), ZHOU Leilei1,2, LUO Jianlan1, CAO Li2()
1. Hunan Geophysical and Geochemical Institute, Changsha 410116, China
2. Key Laboratory of Natural Resources Monitoring and Supervision in Southern Hilly Region, Ministry of Natural Resources, Changsha 410119, China
Download: PDF(8083 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

To explore the feasibility and accuracy of the method of utilizing hyperspectral data to estimate the contents of elements Cd and As for soil quality elevation of cultivated land, this study delves into the extraction of characteristic bands of the spectra of both elements and the modeling of quantitative hyperspectral inversion. The characteristic bands of spectra were extracted using multiple methods derived from the combination of four spectral transformations and two feature selection methods, with the former comprising first-order /second-order differential (FD/SD), reciprocal logarithm (LR), and continuum removal (CR) and the latter consisting of the competitive adaptive reweighted sampling (CARS) method and the Pearson correlation coefficient (PCC) analysis. Based on this, the element content inversion was conducted using the partial least squares regression (PLSR) and the particle swarm optimization optimized random forest regression (PSO-RFR), followed by the verification of inversion accuracy. The results indicate that the FD-CARS-PLSR inversion model exhibited the best prediction effect for both elements, with maximum determination coefficients R2 of 0.863 and 0.959 and relative percent differences (RPDs) of 2.799 and 5.119 for Cd and As, respectively. The FD and SD spectral transformations combined with the CARS method can improve the accuracy of the PLSR inversion model. The results of this study can provide a reference for the rapid estimation of the contents of Cd and As in soil.
Keywords hyperspectral remote sensing      spectral transformation      characteristic band selection      partial least squares regression      competitive adaptive reweighted sampling     
ZTFLH:  TP79  
  P237  
Issue Date: 03 September 2024
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Zifang YI
Leilei ZHOU
Jianlan LUO
Li CAO
Cite this article:   
Zifang YI,Leilei ZHOU,Jianlan LUO, et al. A method for hyperspectral inversion of element contents for soil-quality evaluation of cultivated land[J]. Remote Sensing for Natural Resources, 2024, 36(3): 225-232.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2023068     OR     https://www.gtzyyg.com/EN/Y2024/V36/I3/225
Fig.1  Location of research area and sample distribution
Fig.2  Spectral reflectance curve of soil samples
Fig.3  Correlation coefficient of original spectrum and its transformed spectrum with element content
元素 预处理方法 特征波段数 最大相关系数①
Cd YS 241 (0.385)*
FD 73 (0.441)*
SD 61 0.499*
LR 12 0.336*
CR 68 (0.634) *
As YS 81 (0.521)**
FD 214 (0.839)**
SD 108 0.754**
LR 292 0.758**
CR 191 (0.756)**
Tab.1  Pearson correlation coefficient feature band election
Fig.4  Variable selection process by CARS method
元素 光谱类型 特征波段数 占总波段数比例/%
Cd YS 60 15.8
FD 35 9.2
SD 30 7.9
LR 51 13.4
CR 46 12.1
As YS 35 9.2
FD 32 8.4
SD 41 10.8
LR 35 9.2
CR 32 8.4
Tab.2  CARS feature bands selection
R2 RPD 模型精度评价
R2≤0.5 RPD≤1.5 不具有预测能力
0.5<R2≤0.68 1.5<RPD≤2.0 可区分高值和低值
0.68<R2≤0.82 2.0<RPD≤2.5 能够近似预测
0.82<R2≤0.9 2.5<RPD≤3.0 预测能力良好
R2>0.9 RPD>3.0 预测能力极佳
