English

Grazing Detection using Deep Learning and Sentinel-2 Time Series Data

Computer Vision and Pattern Recognition 2025-10-17 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2510.14493,
  title  = {Grazing Detection using Deep Learning and Sentinel-2 Time Series Data},
  author = {Aleksis Pirinen and Delia Fano Yela and Smita Chakraborty and Erik Källman},
  journal= {arXiv preprint arXiv:2510.14493},
  year   = {2025}
}

Comments

Code and models: https://github.com/aleksispi/pib-ml-grazing

R2 v1 2026-07-01T06:40:54.695Z