Towards an operational SAR-based rice monitoring system in Asia: Examples from 13 demonstration sites across Asia in the RIICE project

Andrew Nelson, Tri Setiyono, Arnel B. Rala, Emma D. Quicho, Jeny V. Raviz, Prosperidad J. Abonete, Aileen A. Maunahan, Cornelia A. Garcia, Hannah Zarah M. Bhatti, Lorena S. Villano, Pongmanee Thongbai, Francesco Holecz, Massimo Barbieri, Francesco Collivignarelli, Luca Gatti, Eduardo Jimmy P. Quilang, Mary Rose O. Mabalay, Pristine E. Mabalot, Mabel I. Barroga, Alfie P. Bacong & 24 others Norlyn T. Detoito, Glorie Belle Berja, Frenciso Varquez, P. Wahyunto, Dwi Kuntjoro, Sri Retno Murdiyati, Sellaperumal Pazhanivelan, Pandian Kannan, Petchimuthu Christy Nirmala Mary, Elangovan Subramanian, Preesan Rakwatin, Amornrat Intrman, Thana Setapayak, Sommai Lertna, Vo Quang Minh, Vo Quoc Tuan, Trinh Hoang Duong, Nguyen Huu Quyen, Duong Van Kham, Sarith Hin, Touch Veasna, Manoj Yadav, Chharom Chin, Nguyen Hong Ninh

Research output: Contribution to journalArticleAcademicpeer-review

55 Citations (Scopus)

Abstract

Rice is the most important food security crop in Asia. Information on its seasonal extent forms part of the national accounting of many Asian countries. Synthetic Aperture Radar (SAR) imagery is highly suitable for detecting lowland rice, especially in tropical and subtropical regions, where pervasive cloud cover in the rainy seasons precludes the use of optical imagery. Here, we present a simple, robust, rule-based classification for mapping rice area with regularly acquired, multi-temporal, X-band, HH-polarized SAR imagery and site-specific parameters for classification. The rules for rice detection are based on the well-studied temporal signature of rice from SAR backscatter and its relationship with crop stages. We also present a procedure for estimating the parameters based on "temporal feature descriptors" that concisely characterize the key information in the rice signatures in monitored field locations within each site. We demonstrate the robustness of the approach on a very large dataset. A total of 127 images across 13 footprints in six countries in Asia were obtained between October 2012, and April 2014, covering 4.78 m ha. More than 1900 in-season site visits were conducted across 228 monitoring locations in the footprints for classification purposes, and more than 1300 field observations were made for accuracy assessment. Some 1.6 m ha of rice were mapped with classification accuracies from 85% to 95% based on the parameters that were closely related to the observed temporal feature descriptors derived for each site. The 13 sites capture much of the diversity in water management, crop establishment and maturity in South and Southeast Asia. The study demonstrates the feasibility of rice detection at the national scale using multi-temporal SAR imagery with robust classification methods and parameters that are based on the knowledge of the temporal dynamics of the rice crop. We highlight the need for the development of an open-access library of temporal signatures, further investigation into temporal feature descriptors and better ancillary data to reduce the risk of misclassification with surfaces that have temporal backscatter dynamics similar to those of rice. We conclude with observations on the need to define appropriate SAR acquisition plans to support policies and decisions related to food security.

Original languageEnglish
Pages (from-to)10773-10812
Number of pages40
JournalRemote sensing
Volume6
Issue number11
DOIs
Publication statusPublished - 2014
Externally publishedYes

Fingerprint

monitoring system
synthetic aperture radar
rice
radar imagery
crop
food security
footprint
backscatter
project
Asia
accuracy assessment
subtropical region
tropical region
cloud cover
water management
imagery
parameter
monitoring

