用图注意力网络预测土壤微塑料和有机质分布，精度高但泛化弱。
Spatial Prediction of Soil Microplastics and Organic Matter Using Graph Attention Networks
- 构建基于地理坐标的图神经网络，融合土壤属性与土地利用数据。
- 微塑料预测RMSE为625.06（R²=0.87），有机质预测RMSE为0.43（R²=0.91）。
- 适合土壤空间建模研究者，需注意小样本下模型泛化问题。
准确估算土壤微塑料和有机质对评估生态系统健康、支持可持续土地利用至关重要。本研究提出一种基于图注意力网络（GATs）的深度学习方法，用于建模91个地理参考土壤样本间的空间依赖关系。通过融合空间坐标、土壤性质及土地利用数据，构建了两层GAT架构以捕捉局部交互。最终模型表现良好，微塑料预测的均方根误差（RMSE）为625.06（R²=0.87），有机质预测的RMSE为0.43（R²=0.91）。然而，交叉验证结果显示模型泛化能力有限，可能源于样本量小和图结构稀疏。结果表明GAT在土壤空间预测中具有潜力，但也凸显出对密集数据集和改进图连通性的需求。
原文摘要 · Abstract (English)
Accurate estimation of soil microplastics and organic matter is essential to assess ecosystem health and support sustainable land use. This study presents a graph-based deep learning approach using Graph Attention Networks (GATs) to model spatial dependencies among 91 georeferenced soil samples. By incorporating spatial coordinates, soil properties, and land use data, a two-layer GAT architecture was developed to capture local interactions. The final model showed strong performance, achieving RMSEs of 625.06 ($R^2 = 0.87$) for microplastics and 0.43 ($R^2 = 0.91$) for organic matter. However, cross-validation results revealed limited generalization, probably due to the small sample size and sparse graph structure. These findings demonstrate the potential of GATs for spatial soil prediction and underscore the need for dense datasets and improved graph connectivity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。