Identification of winter land use in temperate agricultural landscapes based on Sentinel-1 and 2 times-series

Denize Julien, Hubert-Moy Laurence, Corgne Samuel, Betbeder Julie, Pottier Eric. 2018. Identification of winter land use in temperate agricultural landscapes based on Sentinel-1 and 2 times-series. In : Proceedings of 2018 IEEE International Geoscience and Remote Sensing Symposium: Observing, Understanding and Forecasting the Dynamics of our Planet. IEEE. Piscataway : IEEE, 8271-8274. International Geoscience and Remote Sensing Symposium (IGARSS 2018), Valencia, Espagne, 22 Juillet 2018/27 Juillet 2018.

Résumé : Land cover and land use monitoring, particularly during winter season, is still a major environmental and scientific issue in agricultural areas. From an environmental point of view, the presence and type of vegetation cover in winter have an impact on pollutant transport to water bodies. From a methodological point of view, characterizing spatio-temporal dynamics of winter land cover and land use at a field scale remains a challenge due to the diversity of farming strategies and practices. The objective of this study was to evaluate the potential of optical and SAR time-series to improve the monitoring of winter land use in an area of 130 km². For that purpose, Sentinel-1 and 2 time-series were classified using SVM and RF algorithms. Winter land use was identified with an overall accuracy of 81% and a kappa index of 0.77 from a combination of Sentinel-1 and 2 images.

Auteurs et affiliations

• Denize Julien, Université de Rennes I (FRA)
• Hubert-Moy Laurence, Université de Rennes 2 (FRA)
• Corgne Samuel, Université de Rennes 2 (FRA)
• Betbeder Julie, CIRAD-ES-UPR Forêts et sociétés (CRI)
• Pottier Eric, Université de Rennes I (FRA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/599351/)

Métriques

[ Page générée et mise en cache le 2021-10-12 ]