Tab.3  Model accuracy evaluation
元素 光谱类型 PCC-PLSR CARS-PLSR
建模集 验证集 建模集 验证集
R2 RMSE R2 RMSE RPD R2 RMSE R2 RMSE RPD
Cd YS 0.365 1.796 -0.441 1.692 0.862 0.439 1.087 -0.256 2.845 0.924
FD 0.704 1.198 -0.155 1.647 0.963 0.954 0.477 0.863 0.572 2.799
SD 0.811 0.699 0.236 2.407 1.184 0.965 0.423 0.557 0.878 1.555
LR 0.352 1.334 -0.024 2.619 1.023 0.357 1.287 0.150 2.564 1.122
CR 0.631 0.853 0.046 2.835 1.060 0.573 1.447 -0.306 1.763 0.906
As YS 0.832 1.277 0.615 1.932 1.669 0.779 1.528 0.648 1.410 1.746
FD 0.928 0.869 0.794 1.293 2.283 0.981 0.431 0.959 0.639 5.119
SD 0.906 0.955 0.741 1.537 2.033 0.985 0.397 0.870 1.159 2.870
LR 0.843 1.345 0.672 1.256 1.808 0.844 1.267 0.711 1.417 1.926
CR 0.828 1.373 0.733 1.363 2.005 0.880 1.120 0.748 1.369 2.061
Tab.4  PLSR model estimation results
元素 光谱类型 PCC-PSO-RFR CARS-PSO-RFR
建模集 验证集 建模集 验证集
R2 RMSE R2 RMSE RPD R2 RMSE R2 RMSE RPD
Cd YS 0.812 0.977 -1.351 2.162 0.654 0.727 0.759 -0.219 2.804 0.994
FD 0.882 0.757 -0.042 1.564 0.985 0.831 0.912 0.066 1.494 1.039
SD 0.819 0.684 0.323 2.265 1.216 0.858 0.857 0.083 1.264 1.044
LR 0.821 0.701 -0.100 2.714 1.008 0.838 0.646 0.094 2.647 1.051
CR 0.915 0.408 0.230 2.548 1.178 0.836 0.897 -0.511 1.896 0.962
As YS 0.882 1.071 0.586 2.003 1.568 0.863 1.205 -0.205 2.610 1.202
FD 0.909 0.980 0.833 1.164 2.542 0.947 0.722 0.732 1.635 1.968
SD 0.944 0.738 0.554 2.017 1.568 0.936 0.815 0.383 2.523 1.277
LR 0.927 0.921 0.666 1.267 1.819 0.924 0.887 0.559 1.751 1.518
CR 0.948 0.756 0.165 2.412 1.095 0.908 0.983 0.678 1.547 1.762
Tab.5  PSO-RFR model estimation results
Fig.5  The optimal PLSR and PSO-RFR Validation set inversion 1∶1 diagram
[1] 张东辉, 赵英俊, 陆冬华, 等. 高光谱在土壤重金属信息提取中的应用与实现[J]. 土壤通报, 2018, 49(1):31-37.
[1] Zhang D H, Zhao Y J, Lu D H, et al. Application and realization of hyperspectral information extraction of heavy metals in soil[J]. Chinese Journal of Soil Science, 2018, 49(1):31-37.
[2] 余涛, 蒋天宇, 刘旭, 等. 土壤重金属污染现状及检测分析技术研究进展[J]. 中国地质, 2021, 48(2):460-476.
[2] Yu T, Jiang T Y, Liu X, et al. Research progress in current status of soil heavy metal pollution and analysis technology[J]. Geology in China, 2021, 48(2):460-476.
[3] 贺军亮, 张淑媛, 查勇, 等. 高光谱遥感反演土壤重金属含量研究进展[J]. 遥感技术与应用, 2015, 30(3):407-412.
doi: 10.11873/j.issn.1004\|0323.2015.3.0407
[3] He J L, Zhang S Y, Zha Y, et al. Review of retrieving soil heavy metal content by hyperspectral remote sensing[J]. Remote Sensing Technology and Application, 2015, 30(3):407-412.
[4] 张静静, 周卫红, 邹萌萌, 等. 高光谱遥感监测大面积土壤重金属污染的研究现状、原理及展望[J]. 江苏农业科学, 2018, 46(12):9-13.
[4] Zhang J J, Zhou W H, Zou M M, et al. Research status,principle and prospect of hyperspectral remote sensing monitoring of heavy metal pollution in large areas[J]. Jiangsu Agricultural Sciences, 2018, 46(12):9-13.
[5] 刘彦平, 罗晴, 程和发. 高光谱遥感技术在土壤重金属含量测定领域的应用与发展[J]. 农业环境科学学报, 2020, 39(12):2699-2709.
[5] Liu Y P, Luo Q, Cheng H F. Application and development of hyperspectral remote sensing technology to determine the heavy metal content in soil[J]. Journal of Agro-Environment Science, 2020, 39(12):2699-2709.
[6] 杨晓宇, 包妮沙, 曹粤, 等. 基于无人机成像光谱技术的农田土壤养分估测及制图[J]. 地理与地理信息科学, 2021, 37(5):38-45.
[6] Yang X Y, Bao N S, Cao Y, et al. Estimation and mapping of soil nutrient in farmland based on UAV imaging spectrometry[J]. Geography and Geo-Information Science, 2021, 37(5):38-45.
[7] 雷宇斌, 刘宁, 郭云开, 等. 高光谱组合变换下土壤含量模型反演研究[J]. 测绘工程, 2018, 27(11):71-76.
