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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pirinen, Aleksis, Yela, Delia Fano, Chakraborty, Smita, Källman, Erik
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914096348135424
author Pirinen, Aleksis
Yela, Delia Fano
Chakraborty, Smita
Källman, Erik
author_facet Pirinen, Aleksis
Yela, Delia Fano
Chakraborty, Smita
Källman, Erik
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14493
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Grazing Detection using Deep Learning and Sentinel-2 Time Series Data
Pirinen, Aleksis
Yela, Delia Fano
Chakraborty, Smita
Källman, Erik
Computer Vision and Pattern Recognition
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.
title Grazing Detection using Deep Learning and Sentinel-2 Time Series Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.14493