Deploying Geospatial Foundation Models in the Real World: Lessons from WorldCereal

TL;DR

This paper offers a structured protocol for deploying geospatial foundation models in real-world remote sensing applications, emphasizing adaptation, empirical testing, and demonstrating success with crop mapping.

Contribution

It introduces a practical, step-by-step framework for operationalizing geospatial foundation models, validated through a case study on crop mapping.

Findings

Fine-tuning improves model performance over traditional methods.

Models exhibit strong spatial and temporal generalization.

The protocol is scalable and applicable to diverse applications.

Abstract

The increasing availability of geospatial foundation models has the potential to transform remote sensing applications such as land cover classification, environmental monitoring, and change detection. Despite promising benchmark results, the deployment of these models in operational settings is challenging and rare. Standardized evaluation tasks often fail to capture real-world complexities relevant for end-user adoption such as data heterogeneity, resource constraints, and application-specific requirements. This paper presents a structured approach to integrate geospatial foundation models into operational mapping systems. Our protocol has three key steps: defining application requirements, adapting the model to domain-specific data and conducting rigorous empirical testing. Using the Presto model in a case study for crop mapping, we demonstrate that fine-tuning a pre-trained model significantly improves performance over conventional supervised methods. Our results highlight the model's strong spatial and temporal generalization capabilities. Our protocol provides a replicable blueprint for practitioners and lays the groundwork for future research to operationalize foundation models in diverse remote sensing applications. Application of the protocol to the WorldCereal global crop-mapping system showcases the framework's scalability.