CerraData-4 MM: A Multimodal Benchmark Dataset on Cerrado for Land Use and Land Cover Classification

CerraData-4 MM: A Multimodal Benchmark Dataset on Cerrado for Land Use and Land Cover Classification

The <italic>Cerrado</italic> faces increasing environmental pressures, necessitating accurate land use and land cover mapping despite challenges, such as class imbalance and visually similar categories. To address this, we present CerraData-4 MM, a multimodal dataset combining Sentinel-1...

Full description

Saved in:
Bibliographic Details
Main Authors: Mateus de Souza Miranda, Ronny Hansch, Valdivino Alexandre de Santiago Junior, Thales Sehn Korting, Erison Carlos dos Santos Monteiro
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Cerrado
deep learning (DL)
hierarchical level of classes
land use and land cover (LULC) classification
semantic segmentation
Online Access:https://ieeexplore.ieee.org/document/11068119/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The <italic>Cerrado</italic> faces increasing environmental pressures, necessitating accurate land use and land cover mapping despite challenges, such as class imbalance and visually similar categories. To address this, we present CerraData-4 MM, a multimodal dataset combining Sentinel-1 synthetic aperture radar and Sentinel-2 multispectral imagery with 10 m spatial resolution. The dataset includes two hierarchical classification levels with seven and 14 classes, respectively, focusing on the diverse <italic>Bico do Papagaio</italic> ecoregion. We benchmark two models trained on CerraData-4 MM, employing a visual transformer-based architecture and a convolutional-based architecture. The ViT achieves superior performance in multimodal scenarios, with the highest macro F1-score of 57.60&#x0025; and a mean Intersection over Union of 49.05&#x0025; at the first hierarchical level. Both models struggle with minority classes, particularly at the second hierarchical level, where U-Net&#x2019;s performance drops to an F1-score of 18.16&#x0025;. Weighted loss improves representation for underrepresented classes but reduces overall accuracy, underscoring the trade-off in weighted training. CerraData-4 MM offers a challenging benchmark for advancing deep learning models to handle class imbalance and multimodal data fusion.
ISSN:1939-1404
2151-1535

Similar Items