[7] Lei Y B, Liu N, Guo Y K, et al. Inversion of soil Cd content with GWR model under hyper-spectral combined transformation[J]. Engineering of Surveying and Mapping, 2018, 27(11):71-76.
[8] 褚小立, 袁洪福, 陆婉珍. 近红外分析中光谱预处理及波长选择方法进展与应用[J]. 化学进展, 2004, 16(4):528-542.
[8] Chu X L, Yuan H F, Lu W Z. Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique[J]. Progress in Chemistry, 2004, 16(4):528-542.
[9] 宋相中, 唐果, 张录达, 等. 近红外光谱分析中的变量选择算法研究进展[J]. 光谱学与光谱分析, 2017, 37(4):1048-1052.
[9] Song X Z, Tang G, Zhang L D, et al. Research advance of variable selection algorithms in near infrared spectroscopy analysis[J]. Spectroscopy and Spectral Analysis, 2017, 37(4):1048-1052.
[10] 袁自然, 魏立飞, 张杨熙, 等. 优化CARS结合PSO-SVM算法农田土壤重金属砷含量高光谱反演分析[J]. 光谱学与光谱分析, 2020, 40(2):567-573.
[10] Yuan Z R, Wei L F, Zhang Y X, et al. Hyperspectral inversion and analysis of heavy metal arsenic content in farmland soil based on optimizing CARS combined with PSO-SVM algorithm[J]. Spectroscopy and Spectral Analysis, 2020, 40(2):567-573.
[11] 陈元鹏, 张世文, 罗明, 等. 基于高光谱反演的复垦区土壤重金属含量经验模型优选[J]. 农业机械学报, 2019, 50(1):170-179.
[11] Chen Y P, Zhang S W, Luo M, et al. Empirical model optimization of hyperspectral inversion of heavy metal content in reclamation area[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(1):170-179.
[12] 金昭, 吕建树. 基于机器学习模型的区域土壤重金属空间预测精度比较研究[J]. 地理研究, 2022, 41(6):1731-1747.
doi: 10.11821/dlyj020210528
[12] Jin Z, Lyu J S. Comparison of the accuracy of spatial prediction for heavy metals in regional soils based on machine learning models[J]. Geographical Research, 2022, 41(6):1731-1747.
[13] 涂宇龙, 邹滨, 姜晓璐, 等. 矿区土壤Cu含量高光谱反演建模[J]. 光谱学与光谱分析, 2018, 38(2):575-581.
[13] Tu Y L, Zou B, Jiang X L, et al. Hyperspectral remote sensing based modeling of Cu content in mining soil[J]. Spectroscopy and Spectral Analysis, 2018, 38(2):575-581.
[14] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration[J]. Analytica Chimica Acta, 2009, 648(1):77-84.
doi: 10.1016/j.aca.2009.06.046 pmid: 19616692
[15] Tan K, Wang H M, Zhang Q Q, et al. An improved estimation model for soil heavy metal(loid) concentration retrieval in mining areas using reflectance spectroscopy[J]. Journal of Soils and Sediments, 2018, 18(5):2008-2022.
[16] 孙波, 张弛, 尹世超, 等. 基于PSO-RF的GNSS-IR土壤湿度反演方法研究[J]. 无线电工程, 2021, 51(10):1080-1085.
[16] Sun B, Zhang C, Yin S C, et al. Research on GNSS-IR soil moisture inversion method based on PSO-RF[J]. Radio Engineering, 2021, 51(10):1080-1085.
[17] 范升旭, 杨春曦, 杨启良, 等. 基于粒子群-随机森林算法和气象数据的三七叶面积生长预测模型[J]. 中草药, 2022, 53(10):3103-3110.
[17] Fan X X, Yang C X, Yang Q L, et al. Prediction model of Panax notoginseng leaf area growth based on particle swarm-optimization random forest algorithm and meteorological data[J]. Chinese Traditional and Herbal Drugs, 2022, 53(10):3103-3110.
[18] 魏丹萍, 郑光辉. 高光谱反射率的滨海地区土壤全磷含量反演[J]. 光谱学与光谱分析, 2022, 42(2):517-523.
[18] Wei D P, Zheng G H. Estimation of soil total phosphorus content in coastal areas based on hyperspectral reflectance[J]. Spectroscopy and Spectral Analysis, 2022, 42(2):517-523.
[19] Malley D F, Williams P C. Use of near-infrared reflectance spectroscopy in prediction of heavy metals in freshwater sediment by their association with organic matter[J]. Environmental Science & Technology, 1997, 31(12):3461-3467.
