A novel ensemble model for multi-temporal forest vegetation classification: integrating spectral-temporal features and topographic constraints
Understanding species distribution in large forest ecosystems is fundamental for biodiversity conservation, biomass estimation, climate regulation, soil and water conservation. While remote sensing combined with modeling algorithms enables efficient forest monitoring, existing approaches frequently...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-07-01
|
| Series: | Big Earth Data |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/20964471.2025.2525654 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Understanding species distribution in large forest ecosystems is fundamental for biodiversity conservation, biomass estimation, climate regulation, soil and water conservation. While remote sensing combined with modeling algorithms enables efficient forest monitoring, existing approaches frequently treat multi-temporal imagery as one-dimensional sequences, capturing only temporal trends within spectral bands and neglecting the joint spectral-temporal dynamics essential for fine-scale forest classification. Moreover, single-model frameworks frequently suffer from limited generalization and low reliability when applied to complex, large-scale regions. To address these challenges, this study proposes an ensemble classification framework integrating two-dimensional feature reconstruction and multi-classifier fusion. Spectral and temporal dimensions were jointly encoded to enhance feature representation, and an ensemble learning strategy was introduced to improve model robustness and adaptability. The framework comprises a feature extraction module and an ensemble classification module. Using Sentinel-1 and Sentinel-2 imagery from 2021–2022 and field survey data, two datasets were constructed to evaluate model performance. The proposed method achieved overall accuracies of 97.84% and 91.41% on the two datasets, respectively. Outputting and integrating the results of multiple classifiers provides insights into the model’s classification mechanism, results proved the effectiveness of the feature extraction module and the differences among the integration strategies. The Simpson index was employed for visual evaluation, overcoming sample labelling limitations, and the influence of elevation and slope on vegetation was analysed, highlighting the necessity for topographic features in mountainous areas. |
|---|---|
| ISSN: | 2096-4471 2574-5417 |