Predicting Particle Size and Soil Organic Carbon of Soil Profiles Using VIS-NIR-SWIR Hyperspectral Imaging and Machine Learning Models
Remote Sensing · 06.08.2024 · 16 (16) · 2869
DOI: 10.3390/rs16162869 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 06.08.2024. Verfasst von Karym Mayara de Oliveira und 11 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior.
Abstract (Originalsprache)
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.
Förderung
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
Zitieren
APA
Oliveira, K. M. D., Gonçalves, J. V. F., Furlanetto, R. H., Oliveira, C. A. D., Mendonça, W. A., Haubert, D. D. F. D. S., Crusiol, L. G. T., Falcioni, R., Oliveira, R. B. D., Reis, A. S., Ecker, A. E. D. A., & Nanni, M. R. (2024). Predicting Particle Size and Soil Organic Carbon of Soil Profiles Using VIS-NIR-SWIR Hyperspectral Imaging and Machine Learning Models. Remote Sensing, 16(16), 2869. https://doi.org/10.3390/rs16162869
Vancouver
Oliveira KMD, Gonçalves JVF, Furlanetto RH, Oliveira CAD, Mendonça WA, Haubert DDFDS, et al. Predicting Particle Size and Soil Organic Carbon of Soil Profiles Using VIS-NIR-SWIR Hyperspectral Imaging and Machine Learning Models. Remote Sensing. 2024;16(16):2869. doi:10.3390/rs16162869
BibTeX
@article{Oliveira2024,
author = {Oliveira, Karym Mayara de and Gonçalves, João Vitor Ferreira and Furlanetto, Renato Herrig and Oliveira, Caio Almeida de and Mendonça, Weslei Augusto and Haubert, Daiane de Fatima da Silva and Crusiol, Luís Guilherme Teixeira and Falcioni, Renan and Oliveira, Roney Berti de and Reis, Amanda Silveira and Ecker, Arney Eduardo do Amaral and Nanni, Marcos Rafael},
title = {Predicting Particle Size and Soil Organic Carbon of Soil Profiles Using VIS-NIR-SWIR Hyperspectral Imaging and Machine Learning Models},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {16},
pages = {2869},
doi = {10.3390/rs16162869}
}
EUVIMED