UAV multispectral to hyperspectral reconstruction based on deep learning and radiative transfer models for crop nitrogen monitoring
• Proposed a multispectral to hyperspectral reconstruction framework M2H–SWIR. • The M2H–SWIR framework integrates the PROSAIL and deep learning. • M2H–SWIR reconstructs VNIR multispectral to full-range hyperspectral (400–2500 nm) • Reconstructed SWIR bands enhance UAV-based canopy nitrogen mapping accuracy. • M2H–SWIR outperforms traditional PROSAIL inversion for canopy nitrogen estimation.
Authors
- Ittai Herrmann (ORCID: https://orcid.org/0000-0003-1136-1883)
- Kang Yu (ORCID: https://orcid.org/0000-0002-0686-6783)
- Fei li (ORCID: https://orcid.org/0000-0003-4899-262X)
- Anirudh Belwalkar (ORCID: https://orcid.org/0000-0001-6676-5709)
- Sebastian T. Meyer
- Jie Wang (ORCID: https://orcid.org/0000-0001-6062-0728)
Institutions
- Inner Mongolia Agricultural University (CN)
- Hebrew University of Jerusalem (IL)
- Technical University of Munich (DE)
Publication Details
- Journal
- International Journal of Applied Earth Observation and Geoinformation
- Published
- 2026-05-27
- DOI
- https://doi.org/10.1016/j.jag.2026.105364
- Primary Topic
- Remote Sensing in Agriculture
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Deutsche Forschungsgemeinschaft