Wijata et al. (2026) Getting the Most Out of the Image-Level Labels: (Un)Supervised Learning for Extracting Soil Parameters From Hyperspectral Images

Identification

• Journal: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
• Year: 2026
• Date: 2026-01-01
• Authors: A. Wijata, Łukasz Tulczyjew, Peter Naylor, Bertrand Le Saux, Nicolas Longépé, Jakub Nalepa
• DOI: 10.1109/jstars.2026.3660363

Research Groups

Information not available in the provided text.

Short Summary

This paper explores the application of (un)supervised learning methods to extract soil parameters from hyperspectral images, emphasizing the efficient utilization of image-level labels.

Objective

• To extract soil parameters from hyperspectral images.
• To effectively utilize image-level labels through (un)supervised learning for this extraction.

Study Configuration

• Spatial Scale: Implied to be at the pixel or scene level of hyperspectral imagery; specific resolution or extent not provided.
• Temporal Scale: Not specified in the provided text.

Methodology and Data

• Models used: (Un)supervised learning algorithms.
• Data sources: Hyperspectral images, image-level labels.

Main Results

Information not available in the provided text.

Contributions

Information not available in the provided text.

Funding

Information not available in the provided text.

Citation

@article{Wijata2026Getting,
  author = {Wijata, A. and Tulczyjew, Łukasz and Naylor, Peter and Saux, Bertrand Le and Longépé, Nicolas and Nalepa, Jakub},
  title = {Getting the Most Out of the Image-Level Labels: (Un)Supervised Learning for Extracting Soil Parameters From Hyperspectral Images},
  journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
  year = {2026},
  doi = {10.1109/jstars.2026.3660363},
  url = {https://doi.org/10.1109/jstars.2026.3660363}
}