Keywords

  • Asia
  • COSMO skymed
  • Food security
  • Rice
  • SAR
  • TerraSAR-X

Cite this

Nelson, Andrew ; Setiyono, Tri ; Rala, Arnel B. ; Quicho, Emma D. ; Raviz, Jeny V. ; Abonete, Prosperidad J. ; Maunahan, Aileen A. ; Garcia, Cornelia A. ; Bhatti, Hannah Zarah M. ; Villano, Lorena S. ; Thongbai, Pongmanee ; Holecz, Francesco ; Barbieri, Massimo ; Collivignarelli, Francesco ; Gatti, Luca ; Quilang, Eduardo Jimmy P. ; Mabalay, Mary Rose O. ; Mabalot, Pristine E. ; Barroga, Mabel I. ; Bacong, Alfie P. ; Detoito, Norlyn T. ; Berja, Glorie Belle ; Varquez, Frenciso ; Wahyunto, P. ; Kuntjoro, Dwi ; Murdiyati, Sri Retno ; Pazhanivelan, Sellaperumal ; Kannan, Pandian ; Nirmala Mary, Petchimuthu Christy ; Subramanian, Elangovan ; Rakwatin, Preesan ; Intrman, Amornrat ; Setapayak, Thana ; Lertna, Sommai ; Minh, Vo Quang ; Tuan, Vo Quoc ; Duong, Trinh Hoang ; Quyen, Nguyen Huu ; Van Kham, Duong ; Hin, Sarith ; Veasna, Touch ; Yadav, Manoj ; Chin, Chharom ; Ninh, Nguyen Hong. / Towards an operational SAR-based rice monitoring system in Asia : Examples from 13 demonstration sites across Asia in the RIICE project. In: Remote sensing. 2014 ; Vol. 6, No. 11. pp. 10773-10812.
@article{956a1275256e4167acf462373942a017,
title = "Towards an operational SAR-based rice monitoring system in Asia: Examples from 13 demonstration sites across Asia in the RIICE project",
abstract = "Rice is the most important food security crop in Asia. Information on its seasonal extent forms part of the national accounting of many Asian countries. Synthetic Aperture Radar (SAR) imagery is highly suitable for detecting lowland rice, especially in tropical and subtropical regions, where pervasive cloud cover in the rainy seasons precludes the use of optical imagery. Here, we present a simple, robust, rule-based classification for mapping rice area with regularly acquired, multi-temporal, X-band, HH-polarized SAR imagery and site-specific parameters for classification. The rules for rice detection are based on the well-studied temporal signature of rice from SAR backscatter and its relationship with crop stages. We also present a procedure for estimating the parameters based on {"}temporal feature descriptors{"} that concisely characterize the key information in the rice signatures in monitored field locations within each site. We demonstrate the robustness of the approach on a very large dataset. A total of 127 images across 13 footprints in six countries in Asia were obtained between October 2012, and April 2014, covering 4.78 m ha. More than 1900 in-season site visits were conducted across 228 monitoring locations in the footprints for classification purposes, and more than 1300 field observations were made for accuracy assessment. Some 1.6 m ha of rice were mapped with classification accuracies from 85{\%} to 95{\%} based on the parameters that were closely related to the observed temporal feature descriptors derived for each site. The 13 sites capture much of the diversity in water management, crop establishment and maturity in South and Southeast Asia. The study demonstrates the feasibility of rice detection at the national scale using multi-temporal SAR imagery with robust classification methods and parameters that are based on the knowledge of the temporal dynamics of the rice crop. We highlight the need for the development of an open-access library of temporal signatures, further investigation into temporal feature descriptors and better ancillary data to reduce the risk of misclassification with surfaces that have temporal backscatter dynamics similar to those of rice. We conclude with observations on the need to define appropriate SAR acquisition plans to support policies and decisions related to food security.",
keywords = "Asia, COSMO skymed, Food security, Rice, SAR, TerraSAR-X",
author = "Andrew Nelson and Tri Setiyono and Rala, {Arnel B.} and Quicho, {Emma D.} and Raviz, {Jeny V.} and Abonete, {Prosperidad J.} and Maunahan, {Aileen A.} and Garcia, {Cornelia A.} and Bhatti, {Hannah Zarah M.} and Villano, {Lorena S.} and Pongmanee Thongbai and Francesco Holecz and Massimo Barbieri and Francesco Collivignarelli and Luca Gatti and Quilang, {Eduardo Jimmy P.} and Mabalay, {Mary Rose O.} and Mabalot, {Pristine E.} and Barroga, {Mabel I.} and Bacong, {Alfie P.} and Detoito, {Norlyn T.} and Berja, {Glorie Belle} and Frenciso Varquez and P. Wahyunto and Dwi Kuntjoro and Murdiyati, {Sri Retno} and Sellaperumal Pazhanivelan and Pandian Kannan and {Nirmala Mary}, {Petchimuthu Christy} and Elangovan Subramanian and Preesan Rakwatin and Amornrat Intrman and Thana Setapayak and Sommai Lertna and Minh, {Vo Quang} and Tuan, {Vo Quoc} and Duong, {Trinh Hoang} and Quyen, {Nguyen Huu} and {Van Kham}, Duong and Sarith Hin and Touch Veasna and Manoj Yadav and Chharom Chin and Ninh, {Nguyen Hong}",
year = "2014",
doi = "10.3390/rs61110773",
language = "English",
volume = "6",
pages = "10773--10812",
journal = "Remote sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "11",

