Predicting Particle Size and Soil Organic Carbon of Soil Profiles Using VIS-NIR-SWIR Hyperspectral Imaging and Machine Learning Models

被引:4
|
作者
de Oliveira, Karym Mayara [1 ]
Goncalves, Joao Vitor Ferreira [1 ]
Furlanetto, Renato Herrig [2 ]
de Oliveira, Caio Almeida [1 ]
Mendonca, Weslei Augusto [1 ]
Haubert, Daiane de Fatima da Silva [1 ]
Crusiol, Luis Guilherme Teixeira [3 ]
Falcioni, Renan [1 ]
de Oliveira, Roney Berti [1 ]
Reis, Amanda Silveira [1 ]
Ecker, Arney Eduardo do Amaral [4 ]
Nanni, Marcos Rafael [1 ]
机构
[1] Univ Estadual Maringa, Dept Agron, Ave Colombo 5790, BR-87020900 Maringa, PR, Brazil
[2] Univ Florida, Gulf Coast Res & Educ Ctr, Wimauma, FL 33598 USA
[3] Embrapa Soja Empresa Brasileira Pesquisa Agr, BR-86044764 Londrina, Parana, Brazil
[4] Ctr Univ Inga UNINGA, Dept Agron, Rod PR 317,6114, BR-87035510 Maringa, Parana, Brazil
关键词
data modeling; predictive model; remote sensing; spectroscopy of soils; spectral signature; REFLECTANCE SPECTROSCOPY; NITROGEN; TEXTURE;
D O I
10.3390/rs16162869
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Modeling spectral reflectance data using machine learning algorithms presents a promising approach for estimating soil attributes. Nevertheless, a comprehensive investigation of the most effective models, parameters, wavelengths, and data acquisition techniques is essential to ensure optimal predictive accuracy. This work aimed to (a) explore the potential of the soil spectral signature obtained in different spectral bands (VIS-NIR, SWIR, and VIS-NIR-SWIR) and, by using hyperspectral imaging and non-imaging sensors, in the predictive modeling of soil attributes; and (b) analyze the accuracy of different ML models in predicting particle size and soil organic carbon (SOC) applied to the spectral signature of different spectral bands. Six soil monoliths, located in the central north region of Parana, Brazil, were collected and scanned via hyperspectral cameras (VIS-NIR camera and SWIR camera) and spectroradiometer (VIS-NIR-SWIR) in the laboratory. The spectral signature of the soils was analyzed and subsequently applied to ML models to predict particle size and SOC. Each set of data obtained by the different sensors was evaluated separately. The algorithms used were k-nearest neighbors (KNN), support vector machine (SVM), random forest (RF), linear regression (LR), artificial neural network (NN), and partial least square regression (PLSR). The most promising predictive performance was observed for the complete VIS-NIR-SWIR spectrum, followed by SWIR and VIS-NIR. Meanwhile, KNN, RF, and NN models were the most promising algorithms in estimating soil attributes for the dataset obtained from both sensors. The general mean R2 (determination coefficient) values obtained using these models, considering the different spectral bands evaluated, were around 0.99, 0.98, and 0.97 for sand prediction, and around 0.99, 0.98, and 0.96 for clay prediction. The lower performances, obtained for the datasets from both sensors, were observed for silt and SOC, with R2 results between 0.40 and 0.59 for these models. KNN demonstrated the best predictive performance. Integrating effective ML models with robust sample databases, obtained by advanced hyperspectral imaging and spectroradiometers, can enhance the accuracy and efficiency of soil attribute prediction.
