Annual Crop Classification Experiments in Portugal Using Sentinel-2

Pedro Benevides; Hugo Costa; Francisco D. Moreira; Daniel Moraes; Mario Caetano

doi:10.1109/IGARSS47720.2021.9555009

Annual Crop Classification Experiments in Portugal Using Sentinel-2

Pedro Benevides, Hugo Costa, Francisco D. Moreira, Daniel Moraes, Mario Caetano

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

55 Downloads (Pure)

Abstract

This paper presents an experimental crop classification of the 10 most abundant annual crop types in Portugal, using a study area located in Alentejo region. This region has great diversity of land uses as well as multiple crop types. Sentinel-2 2018 intra-annual time-series imagery is considered in the experiment. The Portuguese Land Parcel Identification System (LPIS) is used to extract automatic training samples. LPIS information is automatically processed with the help of auxiliary datasets to filter out crop areas more likely to have been mislabeled. Classification is obtained using random forest. Validation is performed using an independent dataset also based on LPIS. A global accuracy of 76% is obtained. The novelty of the methodology here presented shows that LPIS can be used together with auxiliary data for crop type mapping, helping to characterize the agriculture land diversity in Portugal.

Original language	English
Title of host publication	IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium
Subtitle of host publication	Proceedings
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	5838-5841
Number of pages	4
ISBN (Print)	978-1-6654-0369-6
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9555009
Publication status	Published - 11 Jul 2021
Event	IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium - Brussels, Belgium Duration: 11 Jul 2021 → 16 Jul 2021

Conference

Conference	IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium
Country/Territory	Belgium
City	Brussels
Period	11/07/21 → 16/07/21

Keywords

crop mapping
Portugal
random forest
time-series
Sentinel-2

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IGARSS47720.2021.9555009

Annual_Crop_Classification_Experiments_Portugal_Sentinel-2Accepted author manuscript, 663 KBLicence: Unspecified

https://ieeexplore.ieee.org/document/9555009/

Cite this

@inproceedings{776c01282508442eb6971e236dc43f63,

title = "Annual Crop Classification Experiments in Portugal Using Sentinel-2",

abstract = "This paper presents an experimental crop classification of the 10 most abundant annual crop types in Portugal, using a study area located in Alentejo region. This region has great diversity of land uses as well as multiple crop types. Sentinel-2 2018 intra-annual time-series imagery is considered in the experiment. The Portuguese Land Parcel Identification System (LPIS) is used to extract automatic training samples. LPIS information is automatically processed with the help of auxiliary datasets to filter out crop areas more likely to have been mislabeled. Classification is obtained using random forest. Validation is performed using an independent dataset also based on LPIS. A global accuracy of 76% is obtained. The novelty of the methodology here presented shows that LPIS can be used together with auxiliary data for crop type mapping, helping to characterize the agriculture land diversity in Portugal.",

keywords = "crop mapping, Portugal, random forest, time-series, Sentinel-2",

author = "Pedro Benevides and Hugo Costa and Moreira, {Francisco D.} and Daniel Moraes and Mario Caetano",

note = "info:eu-repo/grantAgreement/FCT/3599-PPCDT/PCIF%2FSSI%2F0102%2F2017/PT# info:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FAI%2F0100%2F2018/PT# info:eu-repo/grantAgreement/FCT/3599-PPCDT/PCIF%2FMOS%2F0046%2F2017/PT# Benevides, P., Costa, H., Moreira, F. D., Moraes, D., & Caetano, M. (2021). Annual Crop Classification Experiments in Portugal Using Sentinel-2. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium: Proceedings (pp. 5838-5841). IEEE. https://doi.org/10.1109/IGARSS47720.2021.9555009 --------------------------- This work has been supported by projects IPSTERS (DSAIPA/AI/0100/2018), foRESTER (PCIF/SSI/0102/2017), and SCAPEFIRE (PCIF/MOS/0046/2017), and by Centro de Investiga{\c c}{\~a}o em Gest{\~a}o de Informa{\c c}{\~a}o (MagIC), all funded by the Portuguese Foundation for Science and Technology (FCT). Value-added data processed by CNES for the Theia data centre www.theia-land.fr using Copernicus products. The satellite image pre-processing uses algorithms developed by Theia's Scientific Expertise Centers. SIP validation data was kindly provided by Instituto de Financiamento da Agricultura e Pescas.; IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium ; Conference date: 11-07-2021 Through 16-07-2021",

year = "2021",

month = jul,

day = "11",

doi = "10.1109/IGARSS47720.2021.9555009",

language = "English",

isbn = "978-1-6654-0369-6",

pages = "5838--5841",

booktitle = "IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Benevides, P, Costa, H, Moreira, FD, Moraes, D & Caetano, M 2021, Annual Crop Classification Experiments in Portugal Using Sentinel-2. in IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium: Proceedings. Institute of Electrical and Electronics Engineers (IEEE), pp. 5838-5841, IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Brussels, Belgium, 11/07/21. https://doi.org/10.1109/IGARSS47720.2021.9555009

