Answers are grounded in this paper and cite their sources.
Glyphosate-based herbicides are widely used in agriculture, particularly in Europe, where they are commonly applied to terminate winter cover crops prior to spring planting. However, their use remains controversial due to concerns over potential environmental and health impacts. Accurate spatial information on glyphosate application is critical for exposure assessment, yet mapping efforts using remote sensing remain limited, especially with open-access data under real-world field conditions. This study presents a remote sensing and machine learning-based methodology to identify agricultural parcels where glyphosate was applied for cover crop termination. Using Flanders, Belgium, as a case study during the 2023 and 2024 seasons, we compiled a training dataset consisting of parcels with crops chemically terminated with glyphosate, parcels with ongoing vegetative cover or bare soil, and parcels with crops mechanically terminated. Sentinel-2 imagery was used to derive spectral indices sensitive to chlorophyll and carotenoid content. We applied a threshold-based approach to analyze time-series spectral variations following termination. Two machine learning classifiers, Decision Tree (DT) and Random Forest (RF), were trained and evaluated using field-validated parcel data. Glyphosate-treated parcels exhibited a distinct spectral response: a rapid decline in chlorophyll-sensitive indices followed by a delayed increase in carotenoid-sensitive indices. These trends contrasted clearly with those observed in mechanically terminated or untreated parcels. The DT and RF classifiers achieved overall accuracies of 0.92 and 0.95, respectively. This study demonstrates the potential of combining open-access satellite data and machine learning to detect glyphosate applications at scale, offering a cost-effective framework for herbicide monitoring in support of environmental and public health assessments.
No takes yet. Share an insight, caveat, or question.
Zago et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: