Assessing the value of advanced Sentinel-1 SLC features for multimodal time-series crop mapping
• Extension of PASTIS-R dataset with Sentinel-1 SLC data for multimodal agricultural mapping. • Reflection symmetry of agricultural targets makes dual-pol decomposition features redundant with backscatter coefficients. • Interferometric coherence boosts robustness under severe optical cloud cover. • In multimodal fusion, biased coherence matches elaborately processed alternatives, simplifying operational deployment. • Coherence gains transfer across held-out regions, with larger marginal contributions under regional distribution shifts.
Authors
- Aosheng Wang (ORCID: https://orcid.org/0009-0007-1572-4190)
- Dongzi Li (ORCID: https://orcid.org/0000-0001-7931-0607)
- Dazhao Fan (ORCID: https://orcid.org/0000-0001-7100-8454)
- Jie Yang (ORCID: https://orcid.org/0000-0003-4801-7162)
- Ding Gao
- Yang Dong (ORCID: https://orcid.org/0000-0001-9323-9675)
- Song Ji
- Ying Xiong
- Ming Li
Institutions
- PLA Information Engineering University (CN)
- Duke University (US)
Publication Details
- Journal
- International Journal of Applied Earth Observation and Geoinformation
- Published
- 2026-05-22
- DOI
- https://doi.org/10.1016/j.jag.2026.105357
- Primary Topic
- Remote Sensing in Agriculture
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China