Scholarlink

<p>Continuous monitoring of the Amazon biome demands land cover classification models that are both highly sensitive and computationally feasible. To resolve the inherent trade-off between architectural complexity and predictive performance in spatial deep learning, this study introduces the Vision Transformer–Graph Neural Network with Feature Adaptation (ViT-GNN RFFA). In contrast to conventional end-to-end pixel models, this hybrid architecture operates exclusively on an 11-dimensional vector of extracted color-based vegetation indices (e.g., GRVI) and textural statistics. The dual-branch design isolates global sequence context via the ViT module while leveraging the GNN branch as a structural prior to learn non-linear covariance between specific features. Evaluated against a suite of benchmarks including MiniViT, Baseline CNN, Random Forest, XGBoost, and LightGBM, the proposed algorithm attained the highest Overall Accuracy of 0.930 utilizing merely 16,323 trainable parameters—a nearly 75% reduction in footprint versus pixel-based models. Crucially, a McNemar’s statistical test confirmed that the accuracy gain over the strongest classical baseline (XGBoost, OA: 0.927) is statistically significant (<i>p</i> &lt; 0.05). By pairing rigorous spatial cross-validation with an interpretable feature space, this work establishes that intelligent data pre-processing combined with graph-based relational learning offers a robust framework for high-precision environmental mapping under severe resource limitations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A lightweight hybrid ViT-GNN framework for data-centric land cover mapping in the amazon biome using graph structural priors

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月26日

查看全文
  • Wibowo Harry Sugiharto,
  • Muhammad Imam Ghozali,
  • Alif Catur Murti

摘要

Continuous monitoring of the Amazon biome demands land cover classification models that are both highly sensitive and computationally feasible. To resolve the inherent trade-off between architectural complexity and predictive performance in spatial deep learning, this study introduces the Vision Transformer–Graph Neural Network with Feature Adaptation (ViT-GNN RFFA). In contrast to conventional end-to-end pixel models, this hybrid architecture operates exclusively on an 11-dimensional vector of extracted color-based vegetation indices (e.g., GRVI) and textural statistics. The dual-branch design isolates global sequence context via the ViT module while leveraging the GNN branch as a structural prior to learn non-linear covariance between specific features. Evaluated against a suite of benchmarks including MiniViT, Baseline CNN, Random Forest, XGBoost, and LightGBM, the proposed algorithm attained the highest Overall Accuracy of 0.930 utilizing merely 16,323 trainable parameters—a nearly 75% reduction in footprint versus pixel-based models. Crucially, a McNemar’s statistical test confirmed that the accuracy gain over the strongest classical baseline (XGBoost, OA: 0.927) is statistically significant (p < 0.05). By pairing rigorous spatial cross-validation with an interpretable feature space, this work establishes that intelligent data pre-processing combined with graph-based relational learning offers a robust framework for high-precision environmental mapping under severe resource limitations.