Home > Research > Publications & Outputs > Mapping paddy rice fields by applying machine l...

Electronic data

  • Author accepted manuscript

    Rights statement: This is an Accepted Manuscript of an article published by Taylor & Francis in International Journal of Remote Sensing on 02/11/2017, available online: http://www.tandfonline.com/10.1080/01431161.2017.1395969

    Accepted author manuscript, 2.18 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data. / Onojeghuo, Alex Okiemute; Blackburn, George Alan; Wang, Qunming et al.
In: International Journal of Remote Sensing, Vol. 39, No. 4, 2018, p. 1042-1067.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Onojeghuo AO, Blackburn GA, Wang Q, Atkinson PM, Kindred D, Miao Y. Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data. International Journal of Remote Sensing. 2018;39(4):1042-1067. Epub 2017 Nov 2. doi: 10.1080/01431161.2017.1395969

Author

Bibtex

@article{04d67424b8a64843b497674148159ce3,
title = "Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data",
abstract = "Sentinel-1A synthetic aperture radar (SAR) data present an opportunity for acquiring crop information without restrictions caused by weather and illumination conditions, at a spatial resolution appropriate for individual rice fields and a temporal resolution sufficient to capture the growth profiles of different crop species. This study investigated the use of multi-temporal Sentinel-1A SAR data and Landsat-derived normalized difference vegetation index (NDVI) data to map the spatial distribution of paddy rice fields across parts of the Sanjiang plain, in northeast China. The satellite sensor data were acquired throughout the rice crop-growing season (May–October). A co-registered set of 10 dual polarization (VH/VV) SAR and NDVI images depicting crop phenological development were used as inputs to Support Vector Machine (SVM) and Random Forest (RF) machine learning classification algorithms in order to map paddy rice fields. The results showed a significant increase in overall classification when the NDVI time-series data were integrated with the various combinations of multi-temporal polarization channels (i.e. VH, VV, and VH/VV). The highest classification accuracies overall (95.2%) and for paddy rice (96.7%) were generated using the RF algorithm applied to combined multi-temporal VH polarization and NDVI data. The SVM classifier was most effective when applied to the dual polarization (i.e. VH and VV) SAR data alone and this generated overall and paddy rice classification accuracies of 91.6% and 82.5%, respectively. The results demonstrate the practicality of implementing RF or SVM machine learning algorithms to produce 10 m spatial resolution maps of paddy rice fields with limited ground data using a combination of multi-temporal SAR and NDVI data, where available, or SAR data alone. The methodological framework developed in this study is apposite for large-scale implementation across China and other major rice-growing regions of the world.",
author = "Onojeghuo, {Alex Okiemute} and Blackburn, {George Alan} and Qunming Wang and Atkinson, {Peter Michael} and Daniel Kindred and Yuxin Miao",
note = "This is an Accepted Manuscript of an article published by Taylor & Francis in International Journal of Remote Sensing on 02/11/2017, available online: http://www.tandfonline.com/10.1080/01431161.2017.1395969",
year = "2018",
doi = "10.1080/01431161.2017.1395969",
language = "English",
volume = "39",
pages = "1042--1067",
journal = "International Journal of Remote Sensing",
issn = "0143-1161",
publisher = "TAYLOR & FRANCIS LTD",
number = "4",

}

RIS

TY - JOUR

T1 - Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data

AU - Onojeghuo, Alex Okiemute

AU - Blackburn, George Alan

AU - Wang, Qunming

AU - Atkinson, Peter Michael

AU - Kindred, Daniel

AU - Miao, Yuxin

N1 - This is an Accepted Manuscript of an article published by Taylor & Francis in International Journal of Remote Sensing on 02/11/2017, available online: http://www.tandfonline.com/10.1080/01431161.2017.1395969

PY - 2018

Y1 - 2018

N2 - Sentinel-1A synthetic aperture radar (SAR) data present an opportunity for acquiring crop information without restrictions caused by weather and illumination conditions, at a spatial resolution appropriate for individual rice fields and a temporal resolution sufficient to capture the growth profiles of different crop species. This study investigated the use of multi-temporal Sentinel-1A SAR data and Landsat-derived normalized difference vegetation index (NDVI) data to map the spatial distribution of paddy rice fields across parts of the Sanjiang plain, in northeast China. The satellite sensor data were acquired throughout the rice crop-growing season (May–October). A co-registered set of 10 dual polarization (VH/VV) SAR and NDVI images depicting crop phenological development were used as inputs to Support Vector Machine (SVM) and Random Forest (RF) machine learning classification algorithms in order to map paddy rice fields. The results showed a significant increase in overall classification when the NDVI time-series data were integrated with the various combinations of multi-temporal polarization channels (i.e. VH, VV, and VH/VV). The highest classification accuracies overall (95.2%) and for paddy rice (96.7%) were generated using the RF algorithm applied to combined multi-temporal VH polarization and NDVI data. The SVM classifier was most effective when applied to the dual polarization (i.e. VH and VV) SAR data alone and this generated overall and paddy rice classification accuracies of 91.6% and 82.5%, respectively. The results demonstrate the practicality of implementing RF or SVM machine learning algorithms to produce 10 m spatial resolution maps of paddy rice fields with limited ground data using a combination of multi-temporal SAR and NDVI data, where available, or SAR data alone. The methodological framework developed in this study is apposite for large-scale implementation across China and other major rice-growing regions of the world.

AB - Sentinel-1A synthetic aperture radar (SAR) data present an opportunity for acquiring crop information without restrictions caused by weather and illumination conditions, at a spatial resolution appropriate for individual rice fields and a temporal resolution sufficient to capture the growth profiles of different crop species. This study investigated the use of multi-temporal Sentinel-1A SAR data and Landsat-derived normalized difference vegetation index (NDVI) data to map the spatial distribution of paddy rice fields across parts of the Sanjiang plain, in northeast China. The satellite sensor data were acquired throughout the rice crop-growing season (May–October). A co-registered set of 10 dual polarization (VH/VV) SAR and NDVI images depicting crop phenological development were used as inputs to Support Vector Machine (SVM) and Random Forest (RF) machine learning classification algorithms in order to map paddy rice fields. The results showed a significant increase in overall classification when the NDVI time-series data were integrated with the various combinations of multi-temporal polarization channels (i.e. VH, VV, and VH/VV). The highest classification accuracies overall (95.2%) and for paddy rice (96.7%) were generated using the RF algorithm applied to combined multi-temporal VH polarization and NDVI data. The SVM classifier was most effective when applied to the dual polarization (i.e. VH and VV) SAR data alone and this generated overall and paddy rice classification accuracies of 91.6% and 82.5%, respectively. The results demonstrate the practicality of implementing RF or SVM machine learning algorithms to produce 10 m spatial resolution maps of paddy rice fields with limited ground data using a combination of multi-temporal SAR and NDVI data, where available, or SAR data alone. The methodological framework developed in this study is apposite for large-scale implementation across China and other major rice-growing regions of the world.

U2 - 10.1080/01431161.2017.1395969

DO - 10.1080/01431161.2017.1395969

M3 - Journal article

VL - 39

SP - 1042

EP - 1067

JO - International Journal of Remote Sensing

JF - International Journal of Remote Sensing

SN - 0143-1161

IS - 4

ER -