arXiv subjects

Astrid Verhegghen

Publications and source records attributed to Astrid Verhegghen.

4 recordsLinked to original sources

arXiv2026

COLD-CI: A large-scale very high-resolution label polygon dataset for cocoa and non-cocoa classification in Cote d'Ivoire

Spatially explicit information on cocoa cultivation is essential for land-use planning, deforestation monitoring, environmental assessment, and supply-chain analysis. Although several cocoa map products exist, their underlying reference data are often not publicly available, limiting transparency and methodological benchmarking. Here, we present a large-scale, very high-resolution cocoa and non-cocoa label polygon dataset for Cote d'Ivoire (COLD-CI), covering the main cocoa-producing regions as well as contrasting non-cocoa landscapes. COLD-CI consists of 123,736 vector polygons corresponding to a total labelled area of 5,996 km^2, including 58,107 cocoa polygons (1,788 km^2) and 65,629 background polygons (4,208 km^2). Polygon label candidates were first generated through conservative automated filtering of polygons from the West Africa Cocoa dataset and the combination of multiple external thematic datasets. These candidates were subsequently refined and complemented through systematic visual interpretation, manual correction, and digitisation using very high-resolution (0.5 m) satellite imagery. The resulting label polygons capture cocoa planted areas and associated fine-scale internal heterogeneity, as well as a wide range of non-cocoa land-cover types. Independent validation using field-based and expert photointerpreted reference data from the Copernicus4GEOGLAM validation dataset indicated an overall agreement of 99%, with producer's and user's accuracy exceeding 98% for both cocoa and background classes. COLD-CI is released as a vector dataset with associated metadata to support transparent benchmarking, model development, and validation across a wide range of spatial resolutions.

q-bio.OT↗

arXiv2026

Is sub-metre resolution necessary for cocoa mapping? A landscape-stratified evaluation of very high resolution imagery, decametric Earth Observation inputs, and operational products in Cote d'Ivoire

Accurate cocoa mapping is increasingly important for deforestation monitoring, supply-chain transparency, and regulatory applications. Spatial aggregation in conventional medium-resolution Earth observation (EO) imagery may limit cocoa detection in heterogeneous smallholder landscapes. In Cote d'Ivoire, we therefore evaluated how mapping performance varies across landscape conditions, whether very high resolution (VHR) imagery provides a meaningful advantage, and whether foundation-model embeddings improve decametric cocoa mapping. We developed models using 0.5 m Pleiades VHR imagery, a 10 m Sentinel-2 annual composite, and embeddings from TESSERA and AlphaEarth Foundations (AEF), and additionally assessed four publicly available cocoa mapping products. Performance was evaluated through a landscape-stratified accuracy assessment using 2,821 independently interpreted reference points distributed across gradients of tree cover density and landscape fragmentation. The VHR model achieved the highest performance (F1 = 0.92) and maintained F1-scores above 0.90 across all strata. Among the decametric inputs, TESSERA performed best (F1 = 0.86), followed by AEF (F1 = 0.82) and Sentinel-2 (F1 = 0.76). Of the existing cocoa products, the Kalischek product performed best (F1 = 0.83), comparable to the internally trained AEF model. Performance differences between VHR and decametric approaches increased with fragmentation and under low and high tree cover density conditions. Targeted VHR acquisition may therefore be particularly beneficial in complex cocoa landscapes, while foundation-model embeddings offer a scalable alternative for large-area mapping.

cs.CV↗

arXiv2024

From parcels to people: development of a spatially explicit risk indicator to monitor residential pesticide exposure in agricultural areas

The increase in global pesticide use has mirrored the rising demand for food over the last decades, resulting in a boost in crop yields. However, concerns about the impact of pesticides on biodiversity, ecosystems, and human health, especially for populations residing close to cultivated areas, are growing. This study investigates how exposure and possible risks to residents can be estimated at high spatial granularity based on plant protection product data. The complexities of such analysis were explored in France, where relevant data with good granularity are publicly available. Integrating sets of spatial datasets and exposure assessment methodologies, we have developed an indicator to monitor the levels of pesticide risk faced by residents. By spatialising pesticide sales data according to their authorization on specific crops, we developed a detailed map depicting potential pesticide loads at parcel level across France. This spatial distribution served as the basis for an exposure and risk assessment, modelled following the European Food Safety Authority's guidelines. Combining the risk map with population distribution data, we have developed an indicator that allows to monitor patterns in non-dietary exposure to pesticides. Our results show that in France, on average, 13% of people might be exposed to pesticides due to living in the proximity to treated crops. This exposure is in the lower range for 34%, moderate range for 40% and higher range for 25% of the exposed population. The risk evaluation is based on worst case assumptions and values should not be taken as a regulatory risk assessment but as indicator to use, for example, for monitoring time trends. The purpose of this indicator is to demonstrate that more granular pesticide data can improve risk reduction strategies. Harmonized and high-resolution data can help in identifying regions where to focus on sustainable farming.

q-bio.QM↗

arXiv2021

From parcel to continental scale -- A first European crop type map based on Sentinel-1 and LUCAS Copernicus in-situ observations

Detailed parcel-level crop type mapping for the whole European Union (EU) is necessary for the evaluation of agricultural policies. The Copernicus program, and Sentinel-1 (S1) in particular, offers the opportunity to monitor agricultural land at a continental scale and in a timely manner. However, so far the potential of S1 has not been explored at such a scale. Capitalizing on the unique LUCAS 2018 Copernicus in-situ survey, we present the first continental crop type map at 10-m spatial resolution for the EU based on S1A and S1B Synthetic Aperture Radar observations for the year 2018. Random forest classification algorithms are tuned to detect 19 different crop types. We assess the accuracy of this EU crop map with three approaches. First, the accuracy is assessed with independent LUCAS core in-situ observations over the continent. Second, an accuracy assessment is done specifically for main crop types from farmers declarations from 6 EU member countries or regions totaling >3M parcels and 8.21 Mha. Finally, the crop areas derived by classification are compared to the subnational (NUTS 2) area statistics reported by Eurostat. The overall accuracy for the map is reported as 80.3% when grouping main crop classes and 76% when considering all 19 crop type classes separately. Highest accuracies are obtained for rape and turnip rape with user and produced accuracies higher than 96%. The correlation between the remotely sensed estimated and Eurostat reported crop area ranges from 0.93 (potatoes) to 0.99 (rape and turnip rape). Finally, we discuss how the framework presented here can underpin the operational delivery of in-season high-resolution based crop mapping.

stat.ML↗