Using Sentinel-2 image time series to map the State of Victoria, Australia

Charlotte Pelletier, Zehui Ji, Olivier Hagolle, Elizabeth Morse-McNabb, Kathryn Sheffield, Geoffrey I. Webb, Francois Petitjean

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

Abstract

Sentinel-2 satellites are now acquiring images of the entire Earth every five days from 10 to 60 m spatial resolution. The supervised classification of this new optical image time series allows the operational production of accurate land cover maps over large areas. In this paper, we investigate the use of one year of Sentinel-2 data to map the state of Victoria in Australia. In particular, we produce two land cover maps using the most established and advanced algorithms in time series classification: Random Forest (RF) and Temporal Convolutional Neural Network (TempCNN). To our knowledge, these are the first land cover maps at 10 m spatial resolution for an Australian state.

Original languageEnglish
Title of host publication2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp 2019)
EditorsFrancesca Bovolo, Sicong Liu
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages13-16
Number of pages4
ISBN (Electronic)9781728146157
ISBN (Print)9781728146164
DOIs
Publication statusPublished - 2019
EventInternational Workshop on the Analysis of Multitemporal Remote Sensing Images 2019 - Shanghai, China
Duration: 5 Aug 20197 Aug 2019
Conference number: 10th
https://multitemp2019.tongji.edu.cn/

Conference

ConferenceInternational Workshop on the Analysis of Multitemporal Remote Sensing Images 2019
Abbreviated titleMultiTemp 2019
CountryChina
CityShanghai
Period5/08/197/08/19
Internet address

Keywords

  • land cover map
  • Random Forests
  • Sentinel-2 images
  • Temporal Convolutional Neural Networks
  • time series

Cite this

Pelletier, C., Ji, Z., Hagolle, O., Morse-McNabb, E., Sheffield, K., Webb, G. I., & Petitjean, F. (2019). Using Sentinel-2 image time series to map the State of Victoria, Australia. In F. Bovolo, & S. Liu (Eds.), 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp 2019) (pp. 13-16). [8866921] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/Multi-Temp.2019.8866921
Pelletier, Charlotte ; Ji, Zehui ; Hagolle, Olivier ; Morse-McNabb, Elizabeth ; Sheffield, Kathryn ; Webb, Geoffrey I. ; Petitjean, Francois. / Using Sentinel-2 image time series to map the State of Victoria, Australia. 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp 2019). editor / Francesca Bovolo ; Sicong Liu. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2019. pp. 13-16
@inproceedings{cfdd0831b33a407b8108563d8323f78d,
title = "Using Sentinel-2 image time series to map the State of Victoria, Australia",
abstract = "Sentinel-2 satellites are now acquiring images of the entire Earth every five days from 10 to 60 m spatial resolution. The supervised classification of this new optical image time series allows the operational production of accurate land cover maps over large areas. In this paper, we investigate the use of one year of Sentinel-2 data to map the state of Victoria in Australia. In particular, we produce two land cover maps using the most established and advanced algorithms in time series classification: Random Forest (RF) and Temporal Convolutional Neural Network (TempCNN). To our knowledge, these are the first land cover maps at 10 m spatial resolution for an Australian state.",
keywords = "land cover map, Random Forests, Sentinel-2 images, Temporal Convolutional Neural Networks, time series",
author = "Charlotte Pelletier and Zehui Ji and Olivier Hagolle and Elizabeth Morse-McNabb and Kathryn Sheffield and Webb, {Geoffrey I.} and Francois Petitjean",
year = "2019",
doi = "10.1109/Multi-Temp.2019.8866921",
language = "English",
isbn = "9781728146164",
pages = "13--16",
editor = "Bovolo, {Francesca } and Liu, {Sicong }",
booktitle = "2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp 2019)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Pelletier, C, Ji, Z, Hagolle, O, Morse-McNabb, E, Sheffield, K, Webb, GI & Petitjean, F 2019, Using Sentinel-2 image time series to map the State of Victoria, Australia. in F Bovolo & S Liu (eds), 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp 2019)., 8866921, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 13-16, International Workshop on the Analysis of Multitemporal Remote Sensing Images 2019, Shanghai, China, 5/08/19. https://doi.org/10.1109/Multi-Temp.2019.8866921

Using Sentinel-2 image time series to map the State of Victoria, Australia. / Pelletier, Charlotte; Ji, Zehui; Hagolle, Olivier; Morse-McNabb, Elizabeth; Sheffield, Kathryn; Webb, Geoffrey I.; Petitjean, Francois.

2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp 2019). ed. / Francesca Bovolo; Sicong Liu. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2019. p. 13-16 8866921.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

TY - GEN

T1 - Using Sentinel-2 image time series to map the State of Victoria, Australia

AU - Pelletier, Charlotte

AU - Ji, Zehui

AU - Hagolle, Olivier

AU - Morse-McNabb, Elizabeth

AU - Sheffield, Kathryn

AU - Webb, Geoffrey I.

AU - Petitjean, Francois

PY - 2019

Y1 - 2019

N2 - Sentinel-2 satellites are now acquiring images of the entire Earth every five days from 10 to 60 m spatial resolution. The supervised classification of this new optical image time series allows the operational production of accurate land cover maps over large areas. In this paper, we investigate the use of one year of Sentinel-2 data to map the state of Victoria in Australia. In particular, we produce two land cover maps using the most established and advanced algorithms in time series classification: Random Forest (RF) and Temporal Convolutional Neural Network (TempCNN). To our knowledge, these are the first land cover maps at 10 m spatial resolution for an Australian state.

AB - Sentinel-2 satellites are now acquiring images of the entire Earth every five days from 10 to 60 m spatial resolution. The supervised classification of this new optical image time series allows the operational production of accurate land cover maps over large areas. In this paper, we investigate the use of one year of Sentinel-2 data to map the state of Victoria in Australia. In particular, we produce two land cover maps using the most established and advanced algorithms in time series classification: Random Forest (RF) and Temporal Convolutional Neural Network (TempCNN). To our knowledge, these are the first land cover maps at 10 m spatial resolution for an Australian state.

KW - land cover map

KW - Random Forests

KW - Sentinel-2 images

KW - Temporal Convolutional Neural Networks

KW - time series

UR - http://www.scopus.com/inward/record.url?scp=85074293581&partnerID=8YFLogxK

U2 - 10.1109/Multi-Temp.2019.8866921

DO - 10.1109/Multi-Temp.2019.8866921

M3 - Conference Paper

AN - SCOPUS:85074293581

SN - 9781728146164

SP - 13

EP - 16

BT - 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp 2019)

A2 - Bovolo, Francesca

A2 - Liu, Sicong

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Pelletier C, Ji Z, Hagolle O, Morse-McNabb E, Sheffield K, Webb GI et al. Using Sentinel-2 image time series to map the State of Victoria, Australia. In Bovolo F, Liu S, editors, 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp 2019). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2019. p. 13-16. 8866921 https://doi.org/10.1109/Multi-Temp.2019.8866921