Grazing Detection using Deep Learning and Sentinel-2 Time Series Data
This work addresses the challenge of monitoring grazing for agricultural and conservation compliance, offering a practical tool for inspectors, though it is incremental as it applies existing deep learning methods to a specific domain.
The study tackled the problem of scalable monitoring of grazing by detecting seasonal grazing from Sentinel-2 time series data, achieving an average F1 score of 77% with 90% recall on grazed pastures and enabling 17.2 times more efficient inspection prioritization for non-grazing sites.
Grazing shapes both agricultural production and biodiversity, yet scalable monitoring of where grazing occurs remains limited. We study seasonal grazing detection from Sentinel-2 L2A time series: for each polygon-defined field boundary, April-October imagery is used for binary prediction (grazed / not grazed). We train an ensemble of CNN-LSTM models on multi-temporal reflectance features, and achieve an average F1 score of 77 percent across five validation splits, with 90 percent recall on grazed pastures. Operationally, if inspectors can visit at most 4 percent of sites annually, prioritising fields predicted by our model as non-grazed yields 17.2 times more confirmed non-grazing sites than random inspection. These results indicate that coarse-resolution, freely available satellite data can reliably steer inspection resources for conservation-aligned land-use compliance. Code and models have been made publicly available.