Work

Deep-learning-based grassland mapping with Sentinel-2: prioritizing key spectral bands and time periods

Year: 2025

Type: conference-paper

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.

Source: International Conference on Remote Sensing and Geoinformation of the Environment (RSCy)

DOI: 10.1117/12.3073215

Authors: Konstantinos Christofi, Charalambos Chrysostomou, Iason Tsardanidis, Michalis Mavrovouniotis, Charalampos Kontoes, Diofantos Hadjimitsis

Institutions: Cyprus University of Technology, ERATOSTHENES Centre of Excellence, National Observatory of Athens

Language: English

Topic: Remote-Sensing Image Classification

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

SDGs: Life on land, Climate action

Open Access status: green

Funders: Cyprus University of Technology, University of Cyprus, European Commission, Horizon 2020 Framework Programme