Precision Meets Speed: An Attention Encoder–Decoder Network for Deforestation Segmentation

Giovana A. Benvenuto

doi:10.1109/LGRS.2025.3590585

Precision Meets Speed: An Attention Encoder–Decoder Network for Deforestation Segmentation

2025-01-01

0

PRE

AI

G

Giovana A. Benvenuto

R

Rogério Galante Negri

DOI：10.1109/LGRS.2025.3590585

Original

Original request for help

Save

Abstract

En 中文

Deforestation remains a critical global environmental concern, requiring effective monitoring approaches. This letter presents a novel attention-powered encoder–decoder neural network designed to address the key challenges in deforestation mapping, including scale heterogeneity, temporal dynamics, and computational efficiency. The proposed framework integrates a modified YOLOv8 backbone, spatial attention (SA) mechanisms, and a conjugated Dice–Focal loss function to enhance sensitivity to small- and large-scale deforestation patterns in temporal remote sensing (RS) data. An extensive battery of tests was conducted using two datasets from the Amazon region, exploring both single-image and image-pair inputs under varying contextual and class balance conditions. The results attest to substantial improvements in accuracy and computational efficiency compared to 13 deep learning (DL) methods, establishing the proposed model as effective in deforestation monitoring scenarios, where accuracy, scalability, and computational cost are simultaneously critical.

Keywords:

Deep learning

deforestation

remote sensing (RS)

Precision Meets Speed: An Attention Encoder–Decoder Network for Deforestation Segmentation

Abstract

Journal

Organization