0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Sign in to save

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

arXiv (Cornell University) 2026
Anik Dev Nath, Md Al Amin, Bikash Kumar Paul

Summary

Scientists tested a new AI tool that predicts how much microplastic pollution and organic matter is hiding in soil, using data from nearby locations to fill in the gaps. The approach worked well on the samples tested, which matters because knowing where microplastics accumulate in soil can help us understand how they might enter our food and water supply—but the researchers caution that more data is needed before this tool can be reliably used elsewhere.

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.

Share this paper