Aarhus University Seal / Aarhus Universitets segl

Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data

Publikation: Bidrag til bog/antologi/rapport/proceedingKonferencebidrag i proceedingsForskningpeer review

Standard

Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data. / Jeppesen, Jacob Hoxbroe; Jacobsen, Rune Hylsberg; Jorgensen, Rasmus Nyholm.

2020 23rd Euromicro Conference on Digital System Design (DSD). red. / Andrej Trost; Andrej Zemva; Amund Skavhaug. Kranj : IEEE, 2020. s. 557-564.

Publikation: Bidrag til bog/antologi/rapport/proceedingKonferencebidrag i proceedingsForskningpeer review

Harvard

Jeppesen, JH, Jacobsen, RH & Jorgensen, RN 2020, Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data. i A Trost, A Zemva & A Skavhaug (red), 2020 23rd Euromicro Conference on Digital System Design (DSD). IEEE, Kranj, s. 557-564, 23rd Euromicro Conference on Digital System Design, DSD 2020, Kranj, Slovenien, 26/08/2020. https://doi.org/10.1109/DSD51259.2020.00092

APA

Jeppesen, J. H., Jacobsen, R. H., & Jorgensen, R. N. (2020). Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data. I A. Trost, A. Zemva, & A. Skavhaug (red.), 2020 23rd Euromicro Conference on Digital System Design (DSD) (s. 557-564). IEEE. https://doi.org/10.1109/DSD51259.2020.00092

CBE

Jeppesen JH, Jacobsen RH, Jorgensen RN. 2020. Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data. Trost A, Zemva A, Skavhaug A, red. I 2020 23rd Euromicro Conference on Digital System Design (DSD). Kranj: IEEE. s. 557-564. https://doi.org/10.1109/DSD51259.2020.00092

MLA

Jeppesen, Jacob Hoxbroe, Rune Hylsberg Jacobsen og Rasmus Nyholm Jorgensen "Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data"., Trost, Andrej Zemva, Andrej Skavhaug, Amund (red.). 2020 23rd Euromicro Conference on Digital System Design (DSD). Kranj: IEEE. 2020, 557-564. https://doi.org/10.1109/DSD51259.2020.00092

Vancouver

Jeppesen JH, Jacobsen RH, Jorgensen RN. Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data. I Trost A, Zemva A, Skavhaug A, red., 2020 23rd Euromicro Conference on Digital System Design (DSD). Kranj: IEEE. 2020. s. 557-564 https://doi.org/10.1109/DSD51259.2020.00092

Author

Jeppesen, Jacob Hoxbroe ; Jacobsen, Rune Hylsberg ; Jorgensen, Rasmus Nyholm. / Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data. 2020 23rd Euromicro Conference on Digital System Design (DSD). red. / Andrej Trost ; Andrej Zemva ; Amund Skavhaug. Kranj : IEEE, 2020. s. 557-564

Bibtex

@inproceedings{1af0a223a5784afead32929b6cc08a15,
title = "Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data",
abstract = "The amount of open satellite data has increased tremendously in recent years, simultaneously with a continuing decrease in the price of high performance cloud computing. This can be combined with machine learning methods to perform crop type classification in the agricultural sector. In this paper, we propose a data processing chain for processing multitemporal Sentinel-1 SAR data, and show how the temporal patterns of agricultural fields can be visualized to provide a valuable overview prior to classification. We then investigate the performance of 6 machine learning methods for crop type classification of 12 crop types based on 44333 fields, and achieve an overall accuracy of (94.02 ± 0.25)% with an RBF SVM classifier. The dataset used is a subset of all the fields of the chosen crop types in Denmark in 2019, which comprises a total of 289810, or 49.34% of all fields in the country for the 2019 season. The entire data processing chain is based on open data and free open source software, thereby minimizing the cost of practical applications and future work for both industry and academia. All code used for the paper is available on GitHub.",
keywords = "crop type classification, geospatial data analytics, machine learning, precision agriculture, Satellite radar data",
author = "Jeppesen, {Jacob Hoxbroe} and Jacobsen, {Rune Hylsberg} and Jorgensen, {Rasmus Nyholm}",
year = "2020",
month = aug,
doi = "10.1109/DSD51259.2020.00092",
language = "English",
isbn = "978-1-7281-9536-0",
pages = "557--564",
editor = "Andrej Trost and Andrej Zemva and Amund Skavhaug",
booktitle = "2020 23rd Euromicro Conference on Digital System Design (DSD)",
publisher = "IEEE",
note = "23rd Euromicro Conference on Digital System Design, DSD 2020 ; Conference date: 26-08-2020 Through 28-08-2020",

}

RIS

TY - GEN

T1 - Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data

AU - Jeppesen, Jacob Hoxbroe

AU - Jacobsen, Rune Hylsberg

AU - Jorgensen, Rasmus Nyholm

PY - 2020/8

Y1 - 2020/8

N2 - The amount of open satellite data has increased tremendously in recent years, simultaneously with a continuing decrease in the price of high performance cloud computing. This can be combined with machine learning methods to perform crop type classification in the agricultural sector. In this paper, we propose a data processing chain for processing multitemporal Sentinel-1 SAR data, and show how the temporal patterns of agricultural fields can be visualized to provide a valuable overview prior to classification. We then investigate the performance of 6 machine learning methods for crop type classification of 12 crop types based on 44333 fields, and achieve an overall accuracy of (94.02 ± 0.25)% with an RBF SVM classifier. The dataset used is a subset of all the fields of the chosen crop types in Denmark in 2019, which comprises a total of 289810, or 49.34% of all fields in the country for the 2019 season. The entire data processing chain is based on open data and free open source software, thereby minimizing the cost of practical applications and future work for both industry and academia. All code used for the paper is available on GitHub.

AB - The amount of open satellite data has increased tremendously in recent years, simultaneously with a continuing decrease in the price of high performance cloud computing. This can be combined with machine learning methods to perform crop type classification in the agricultural sector. In this paper, we propose a data processing chain for processing multitemporal Sentinel-1 SAR data, and show how the temporal patterns of agricultural fields can be visualized to provide a valuable overview prior to classification. We then investigate the performance of 6 machine learning methods for crop type classification of 12 crop types based on 44333 fields, and achieve an overall accuracy of (94.02 ± 0.25)% with an RBF SVM classifier. The dataset used is a subset of all the fields of the chosen crop types in Denmark in 2019, which comprises a total of 289810, or 49.34% of all fields in the country for the 2019 season. The entire data processing chain is based on open data and free open source software, thereby minimizing the cost of practical applications and future work for both industry and academia. All code used for the paper is available on GitHub.

KW - crop type classification

KW - geospatial data analytics

KW - machine learning

KW - precision agriculture

KW - Satellite radar data

UR - http://www.scopus.com/inward/record.url?scp=85096356106&partnerID=8YFLogxK

U2 - 10.1109/DSD51259.2020.00092

DO - 10.1109/DSD51259.2020.00092

M3 - Article in proceedings

AN - SCOPUS:85096356106

SN - 978-1-7281-9536-0

SP - 557

EP - 564

BT - 2020 23rd Euromicro Conference on Digital System Design (DSD)

A2 - Trost, Andrej

A2 - Zemva, Andrej

A2 - Skavhaug, Amund

PB - IEEE

CY - Kranj

T2 - 23rd Euromicro Conference on Digital System Design, DSD 2020

Y2 - 26 August 2020 through 28 August 2020

ER -