EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Soil Suborder Discrimination Using Machine Learning Is Improved by SWIR Imaging Compared with Full VIS–NIR–SWIR Spectra

Daiane de Fatima da Silva Haubert, Nicole Ghinzelli Vedana, Weslei Augusto Mendonça, Karym Mayara de Oliveira, Caio Almeida de Oliveira, João Vitor Ferreira Gonçalves, José Alexandre M. Demattê, Roney Berti de Oliveira, Amanda Silveira Reis, Renan Falcioni, Marcos Rafael Nanni

Remote Sensing · 15.03.2026 · 18 (6) · 898

DOI: 10.3390/rs18060898 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 15.03.2026. Verfasst von Daiane de Fatima da Silva Haubert und 10 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, National Council for Scientific and Technological Development, Bolsa de Mestrado e Doutorado.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rapid, standardised discrimination of soil taxonomic units remains challenging when relying solely on conventional field descriptions and laboratory analyses, particularly at high sampling densities. This study evaluated whether proximal spectroscopy and hyperspectral imaging can support the classification of Brazilian Soil Classification System (SiBCS) suborders and pedogenetic horizons when surface and subsurface spectra are treated separately. Six intact soil monoliths (0.12 × 1.60 m) were collected in Paraná State, southern Brazil, representing one Organossolo (Ooy), three Latossolos (LVd, LVd1, and LVd2) and two Argissolos (PVAd and PVd). For each monolith, 800 spectra were acquired per sensor with a non-imaging VIS–NIR–SWIR spectroradiometer (350–2500 nm), and 800 spectra per sensor per monolith were extracted from the SWIR hyperspectral images (1200–2450 nm). Principal component analysis (PCA) was used to summarise spectral variability, and supervised classification was performed via k-nearest neighbours, random forest, decision tree and gradient boosting for suborders (10-fold cross-validation), and a neural network was used for within-profile horizon classification. PCA indicated that most of the spectral variance was captured by a dominant axis, with clearer separation among suborders in the SWIR space than in the full VIS–NIR–SWIR range. With respect to suborder classification, subsurface spectra outperformed surface spectra, and SWIR outperformed VIS–NIR–SWIR: the best accuracies were 0.96 for subsurface SWIR (gradient boosting; AUC = 0.99; MCC = 0.95) and 0.89 for surface SWIR (k-nearest neighbours; AUC = 0.98; MCC = 0.87). Within-profile horizon classification via VIS–NIR–SWIR achieved accuracies of 0.84–0.97 with the Neural Network, with most misclassifications occurring between adjacent horizons. Overall, subsurface SWIR information provided the most reliable basis for taxonomic discrimination, whereas horizon classification was feasible but reflected gradual spectral transitions along the profile.

Förderung

  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
  • National Council for Scientific and Technological Development
  • Bolsa de Mestrado e Doutorado
  • Fundação Araucária
  • Financiadora de Estudos e Projetos

Zitieren

APA

Haubert, D. D. F. D. S., Vedana, N. G., Mendonça, W. A., Oliveira, K. M. D., Oliveira, C. A. D., Gonçalves, J. V. F., Demattê, J. A. M., Oliveira, R. B. D., Reis, A. S., Falcioni, R., & Nanni, M. R. (2026). Soil Suborder Discrimination Using Machine Learning Is Improved by SWIR Imaging Compared with Full VIS–NIR–SWIR Spectra. Remote Sensing, 18(6), 898. https://doi.org/10.3390/rs18060898

Vancouver

Haubert DDFDS, Vedana NG, Mendonça WA, Oliveira KMD, Oliveira CAD, Gonçalves JVF, et al. Soil Suborder Discrimination Using Machine Learning Is Improved by SWIR Imaging Compared with Full VIS–NIR–SWIR Spectra. Remote Sensing. 2026;18(6):898. doi:10.3390/rs18060898

BibTeX
@article{Haubert2026,
  author = {Haubert, Daiane de Fatima da Silva and Vedana, Nicole Ghinzelli and Mendonça, Weslei Augusto and Oliveira, Karym Mayara de and Oliveira, Caio Almeida de and Gonçalves, João Vitor Ferreira and Demattê, José Alexandre M. and Oliveira, Roney Berti de and Reis, Amanda Silveira and Falcioni, Renan and Nanni, Marcos Rafael},
  title = {Soil Suborder Discrimination Using Machine Learning Is Improved by SWIR Imaging Compared with Full VIS–NIR–SWIR Spectra},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {6},
  pages = {898},
  doi = {10.3390/rs18060898}
}
Kostenlos starten →