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
  • [31] Estimation of soil hydraulic properties using proximal spectral reflectance in visible, near-infrared, and shortwave-infrared (VIS-NIR-SWIR) region
    Santra, Priyabrata
    Sahoo, Rabi Narayan
    Das, Bhabani Sankar
    Samal, Ravindra Nath
    Pattanaik, Ajit Kumar
    Gupta, Vinod Kumar
    GEODERMA, 2009, 152 (3-4) : 338 - 349
  • [32] In Situ Measurements of Organic Carbon in Soil Profiles Using vis-NIR Spectroscopy on the Qinghai-Tibet Plateau
    Li, Shuo
    Shi, Zhou
    Chen, Songchao
    Ji, Wenjun
    Zhou, Lianqing
    Yu, Wu
    Webster, Richard
    ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2015, 49 (08) : 4980 - 4987
  • [33] Soil Organic Carbon Prediction Using Vis-NIR Spectroscopy with a Large Dataset
    Shi, Yang
    Wang, Rujing
    Wang, Yubing
    COMPUTER AND COMPUTING TECHNOLOGIES IN AGRICULTURE XI, PT I, 2019, 545 : 76 - 86
  • [34] Estimating Soil Organic Carbon Using VIS/NIR Spectroscopy with SVMR and SPA Methods
    Peng, Xiaoting
    Shi, Tiezhu
    Song, Aihong
    Chen, Yiyun
    Gao, Wenxiu
    REMOTE SENSING, 2014, 6 (04) : 2699 - 2717
  • [35] Using Vis-NIR Spectroscopy for Monitoring Temporal Changes in Soil Organic Carbon
    Deng, Fan
    Minasny, Budiman
    Knadel, Maria
    McBratney, Alex
    Heckrath, Goswin
    Greve, Mogens H.
    SOIL SCIENCE, 2013, 178 (08) : 389 - 399
  • [36] Applicability of machine learning models for predicting soil organic carbon content and bulk density under different soil conditions
    Hateffard, Fatemeh
    Szatmari, Gabor
    Novak, Tibor Jozsef
    SOIL SCIENCE ANNUAL, 2023, 74 (01)
  • [37] Mapping Particle Size and Soil Organic Matter in Tropical Soil Based on Hyperspectral Imaging and Non-Imaging Sensors
    Nanni, Marcos Rafael
    Dematte, Jose Alexandre Melo
    Rodrigues, Marlon
    dos Santos, Glaucio Leboso Alemparte Abrantes
    Reis, Amanda Silveira
    de Oliveira, Karym Mayara
    Cezar, Everson
    Furlanetto, Renato Herrig
    Crusiol, Luis Guilherme Teixeira
    Sun, Liang
    REMOTE SENSING, 2021, 13 (09)
  • [38] Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran
    Emadi, Mostafa
    Taghizadeh-Mehrjardi, Ruhollah
    Cherati, Ali
    Danesh, Majid
    Mosavi, Amir
    Scholten, Thomas
    REMOTE SENSING, 2020, 12 (14)
  • [39] Use of Machine Learning Models for Prediction of Organic Carbon and Nitrogen in Soil from Hyperspectral Imagery in Laboratory
    Monsalve, Manuela Ortega
    Ceron-Munoz, Mario
    Galeano-Vasco, Luis
    Medina-Sierra, Marisol
    JOURNAL OF SPECTROSCOPY, 2023, 2023
  • [40] Soil organic carbon and particle sizes mapping using vis-NIR, EC and temperature mobile sensor platform
    Knadel, Maria
    Thomsen, Anton
    Schelde, Kirsten
    Greve, Mogens Humlekrog
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2015, 114 : 134 - 144