Space2Ground 2.0: A Multi-Source Dataset and Framework for Agricultural Monitoring through Fusion of Street-Level and Satellite Imagery

2026-07-30

AI Summary

This study addresses the challenge of temporal data gaps in parcel-level agricultural monitoring caused by limited viewing angles and persistent cloud cover in satellite remote sensing. To overcome this, the work presents the first large-scale integration of Sentinel-1/2 time-series satellite data with Mapillary crowdsourced street-level imagery, establishing a scalable and reproducible multimodal agricultural monitoring framework. By employing semantic filtering, image quality assessment, viewpoint-aware parcel matching, and a multi-source fusion strategy, the approach effectively enhances complementarity between fine-grained visual cues and remote sensing observations. Evaluated on a novel dataset from Cyprus’s 2022 growing season—comprising 46,050 annotated street-view images covering 8,581 agricultural parcels—the method significantly improves crop classification accuracy, demonstrating the effectiveness and innovative potential of multimodal data fusion in precision agriculture.

Abstract

Accurate and scalable parcel-level agricultural monitoring remains challenging because satellite Earth Observation alone provides only an overhead perspective of agricultural parcels, while optical observations are further affected by cloud-induced temporal gaps. This paper presents Space2Ground 2.0, a multi-source framework integrating Sentinel-1 SAR and Sentinel-2 multispectral time series with geo-tagged street-level imagery acquired using vehicle-mounted cameras and shared through the Mapillary platform. A largely automated processing pipeline performs semantic filtering, image quality assessment, viewpoint-based parcel association, and dataset refinement, transforming large volumes of crowdsourced imagery into parcel-linked, analysis-ready data. Applied over Cyprus during the 2022 growing season, the pipeline produced a curated dataset of 46,050 annotated street-level images, selected from an initial collection exceeding 900,000 images and linked with satellite information for 8,581 agricultural parcels. The practical value of the dataset was assessed through parcel-level crop classification experiments using both single- and multi-source observations. The results demonstrate that street-level imagery provides complementary fine-scale visual information that enhances classification when integrated with satellite time series. Overall, Space2Ground 2.0 provides an openly available benchmark dataset and a reproducible methodology for multimodal agricultural monitoring, with potential applications in visual verification, reduced reliance on costly field inspections, and data-driven agricultural policy implementation.

Problem

• agricultural monitoring
• parcel-level
• satellite imagery
• street-level imagery
• cloud-induced gaps

Innovation

• street-level imagery
• satellite data fusion
• automated pipeline
• parcel-level monitoring
• multimodal agricultural monitoring