Answers are grounded in this paper and cite their sources.
Evaluates innovative models for soil organic carbon prediction in cropland regions, suggesting effective alternatives for management practices.
• Limited bare soil conditions restrict conventional EO-based SOC monitoring • Farm management strongly controls bare-soil frequency and SOC predictability • Deep-learning satellite embeddings provide top SOC prediction • Spatially informed models help capture SOC variability across regions • SOC assessment is feasible without relying solely on bare-soil imagery The estimation of Soil Organic Carbon (SOC) from optical image spectroscopy typically relies on the availability of bare-soil conditions, which are increasingly rare due to the widespread adoption of conservation agriculture practices. This study evaluates alternative strategies for SOC prediction under limited bare-soil availability by comparing four methodological approaches based on Sentinel-2 imagery and related products: (i) bare-soil multispectral composites, (ii) vegetation indices, (iii) AlphaEarth Satellite Embeddings, and (iv) a hybrid geostatistical–machine learning model (KpR–Cubist). These methods were tested across three cropland regions with contrasting pedoclimatic conditions: Italy, France, and Taiwan. The evaluation relied on more than 1,800 topsoil samples collected between 2020 and 2024. Results show that bare-soil availability varies significantly by region, with cloud cover and vegetation/farm management being the main limiting factors. Models using Satellite Embeddings consistently achieved the highest predictive accuracy (RPIQ up to 2.24) , outperforming conventional bare-soil composite and vegetation-based models. Incorporating spatial coordinates further improved model performance, revealing strong spatial autocorrelation in SOC distribution. The hybrid kriging–Cubist approach achieved comparable accuracy to the embedding-based models, confirming the value of integrating spatial dependence into data-driven frameworks. Overall, the study demonstrates that deep-learning–derived satellite embeddings models provide effective alternatives for SOC estimation in croplands where bare-soil imagery is increasingly unavailable due to sustainable soil management practices.
No takes yet. Share an insight, caveat, or question.
Castaldi et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: