Preprint Article Version 2 This version is not peer-reviewed

Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems

Version 1 : Received: 25 June 2019 / Approved: 26 June 2019 / Online: 26 June 2019 (14:04:13 CEST)
Version 2 : Received: 8 August 2019 / Approved: 9 August 2019 / Online: 9 August 2019 (11:54:37 CEST)

A peer-reviewed article of this Preprint also exists.

Stoian, A.; Poulain, V.; Inglada, J.; Poughon, V.; Derksen, D. Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems. Remote Sens. 2019, 11, 1986. Stoian, A.; Poulain, V.; Inglada, J.; Poughon, V.; Derksen, D. Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems. Remote Sens. 2019, 11, 1986.

Journal reference: Remote Sens. 2019, 11, 1986
DOI: 10.3390/rs11171986

Abstract

The Sentinel-2 satellite mission offers high resolution multispectral time series image data, enabling the production of detailed land cover maps globally. At this scale, the trade-off between processing time and result quality is a central design decision. Currently, this machine learning task is usually performed using pixelwise classification methods. The radical shift of the computer vision field away from hand engineered image features and towards more automation by representation learning comes with many promises, including higher quality results and less engineering effort. In this paper we assess fully convolutional neural networks architectures as replacements for a Random Forest classifier in an operational context for the production of high resolution land cover maps with Sentinel-2 time series at the country scale. Our contributions include a framework for working with Sentinel-2 L2A time series image data, an adaptation of the U-Net model for dealing with sparse annotation data while maintaining high resolution output, and an analysis of those results in the context of operational production of land cover maps.

Subject Areas

Land cover mapping; Convolutional neural networks; UNET; Sentinel-2

Comments (1)

Comment 1
Received: 9 August 2019
Commenter: Jordi Inglada
Commenter's Conflict of Interests: Author
Comment: Revised version of the manuscript (minor revision for the journal)
+ Respond to this comment

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 1
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.