Annual Crop Classification Experiments in Portugal Using Sentinel-2. / Benevides, Pedro; Costa, Hugo; Moreira, Francisco D. et al.
IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium: Proceedings. Institute of Electrical and Electronics Engineers (IEEE), 2021. p. 5838-5841.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Annual Crop Classification Experiments in Portugal Using Sentinel-2

AU - Benevides, Pedro

AU - Costa, Hugo

AU - Moreira, Francisco D.

AU - Moraes, Daniel

AU - Caetano, Mario

N1 - info:eu-repo/grantAgreement/FCT/3599-PPCDT/PCIF%2FSSI%2F0102%2F2017/PT# info:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FAI%2F0100%2F2018/PT# info:eu-repo/grantAgreement/FCT/3599-PPCDT/PCIF%2FMOS%2F0046%2F2017/PT# Benevides, P., Costa, H., Moreira, F. D., Moraes, D., & Caetano, M. (2021). Annual Crop Classification Experiments in Portugal Using Sentinel-2. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium: Proceedings (pp. 5838-5841). IEEE. https://doi.org/10.1109/IGARSS47720.2021.9555009 --------------------------- This work has been supported by projects IPSTERS (DSAIPA/AI/0100/2018), foRESTER (PCIF/SSI/0102/2017), and SCAPEFIRE (PCIF/MOS/0046/2017), and by Centro de Investigação em Gestão de Informação (MagIC), all funded by the Portuguese Foundation for Science and Technology (FCT). Value-added data processed by CNES for the Theia data centre www.theia-land.fr using Copernicus products. The satellite image pre-processing uses algorithms developed by Theia's Scientific Expertise Centers. SIP validation data was kindly provided by Instituto de Financiamento da Agricultura e Pescas.

PY - 2021/7/11

Y1 - 2021/7/11

N2 - This paper presents an experimental crop classification of the 10 most abundant annual crop types in Portugal, using a study area located in Alentejo region. This region has great diversity of land uses as well as multiple crop types. Sentinel-2 2018 intra-annual time-series imagery is considered in the experiment. The Portuguese Land Parcel Identification System (LPIS) is used to extract automatic training samples. LPIS information is automatically processed with the help of auxiliary datasets to filter out crop areas more likely to have been mislabeled. Classification is obtained using random forest. Validation is performed using an independent dataset also based on LPIS. A global accuracy of 76% is obtained. The novelty of the methodology here presented shows that LPIS can be used together with auxiliary data for crop type mapping, helping to characterize the agriculture land diversity in Portugal.

AB - This paper presents an experimental crop classification of the 10 most abundant annual crop types in Portugal, using a study area located in Alentejo region. This region has great diversity of land uses as well as multiple crop types. Sentinel-2 2018 intra-annual time-series imagery is considered in the experiment. The Portuguese Land Parcel Identification System (LPIS) is used to extract automatic training samples. LPIS information is automatically processed with the help of auxiliary datasets to filter out crop areas more likely to have been mislabeled. Classification is obtained using random forest. Validation is performed using an independent dataset also based on LPIS. A global accuracy of 76% is obtained. The novelty of the methodology here presented shows that LPIS can be used together with auxiliary data for crop type mapping, helping to characterize the agriculture land diversity in Portugal.

KW - crop mapping

KW - Portugal

KW - random forest

KW - time-series

KW - Sentinel-2

UR - http://www.scopus.com/inward/record.url?scp=85118698502&partnerID=8YFLogxK

U2 - 10.1109/IGARSS47720.2021.9555009

DO - 10.1109/IGARSS47720.2021.9555009

M3 - Conference contribution

SN - 978-1-6654-0369-6

SP - 5838

EP - 5841

BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium

Y2 - 11 July 2021 through 16 July 2021

ER -

Annual Crop Classification Experiments in Portugal Using Sentinel-2

Abstract

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this