Graph Neural Networks Extract High-Resolution Cultivated Land Maps from Sentinel-2 Image Series

TL;DR

This paper presents a graph neural network approach for high-resolution cultivated land mapping using Sentinel-2 satellite imagery, achieving superior accuracy and significantly reduced model size compared to traditional methods.

Contribution

The authors introduce a compact graph convolutional neural network that outperforms classical and deep learning techniques in land segmentation while drastically reducing model size.

Findings

Higher-quality segmentation maps than classical and deep learning methods

Model size is nearly 8,000 parameters, much smaller than U-Nets with up to 31 million parameters

Memory efficiency enables model uplink to satellites in orbit

Abstract

Maintaining farm sustainability through optimizing the agricultural management practices helps build more planet-friendly environment. The emerging satellite missions can acquire multi- and hyperspectral imagery which captures more detailed spectral information concerning the scanned area, hence allows us to benefit from subtle spectral features during the analysis process in agricultural applications. We introduce an approach for extracting 2.5 m cultivated land maps from 10 m Sentinel-2 multispectral image series which benefits from a compact graph convolutional neural network. The experiments indicate that our models not only outperform classical and deep machine learning techniques through delivering higher-quality segmentation maps, but also dramatically reduce the memory footprint when compared to U-Nets (almost 8k trainable parameters of our models, with up to 31M parameters of U-Nets). Such memory frugality is pivotal in the missions which allow us to uplink a model to the AI-powered satellite once it is in orbit, as sending large nets is impossible due to the time constraints.