arXiv subjects

Felix Rembold

Publications and source records attributed to Felix Rembold.

5 recordsLinked to original sources

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↗

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↗

arXiv2025

From Rows to Yields: How Foundation Models for Tabular Data Simplify Crop Yield Prediction

We present an application of a foundation model for small- to medium-sized tabular data (TabPFN), to sub-national yield forecasting task in South Africa. TabPFN has recently demonstrated superior performance compared to traditional machine learning (ML) models in various regression and classification tasks. We used the dekadal (10-days) time series of Earth Observation (EO; FAPAR and soil moisture) and gridded weather data (air temperature, precipitation and radiation) to forecast the yield of summer crops at the sub-national level. The crop yield data was available for 23 years and for up to 8 provinces. Covariate variables for TabPFN (i.e., EO and weather) were extracted by region and aggregated at a monthly scale. We benchmarked the results of the TabPFN against six ML models and three baseline models. Leave-one-year-out cross-validation experiment setting was used in order to ensure the assessment of the models capacity to forecast an unseen year. Results showed that TabPFN and ML models exhibit comparable accuracy, outperforming the baselines. Nonetheless, TabPFN demonstrated superior practical utility due to its significantly faster tuning time and reduced requirement for feature engineering. This renders TabPFN a more viable option for real-world operation yield forecasting applications, where efficiency and ease of implementation are paramount.

cs.AI↗

arXiv2025

A monthly sub-national Harmonized Food Insecurity Dataset for comprehensive analysis and predictive modeling

Food security is a complex, multidimensional concept challenging to measure comprehensively. Effective anticipation, monitoring, and mitigation of food crises require timely and comprehensive global data. This paper introduces the Harmonized Food Insecurity Dataset (HFID), an open-source resource consolidating four key data sources: the Integrated Food Security Phase Classification (IPC)/Cadre Harmonis\'e (CH) phases, the Famine Early Warning Systems Network (FEWS NET) IPC-compatible phases, and the World Food Program's (WFP) Food Consumption Score (FCS) and reduced Coping Strategy Index (rCSI). Updated monthly and using a common reference system for administrative units, the HFID offers extensive spatial and temporal coverage. It serves as a vital tool for food security experts and humanitarian agencies, providing a unified resource for analyzing food security conditions and highlighting global data disparities. The scientific community can also leverage the HFID to develop data-driven predictive models, enhancing the capacity to forecast and prevent future food crises.

cs.LG↗

arXiv2021

Yield forecasting with machine learning and small data: what gains for grains?

Forecasting crop yields is important for food security, in particular to predict where crop production is likely to drop. Climate records and remotely-sensed data have become instrumental sources of data for crop yield forecasting systems. Similarly, machine learning methods are increasingly used to process big Earth observation data. However, access to data necessary to train such algorithms is often limited in food-insecure countries. Here, we evaluate the performance of machine learning algorithms and small data to forecast yield on a monthly basis between the start and the end of the growing season. To do so, we developed a robust and automated machine-learning pipeline which selects the best features and model for prediction. Taking Algeria as case study, we predicted national yields for barley, soft wheat and durum wheat with an accuracy of 0.16-0.2 t/ha (13-14 % of mean yield) within the season. The best machine-learning models always outperformed simple benchmark models. This was confirmed in low-yielding years, which is particularly relevant for early warning. Nonetheless, the differences in accuracy between machine learning and benchmark models were not always of practical significance. Besides, the benchmark models outperformed up to 60% of the machine learning models that were tested, which stresses the importance of proper model calibration and selection. For crop yield forecasting, like for many application domains, machine learning has delivered significant improvement in predictive power. Nonetheless, superiority over simple benchmarks is often fully achieved after extensive calibration, especially when dealing with small data.

stat.AP↗