Cropland Mapping using Geospatial Embeddings

TL;DR

This paper explores the use of geospatial embeddings from Presto and AlphaEarth to improve cropland mapping accuracy in Togo, demonstrating their potential to simplify workflows and enhance land use change assessments.

Contribution

It evaluates the effectiveness of geospatial embeddings in cropland mapping, highlighting their advantages over traditional methods in real-world applications.

Findings

High-accuracy cropland classification achieved

Embeddings simplify mapping workflows

Supports better land use change assessments

Abstract

Accurate and up-to-date land cover maps are essential for understanding land use change, a key driver of climate change. Geospatial embeddings offer a more efficient and accessible way to map landscape features, yet their use in real-world mapping applications remains underexplored. In this work, we evaluated the utility of geospatial embeddings for cropland mapping in Togo. We produced cropland maps using embeddings from Presto and AlphaEarth. Our findings show that geospatial embeddings can simplify workflows, achieve high-accuracy cropland classification and ultimately support better assessments of land use change and its climate impacts.