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

Researchers used a smart computer model to map where microplastics and organic matter show up in soil, based on location and land-use patterns—an early step toward better tracking of how plastic pollution spreads through the ground we grow food in. The tool worked well on the soil samples tested, but the study was based on a small dataset, so more research is needed before it can be reliably used to predict microplastic contamination in new areas. Still, this kind of technology could eventually help identify contaminated farmland faster, which matters since microplastics in soil can end up in crops and, ultimately, our food.

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