FCDNet: A Multiscale Attention Network for Forest Change Detection Using Dual-Temporal Very-High-Resolution Remote Sensing Images

Forest change detection (CD) plays a vital role in remote sensing research, serving as a cornerstone for ecological protection and sustainable environmental management. While existing research on CD primarily focuses on urban areas and croplands, forest CD remains underdeveloped. As the demand for real-time monitoring of forest changes grows in response to challenges like climate change and environmental degradation, advancements in remote sensing technologies make it possible to bridge this research gap. The complexity of forest CD stems from high seasonal and interannual variability, with fluctuations often showing strong similarities across years. In this article, we introduce FCDNet: A Multiscale Attention Network for Forest CD Using Dual-Temporal Very-High-Resolution Remote Sensing Images. The proposed network is designed to enhance the precision and robustness of CD through the integration of multiscale feature aggregation and an adaptive channel attention strategy. This design enables FCDNet to sensitively identify fine-grained forest alterations while maintaining strong adaptability to spatial and temporal variability in the input imagery. Comprehensive experiments confirm that FCDNet delivers superior performance compared with existing state-of-the-art approaches, showing notable advantages under challenging scenarios characterized by seasonal transitions and interannual fluctuations. FCDNet achieves impressive ${F}1$ -scores of 78.51%, 90.48%, and 92.57% on the Forest CD dataset (FCDD), LEVIR-CD, and WHU-CD datasets, respectively, delivering state-of-the-art results. This approach holds significant potential for advancing forest monitoring, providing a reliable tool for researchers and policymakers to better understand and protect forest ecosystems.

• Publication year

  2025

• Venue

  IEEE Transactions on Geoscience and Remote Sensing

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Environmental Science

• Identifiers
  DOI 10.1109/TGRS.2025.3631750
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images

  2024cited by this paper
• PRISMethaNet: A novel deep learning model for landfill methane detection using PRISMA satellite data

  2024cited by this paper
• FBA-DPAttResU-Net: Forest burned area detection using a novel end-to-end dual-path attention residual-based U-Net from post-fire Sentinel-1 and Sentinel-2 images

  2024cited by this paper
• Application of Explainable Artificial Intelligence in Predicting Wildfire Spread: An ASPP-Enabled CNN Approach

  2024cited by this paper
• C2F-SemiCD: A Coarse-to-Fine Semi-Supervised Change Detection Method Based on Consistency Regularization in High-Resolution Remote Sensing Images

  2024cited by this paper
• Spatiotemporal Enhancement and Interlevel Fusion Network for Remote Sensing Images Change Detection

  2024cited by this paper
• Very fine spatial resolution urban land cover mapping using an explicable sub-pixel mapping network based on learnable spatial correlation

  2023cited by this paper
• Exchanging Dual-Encoder–Decoder: A New Strategy for Change Detection With Semantic Guidance and Spatial Localization

  2023cited by this paper
• HCGMNet: A Hierarchical Change Guiding Map Network for Change Detection

  2023cited by this paper
• An Empirical Study of Remote Sensing Pretraining

  2022cited by this paper
• FCD-R2U-net: Forest change detection in bi-temporal satellite images using the recurrent residual-based U-net

  2022cited by this paper
• Channel exchange and adversarial learning guided cross-modal person re-identification

  2022cited by this paper
• An improved YOLOv5 method for large objects detection with multi-scale feature cross-layer fusion network

  2022cited by this paper
• A Transformer-Based Siamese Network for Change Detection

  2022cited by this paper
• SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images

  2021cited by this paper
• Deep Multiscale Siamese Network with Parallel Convolutional Structure and Self-Attention for Change Detection

  2021cited by this paper
• Quad-FPN: A Novel Quad Feature Pyramid Network for SAR Ship Detection

  2021cited by this paper
• Remote Sensing Image Change Detection With Transformers

  2021cited by this paper
• ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias

  2021cited by this paper
• On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances, and Million-AID

  2021cited by this paper
• VNet: An End-to-End Fully Convolutional Neural Network for Road Extraction From High-Resolution Remote Sensing Data

  2020cited by this paper
• A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection

  2020cited by this paper
• WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF

  2020cited by this paper
• Semantic Change Detection with Asymmetric Siamese Networks

  2020cited by this paper
• DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

  2019cited by this paper
• What causes deforestation in Indonesia?

  2019cited by this paper
• Going Deeper in Spiking Neural Networks: VGG and Residual Architectures

  2018cited by this paper
• Fully Convolutional Siamese Networks for Change Detection

  2018cited by this paper
• SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning

  2016cited by this paper
• Forest biomass, carbon neutrality and climate change mitigation. From Science to Policy 3

  2016cited by this paper
• A review of the relationships between drought and forest fire in the United States

  2016cited by this paper
• Recent advances in convolutional neural networks

  2015cited by this paper
• CTFS‐ForestGEO: a worldwide network monitoring forests in an era of global change

  2015cited by this paper
• Modeling the effect of scale on clustering of spatial points

  2015cited by this paper
• U-Net: Convolutional Networks for Biomedical Image Segmentation

  2015cited by this paper
• Global soil carbon: understanding and managing the largest terrestrial carbon pool

  2014cited by this paper
• Multispectral demosaicking algorithm based on inter-channel correlation

  2014cited by this paper
• Fast Feature Pyramids for Object Detection

  2014cited by this paper
• Fully convolutional networks for semantic segmentation

  2014cited by this paper
• p-Channel Enhancement and Depletion Mode GaN-Based HFETs With Quaternary Backbarriers

  2013cited by this paper
• Advances in remote sensing technology and implications for measuring and monitoring forest carbon stocks and change

  2011cited by this paper
• Object-oriented change detection method based on multi-scale and multi-feature fusion

  2009cited by this paper
• Forest change detection by statistical object-based method

  2006cited by this paper
• Digital change detection in forest ecosystems with remote sensing imagery

  1996cited by this paper
• Forest Ecology

  1968cited by this paper

• No citing papers are available for this paper.