ForCM: Forest Cover Mapping from Multispectral Sentinel-2 Image by Integrating Deep Learning with Object-Based Image Analysis

2025-12-28

AI Summary

Insufficient accuracy in Amazon rainforest forest cover mapping hinders effective ecological monitoring. Method: This study proposes a coupled framework integrating deep learning with object-based image analysis (OBIA), systematically evaluating five semantic segmentation models—U-Net, UNet++, ResUNet, AttentionUNet, and ResNet50-SegNet—in conjunction with OBIA. Processing leverages Sentinel-2 Level 2A multispectral imagery within the open-source QGIS platform. Contribution/Results: AttentionUNet-OBIA achieves the highest overall accuracy (95.64%), followed by ResUNet-OBIA (94.54%), both significantly outperforming conventional OBIA (92.91%). This work constitutes the first systematic validation of multiple U-Net variants synergized with OBIA for tropical forest mapping. It demonstrates the feasibility of an open-source, reproducible, and cost-effective technical pipeline for high-accuracy ecological land-cover mapping, offering a scalable solution for global forest dynamics monitoring.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Ensemble Methods
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

This research proposes "ForCM", a novel approach to forest cover mapping that combines Object-Based Image Analysis (OBIA) with Deep Learning (DL) using multispectral Sentinel-2 imagery. The study explores several DL models, including UNet, UNet++, ResUNet, AttentionUNet, and ResNet50-Segnet, applied to high-resolution Sentinel-2 Level 2A satellite images of the Amazon Rainforest. The datasets comprise three collections: two sets of three-band imagery and one set of four-band imagery. After evaluation, the most effective DL models are individually integrated with the OBIA technique to enhance mapping accuracy. The originality of this work lies in evaluating different deep learning models combined with OBIA and comparing them with traditional OBIA methods. The results show that the proposed ForCM method improves forest cover mapping, achieving overall accuracies of 94.54 percent with ResUNet-OBIA and 95.64 percent with AttentionUNet-OBIA, compared to 92.91 percent using traditional OBIA. This research also demonstrates the potential of free and user-friendly tools such as QGIS for accurate mapping within their limitations, supporting global environmental monitoring and conservation efforts.

Problem

• Combines deep learning with object-based image analysis for forest mapping
• Evaluates multiple deep learning models on Sentinel-2 Amazon imagery
• Improves mapping accuracy over traditional methods using integrated approach

Innovation

• Integrates deep learning with object-based image analysis
• Evaluates multiple deep learning models for forest mapping
• Uses Sentinel-2 multispectral imagery for high accuracy