[20] 李冠稳, 高小红, 肖能文, 等. 基于sCARS-RF算法的高光谱估算土壤有机质含量[J]. 发光学报, 2019, 40(8):1030-1039.
[20] Li G W, Gao X H, Xiao N W, et al. Estimation soil organic matter contents with hyperspectra based on sCARS and RF algorithms[J]. Chinese Journal of Luminescence, 2019, 40(8):1030-1039.
[1] SONG Qi, GAO Xiaohong, SONG Yuting, LI Qiaoli, CHEN Zhen, LI Runxiang, ZHANG Hao, CAI Sangjie. Estimation of soil organic carbon content in farmland based on UAV hyperspectral images: A case study of farmland in the Huangshui River basin[J]. Remote Sensing for Natural Resources, 2024, 36(2): 160-172.
[2] KONG Zhuo, YANG Haitao, ZHENG Fengjie, LI Yang, QI Ji, ZHU Qinyu, YANG Zhonglin. Research advances in atmospheric correction of hyperspectral remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(4): 1-10.
[3] WANG Qian, REN Guangli. Application of hyperspectral remote sensing data-based anomaly extraction in copper-gold prospecting in the Solake area in the Altyn metallogenic belt, Xinjiang[J]. Remote Sensing for Natural Resources, 2022, 34(1): 277-285.
[4] GAO Wenlong, ZHANG Shengwei, LIN Xi, LUO Meng, REN Zhaoyi. The remote sensing-based estimation and spatial-temporal dynamic analysis of SOM in coal mining[J]. Remote Sensing for Natural Resources, 2021, 33(4): 235-242.
[5] JIANG Yanan, ZHANG Xin, ZHANG Chunlei, ZHONG Chengcheng, ZHAO Junfang. Classification of remote sensing images based on multi-scale feature fusion using local binary patterns[J]. Remote Sensing for Natural Resources, 2021, 33(3): 36-44.
[6] ZANG Chuankai, SHEN Fang, YANG Zhengdong. Aquatic environmental monitoring of inland waters based on UAV hyperspectral remote sensing[J]. Remote Sensing for Natural Resources, 2021, 33(3): 45-53.
[7] HU Xinyu, XU Zhanghua, CHEN Wenhui, CHEN Qiuxia, WANG Lin, LIU Hui, LIU Zhicai. Construction and application effect of normalized shadow vegetation index NSVI based on PROBA/CHRIS image[J]. Remote Sensing for Land & Resources, 2021, 33(2): 55-65.
[8] WANG Ruijun, ZHANG Chunlei, SUN Yongbin, WANG Shen, DONG Shuangfa, WANG Yongjun, YAN Bokun. Application of hyperspectral spectroscopy to constructing polymetallic prospecting model in Hongshan, Gansu Province[J]. Remote Sensing for Land & Resources, 2020, 32(3): 222-231.
[9] Junliang HE, Chaoshan HAN, Rui WEI, Zhiyong ZHOU, Qiliang DONG. Research on indirect hyperspectral estimating model of heavy metal Cd based on partial least squares regression[J]. Remote Sensing for Land & Resources, 2019, 31(4): 96-103.
[10] Xifeng CAO, Lin SUN, Zifei ZHAO, Xiaofeng HAN, Mingjie YAN. Application of MODIS remote sensing products in the estimation of grass yield in Sanjiang Source Area[J]. Remote Sensing for Land & Resources, 2018, 30(4): 115-124.
[11] Donghui ZHANG, Yingjun ZHAO, Kai QIN. Design and construction of the typical ground target spectral information system[J]. Remote Sensing for Land & Resources, 2018, 30(4): 206-211.
[12] Jing CUI, Xinfeng DONG, Rui DING, Shimin ZHANG, Conghe WANG, Hengxin LU, Yanyun SUN. Stratigraphic division of loess along loess profile based on hyperspectral remote sensing[J]. Remote Sensing for Land & Resources, 2018, 30(2): 202-207.
[13] REN Guangli, YANG Min, LI Jianqiang, GAO Ting, LIANG Nan, YI Huan, YANG Junlu. Application of hyperspectral alteration information to gold prospecting: A case study of Fangshankou area,Beishan[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(3): 182-190.
[14] SU Hongjun, LIU Hao. A novel dynamic classifier selection algorithm using spatial-spectral information for hyperspectral classification[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(2): 15-21.
[15] YU Junchuan, LIU Wenliang, YAN Bokun, DONG Xinfeng, WANG Zhe, LI Na. Inversion of geochemical compositions of basalts based on field measured spectra[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 158-163.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech