Predicting Particle Size and Soil Organic Carbon of Soil Profiles Using VIS-NIR-SWIR Hyperspectral Imaging and Machine Learning Models
-
Published:2024-08-06
Issue:16
Volume:16
Page:2869
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Oliveira Karym Mayara de1, Gonçalves João Vitor Ferreira1ORCID, Furlanetto Renato Herrig2, Oliveira Caio Almeida de1, Mendonça Weslei Augusto1, Haubert Daiane de Fatima da Silva1, Crusiol Luís Guilherme Teixeira3, Falcioni Renan1ORCID, Oliveira Roney Berti de1ORCID, Reis Amanda Silveira1, Ecker Arney Eduardo do Amaral4, Nanni Marcos Rafael1ORCID
Affiliation:
1. Department of Agronomy, State University of Maringa, Av. Colombo, 5790, Maringa 87020-900, Parana, Brazil 2. Gulf Coast Research and Education Center, University of Florida, Wimauma, FL 33598, USA 3. Embrapa Soja (Empresa Brasileira de Pesquisa Agropecuária), Londrina 86044-764, Parana, Brazil 4. Department of Agronomy, Centro Universitário Ingá (UNINGÁ), Rod. PR 317, 6114, Maringa 87035-510, Parana, Brazil
Abstract
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.
Funder
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
Reference52 articles.
1. Prediction of Soil Texture Classes through Different Wavelength Regions of Reflectance Spectroscopy at Various Soil Depths;Coblinski;Catena,2020 2. High-Resolution and Three-Dimensional Mapping of Soil Texture of China;Liu;Geoderma,2020 3. Using Imaging Spectroscopy to Study Soil Properties;Chabrillat;Remote Sens. Environ.,2009 4. Distribution Mapping of Soil Profile Carbon and Nitrogen with Laboratory Imaging Spectroscopy;Sorenson;Geoderma,2020 5. Teixeira, P.C., Donagemma, G.K., Fontana, A., and Teixeira, W.G. (2017). Manual de Métodos de Análise de Solo, Embrapa. [3rd ed.].
|
|