}

Nelson, A, Setiyono, T, Rala, AB, Quicho, ED, Raviz, JV, Abonete, PJ, Maunahan, AA, Garcia, CA, Bhatti, HZM, Villano, LS, Thongbai, P, Holecz, F, Barbieri, M, Collivignarelli, F, Gatti, L, Quilang, EJP, Mabalay, MRO, Mabalot, PE, Barroga, MI, Bacong, AP, Detoito, NT, Berja, GB, Varquez, F, Wahyunto, P, Kuntjoro, D, Murdiyati, SR, Pazhanivelan, S, Kannan, P, Nirmala Mary, PC, Subramanian, E, Rakwatin, P, Intrman, A, Setapayak, T, Lertna, S, Minh, VQ, Tuan, VQ, Duong, TH, Quyen, NH, Van Kham, D, Hin, S, Veasna, T, Yadav, M, Chin, C & Ninh, NH 2014, 'Towards an operational SAR-based rice monitoring system in Asia: Examples from 13 demonstration sites across Asia in the RIICE project' Remote sensing, vol. 6, no. 11, pp. 10773-10812. https://doi.org/10.3390/rs61110773

Towards an operational SAR-based rice monitoring system in Asia : Examples from 13 demonstration sites across Asia in the RIICE project. / Nelson, Andrew; Setiyono, Tri; Rala, Arnel B.; Quicho, Emma D.; Raviz, Jeny V.; Abonete, Prosperidad J.; Maunahan, Aileen A.; Garcia, Cornelia A.; Bhatti, Hannah Zarah M.; Villano, Lorena S.; Thongbai, Pongmanee; Holecz, Francesco; Barbieri, Massimo; Collivignarelli, Francesco; Gatti, Luca; Quilang, Eduardo Jimmy P.; Mabalay, Mary Rose O.; Mabalot, Pristine E.; Barroga, Mabel I.; Bacong, Alfie P.; Detoito, Norlyn T.; Berja, Glorie Belle; Varquez, Frenciso; Wahyunto, P.; Kuntjoro, Dwi; Murdiyati, Sri Retno; Pazhanivelan, Sellaperumal; Kannan, Pandian; Nirmala Mary, Petchimuthu Christy; Subramanian, Elangovan; Rakwatin, Preesan; Intrman, Amornrat; Setapayak, Thana; Lertna, Sommai; Minh, Vo Quang; Tuan, Vo Quoc; Duong, Trinh Hoang; Quyen, Nguyen Huu; Van Kham, Duong; Hin, Sarith; Veasna, Touch; Yadav, Manoj; Chin, Chharom; Ninh, Nguyen Hong.

In: Remote sensing, Vol. 6, No. 11, 2014, p. 10773-10812.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Towards an operational SAR-based rice monitoring system in Asia

T2 - Examples from 13 demonstration sites across Asia in the RIICE project

AU - Nelson, Andrew

AU - Setiyono, Tri

AU - Rala, Arnel B.

AU - Quicho, Emma D.

AU - Raviz, Jeny V.

AU - Abonete, Prosperidad J.

AU - Maunahan, Aileen A.

AU - Garcia, Cornelia A.

AU - Bhatti, Hannah Zarah M.

AU - Villano, Lorena S.

AU - Thongbai, Pongmanee

AU - Holecz, Francesco

AU - Barbieri, Massimo

AU - Collivignarelli, Francesco

AU - Gatti, Luca

AU - Quilang, Eduardo Jimmy P.

AU - Mabalay, Mary Rose O.

AU - Mabalot, Pristine E.

AU - Barroga, Mabel I.

AU - Bacong, Alfie P.

AU - Detoito, Norlyn T.

AU - Berja, Glorie Belle

AU - Varquez, Frenciso

AU - Wahyunto, P.

