Challenges in Grassland Mowing Event Detection with Multimodal Sentinel Images

Anatol Garioud (1, 2) , Sébastien Giordano (2) , Silvia Valero (1) , Clément Mallet (2)

1 CESBIO - Centre d'études spatiales de la biosphère
2 LaSTIG - Laboratoire des Sciences et Technologies de l'Information Géographique

Permanent Grasslands (PG) are heterogeneous environments with high spatial and temporal dynamics, subject to increasing environmental challenges. This study aims to identify requirements, key constraining factors and solutions for robust and complete detection of Mowing Events. Remote sensing is a powerful tool to monitor and investigate Near-Real-Time and seasonally PG cover. Here, pros and cons of Sentinel-2 (S2) and Sentinel-1 (S1) time series exploitation for Mowing Events (MowEve) detection are analysed. A deep-based approach is proposed to obtain consistent and homogeneous biophysical parameter times series for MowEve detection. Recurrent Neural Networks are proposed as regression strategy allowing the synergistic integration of optical and Synthetic Aperture Radar data to reconstruct dense NDVI times series. Experimental results corroborates the interest of deriving consistent and homogeneous series of biophysical parameters for subsequent MowEve detection .

Mots clés: Mowing Events; Permanent Grasslands; Recurrent Neural Networks; Sentinel; Time Series; Regression; NDVI

Domaines: Traitement du signal et de l'image [eess.SP]; Apprentissage [cs.LG]

Anatol Garioud, Sébastien Giordano, Silvia Valero, Clément Mallet. Challenges in Grassland Mowing Event Detection with Multimodal Sentinel Images. 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp), Aug 2019, Shanghai, France. pp.1-4, ⟨10.1109/Multi-Temp.2019.8866914⟩. ⟨hal-02387167⟩