Spatial Prediction of Soil Microplastics and Organic Matter Using Graph Attention Networks

arXiv cs.LG Papers

Summary

This paper presents a Graph Attention Network (GAT) approach to model spatial dependencies in soil samples for predicting microplastics and organic matter, achieving high R² values but limited cross-validation generalization due to small sample size.

arXiv:2607.22875v1 Announce Type: new Abstract: 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.
Original Article
View Cached Full Text

Cached at: 07/28/26, 06:22 AM

# Spatial Prediction of Soil Microplastics and Organic Matter Using Graph Attention Networks
Source: [https://arxiv.org/abs/2607.22875](https://arxiv.org/abs/2607.22875)
[View PDF](https://arxiv.org/pdf/2607.22875)

> Abstract: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\.

## Submission history

From: Md Al Amin \[[view email](https://arxiv.org/show-email/41817b8a/2607.22875)\] **\[v1\]**Fri, 24 Jul 2026 19:35:29 UTC \(941 KB\)

Similar Articles

A Global-Local Graph Attention Network for Traffic Forecasting

arXiv cs.AI

Proposes a Global-Local Graph Attention Network (GLGAT) with pairwise encoding and event-based adjacency matrix for traffic forecasting, effectively capturing spatio-temporal correlations and achieving competitive performance on real-world datasets.

A Temporally Augmented Graph Attention Network for Affordance Classification

Hugging Face Daily Papers

EEG-tGAT is a temporally augmented Graph Attention Network that improves affordance classification from interaction sequences by incorporating temporal attention and dropout mechanisms. The model enhances GATv2 for sequential data where temporal dimensions are semantically non-uniform.