AU - Kuntjoro, Dwi

AU - Murdiyati, Sri Retno

AU - Pazhanivelan, Sellaperumal

AU - Kannan, Pandian

AU - Nirmala Mary, Petchimuthu Christy

AU - Subramanian, Elangovan

AU - Rakwatin, Preesan

AU - Intrman, Amornrat

AU - Setapayak, Thana

AU - Lertna, Sommai

AU - Minh, Vo Quang

AU - Tuan, Vo Quoc

AU - Duong, Trinh Hoang

AU - Quyen, Nguyen Huu

AU - Van Kham, Duong

AU - Hin, Sarith

AU - Veasna, Touch

AU - Yadav, Manoj

AU - Chin, Chharom

AU - Ninh, Nguyen Hong

PY - 2014

Y1 - 2014

N2 - Rice is the most important food security crop in Asia. Information on its seasonal extent forms part of the national accounting of many Asian countries. Synthetic Aperture Radar (SAR) imagery is highly suitable for detecting lowland rice, especially in tropical and subtropical regions, where pervasive cloud cover in the rainy seasons precludes the use of optical imagery. Here, we present a simple, robust, rule-based classification for mapping rice area with regularly acquired, multi-temporal, X-band, HH-polarized SAR imagery and site-specific parameters for classification. The rules for rice detection are based on the well-studied temporal signature of rice from SAR backscatter and its relationship with crop stages. We also present a procedure for estimating the parameters based on "temporal feature descriptors" that concisely characterize the key information in the rice signatures in monitored field locations within each site. We demonstrate the robustness of the approach on a very large dataset. A total of 127 images across 13 footprints in six countries in Asia were obtained between October 2012, and April 2014, covering 4.78 m ha. More than 1900 in-season site visits were conducted across 228 monitoring locations in the footprints for classification purposes, and more than 1300 field observations were made for accuracy assessment. Some 1.6 m ha of rice were mapped with classification accuracies from 85% to 95% based on the parameters that were closely related to the observed temporal feature descriptors derived for each site. The 13 sites capture much of the diversity in water management, crop establishment and maturity in South and Southeast Asia. The study demonstrates the feasibility of rice detection at the national scale using multi-temporal SAR imagery with robust classification methods and parameters that are based on the knowledge of the temporal dynamics of the rice crop. We highlight the need for the development of an open-access library of temporal signatures, further investigation into temporal feature descriptors and better ancillary data to reduce the risk of misclassification with surfaces that have temporal backscatter dynamics similar to those of rice. We conclude with observations on the need to define appropriate SAR acquisition plans to support policies and decisions related to food security.

AB - Rice is the most important food security crop in Asia. Information on its seasonal extent forms part of the national accounting of many Asian countries. Synthetic Aperture Radar (SAR) imagery is highly suitable for detecting lowland rice, especially in tropical and subtropical regions, where pervasive cloud cover in the rainy seasons precludes the use of optical imagery. Here, we present a simple, robust, rule-based classification for mapping rice area with regularly acquired, multi-temporal, X-band, HH-polarized SAR imagery and site-specific parameters for classification. The rules for rice detection are based on the well-studied temporal signature of rice from SAR backscatter and its relationship with crop stages. We also present a procedure for estimating the parameters based on "temporal feature descriptors" that concisely characterize the key information in the rice signatures in monitored field locations within each site. We demonstrate the robustness of the approach on a very large dataset. A total of 127 images across 13 footprints in six countries in Asia were obtained between October 2012, and April 2014, covering 4.78 m ha. More than 1900 in-season site visits were conducted across 228 monitoring locations in the footprints for classification purposes, and more than 1300 field observations were made for accuracy assessment. Some 1.6 m ha of rice were mapped with classification accuracies from 85% to 95% based on the parameters that were closely related to the observed temporal feature descriptors derived for each site. The 13 sites capture much of the diversity in water management, crop establishment and maturity in South and Southeast Asia. The study demonstrates the feasibility of rice detection at the national scale using multi-temporal SAR imagery with robust classification methods and parameters that are based on the knowledge of the temporal dynamics of the rice crop. We highlight the need for the development of an open-access library of temporal signatures, further investigation into temporal feature descriptors and better ancillary data to reduce the risk of misclassification with surfaces that have temporal backscatter dynamics similar to those of rice. We conclude with observations on the need to define appropriate SAR acquisition plans to support policies and decisions related to food security.

KW - Asia

KW - COSMO skymed

KW - Food security

KW - Rice

KW - SAR

KW - TerraSAR-X

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2014/isi/nelson_tow.pdf

U2 - 10.3390/rs61110773

DO - 10.3390/rs61110773

M3 - Article

VL - 6

SP - 10773

EP - 10812

JO - Remote sensing

JF - Remote sensing

SN - 2072-4292

IS - 11

ER -