引用
收藏
页数:21
相关论文
共 50 条
  • [41] Analysis of organic and mineral nitrogen, total organic carbon and humic fractions in Ferralsols: an approach using Vis-NIR-SWIR, MIR and X-ray fluorescence spectroscopy
    Bruna Coelho de Lima
    Carlos H. dos Santos
    Carlos S. Tiritan
    José A. M. Demattê
    Andres M. R. Gomez
    Heidy S. R. Albarracín
    Bruno A. Bartsch
    Discover Environment, 2 (1):
  • [42] Prediction of soil organic carbon in soil profiles based on visible-near-infrared hyperspectral imaging spectroscopy
    Liu, Shuyu
    Chen, Jiaying
    Guo, Long
    Wang, Junguang
    Zhou, Zefan
    Luo, Jingyi
    Yang, Ruiqing
    SOIL & TILLAGE RESEARCH, 2023, 232
  • [43] Transferability of Vis-NIR models for Soil Organic Carbon Estimation between Two Study Areas by using Spiking
    Hong, Yongsheng
    Chen, Yiyun
    Zhang, Yong
    Liu, Yanfang
    Liu, Yaolin
    Yu, Lei
    Liu, Yi
    Cheng, Hang
    SOIL SCIENCE SOCIETY OF AMERICA JOURNAL, 2018, 82 (05) : 1231 - 1242
  • [44] Using soil library hyperspectral reflectance and machine learning to predict soil organic carbon: Assessing potential of airborne and spaceborne optical soil sensing
    Wang, Sheng
    Guan, Kaiyu
    Zhang, Chenhui
    Lee, DoKyoung
    Margenot, Andrew J.
    Ge, Yufeng
    Peng, Jian
    Zhou, Wang
    Zhou, Qu
    Huang, Yizhi
    REMOTE SENSING OF ENVIRONMENT, 2022, 271
  • [45] Selection of "Local" Models for Prediction of Soil Organic Matter Using a Regional Soil Vis-NIR Spectral Library
    Zeng, Rong
    Zhao, Yu-Guo
    Li, De-Cheng
    Wu, Deng-Wei
    Wei, Chang-Long
    Zhang, Gan-Lin
    SOIL SCIENCE, 2016, 181 (01) : 13 - 19
  • [46] Understanding the changes in millable oil content and fatty acid composition of infrared radiation treated mustard (Brassica juncea) seeds using Vis-NIR-SWIR hyperspectral imaging
    Hamad, Rajendra
    Chakraborty, Subir Kumar
    Kate, Adinath
    Mansuri, Shekh Mukhtar
    INFRARED PHYSICS & TECHNOLOGY, 2024, 137
  • [47] Evaluation of spectral data based soil organic carbon content estimation models in VIS-NIR
    Nagy, Attila
    Szabo, Andrea
    Escobar, Diana Quintin
    Tamas, Janos
    SOIL SCIENCE ANNUAL, 2024, 75 (01)
  • [48] Prediction of soil organic carbon and total nitrogen affected by mine using Vis-NIR spectroscopy coupled with machine learning algorithms in calcareous soils
    Zhang, Tianqi
    Li, Ye
    Wang, Mingyou
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [49] Strategies for monitoring within-field soybean yield using Sentinel-2 Vis-NIR-SWIR spectral bands and machine learning regression methods
    L. G.T. Crusiol
    Liang Sun
    R. N.R. Sibaldelli
    V. Felipe Junior
    W. X. Furlaneti
    R. Chen
    Z. Sun
    D. Wuyun
    Z. Chen
    M. R. Nanni
    R. H. Furlanetto
    E. Cezar
    A. L. Nepomuceno
    J. R.B. Farias
    Precision Agriculture, 2022, 23 : 1093 - 1123
  • [50] Strategies for monitoring within-field soybean yield using Sentinel-2 Vis-NIR-SWIR spectral bands and machine learning regression methods
    Crusiol, L. G. T.
    Sun, Liang
    Sibaldelli, R. N. R.
    Felipe Junior, V
    Furlaneti, W. X.
    Chen, R.
    Sun, Z.
    Wuyun, D.
    Chen, Z.
    Nanni, M. R.
    Furlanetto, R. H.
    Cezar, E.
    Nepomuceno, A. L.
    Farias, J. R. B.
    PRECISION AGRICULTURE, 2022, 23 (03) : 1093 - 1123