Deep-learning-based grassland mapping with Sentinel-2: prioritizing key spectral bands and time periods
Journal
SPIE
Date Issued
September 19, 2025
DOI
10.1117/12.3073215
Abstract
Accurate grassland mapping is essential for biodiversity conservation and sustainable land management, yet
remains challenging due to the spectral and temporal variability of grassland ecosystems. This study presents
a Deep Learning approach for grassland classification using multi-temporal Sentinel-2 imagery, incorporating
a dynamic feature selection mechanism to prioritize informative spectral bands and time periods. In order to
allow the model to adaptively focus on discriminative temporal spectral patterns, we compare a baseline neural
network with a modified design that learns to weight input features dynamically. Our findings demonstrate
that the feature selection model achieves superior performance (Accuracy: 0.954 ± 0.004, MCC: 0.726 ± 0.027)
compared to both the baseline network and single-date models, highlighting the importance of temporal diversity in grassland classification.
remains challenging due to the spectral and temporal variability of grassland ecosystems. This study presents
a Deep Learning approach for grassland classification using multi-temporal Sentinel-2 imagery, incorporating
a dynamic feature selection mechanism to prioritize informative spectral bands and time periods. In order to
allow the model to adaptively focus on discriminative temporal spectral patterns, we compare a baseline neural
network with a modified design that learns to weight input features dynamically. Our findings demonstrate
that the feature selection model achieves superior performance (Accuracy: 0.954 ± 0.004, MCC: 0.726 ± 0.027)
compared to both the baseline network and single-date models, highlighting the importance of temporal diversity in grassland classification.
File(s)![Thumbnail Image]()
Name
1381610.pdf
Size
390.5 KB
Format
Adobe PDF
Checksum (MD5)
99a4b80431c932028b13a24ec839cf29