Abstract
Rice has been the most important agricultural commodity in Asia. Various monitoring schemes based on remotely sensed data have been dedicated for rice research purposes, and responsible agencies currently seek an efficient, operational paddy field monitoring. Multispectral datasets serve as the backbone to the application; nonetheless, their successful implementation in tropical regions is somewhat fluctuating due to persistent cloud cover. Options in the use of synthetic-aperture radar (SAR) data are currently available, from X-, C-, or L-band spaceborne systems. The latter is preferable as long wavelength is less susceptible to the attenuation of high precipitation often seen in tropical regions. In this chapter, hybrid polarization as one of the emerging SAR techniques is investigated to retrieve waterlogged rice fields as a proxy for the commencement of a new planting season. Two popular hybrid polarimetric representations, i.e., modulus of covariance matrix and polarimetric features of Raney decompositions, are discussed. Information extraction was done using 11 supervised learners. The findings indicated that modulus of covariance matrix generally performed inferior than Raney decomposition datasets. The latter amplified the overall accuracy to around 95%, with about 20% discrepancy to the covariance matrix. Although modern data mining methods including random forests and support vector machines were preferable than conventional methods such as single tree approach, this research indicated that some variants of random forests and support vector machines may yield overall accuracy below the expectation. The research also discovered that Raney decomposition features outweighed fully polarimetric backscatter coefficients, although the difference is considerably low (about 5%). Hence, it could be summarized that hybrid polarimetry may provide an efficacious solution to large-scale monitoring of active rice fields.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ainsworth TL, Ferro-Famil L, Lee J-S (2006) Orientation angle preserving a posteriori polarimetric SAR calibration. IEEE Trans Geosci Remote Sens 44(4):994–1003. https://doi.org/10.1109/TGRS.2005.862508
Amani M, Salehi B, Mahdavi S, Granger J, Brisco B (2017) Wetland classification in Newfoundland and Labrador using multi-source SAR and optical data integration. GISci Remote Sens 54(6):779–796. https://doi.org/10.1080/15481603.2017.1331510
Attarchi S, Gloaguen R (2014) Classifying complex mountainous forests with L-band SAR and landsat data integration: a comparison among different machine learning methods in the Hyrcanian forest. Remote Sens 6(5):3624–3647. https://doi.org/10.3390/rs6053624
Bickel SH, Bates RHT (1965) Effects of magneto-ionic propagation on the polarization scattering matrix. Proc IEEE 53(8):1089–1091. https://doi.org/10.1109/PROC.1965.4097
Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Chapman and Hall/CRC, Boca Raton
Chan JCW, Beckers P, Spanhove T, Borre JV (2012) An evaluation of ensemble classifiers for mapping Natura 2000 heathland in Belgium using spaceborne angular hyperspectral (CHRIS/Proba) imagery. Int J Appl Earth Obs Geoinf 18(1):13–22. https://doi.org/10.1016/j.jag.2012.01.002
Charbonneau FJ, Brisco B, Raney RK, McNairn H, Liu C, Vachon PW, Shang J, De Abreu R, Champagne C, Merzouki A, Geldsetzer T (2010) Compact polarimetry overview and applications assessment. Can J Remote Sens 36(SUPPL. 2):S298–S315
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. Paper presented at the Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, San Francisco, California, USA
Chen H, Goodenough DG, Cloude SR (2014) Mapping forest fire scars with simulated RCM compact-pol data:1572–1575. https://doi.org/10.1109/IGARSS.2014.6946740
Cloude SR (2009) Dual versus quadpol: a new test statistic for radar polarimetry. In: Polinsar 2009, Frascati, Italy, 26–30 Jan 2009
Friedman JH (1991) Multivariate adaptive regression splines. Ann Stat 19(1):1–141
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232. https://doi.org/10.2307/2699986
Haldar D, Patnaik C (2010) Synergistic use of multi-temporal Radarsat SAR and AWiFS data for Rabi rice identification. J Indian Soc Remote Sens 38(1):153–160. https://doi.org/10.1007/s12524-010-0006-x
Kontgis C, Schneider A, Ozdogan M (2015) Mapping rice paddy extent and intensification in the Vietnamese Mekong River Delta with dense time stacks of Landsat data. Remote Sens Environ 169:255–269. https://doi.org/10.1016/j.rse.2015.08.004
Kumar V, Kumari M, Saha SK (2016) Discrimination of basmati and non-basmati rice types using polarimetric target decomposition of temporal SAR data. Curr Sci 110(11):2166–2169. https://doi.org/10.18520/cs/v110/i11/2166-2169
Lardeux C, Niamen D, Routier JB, Giraud A, Frison PL, Pottier E, Rudant JP (2010) Use of PalSAR polarimetric data for tropical forest stratification and comparison of simulated dual and compact polarimetric modes. Paper presented at the international geoscience and remote sensing symposium (IGARSS)
Lee JS, Grunes MR, Pottier E (2001) Quantitative comparison of classification capability: fully polarimetric versus dual and single-polarization SAR. IEEE Trans Geosci Remote Sens 39(11):2343–2351. https://doi.org/10.1109/36.964970
Lopez-Sanchez JM, Vicente-Guijalba F, Ballester-Berman JD, Cloude SR (2014) Polarimetric response of rice fields at C-band: analysis and phenology retrieval. IEEE Trans Geosci Remote Sens 52(5):2977–2993. https://doi.org/10.1109/TGRS.2013.2268319
McNairn H, Homayouni S, Hosseini M, Powers J, Beckett K, Parkinson W (2017) Compact polarimetric synthetic aperture radar for monitoring crop condition. Paper presented at the international geoscience and remote sensing symposium (IGARSS)
Ouchi K, Wang H, Ishitsuka N, Saito G, Mohri K (2006) On the Bragg scattering observed in L-band synthetic aperture radar images of flooded rice fields. IEICE Trans Commun E89-B(8):2218–2225. https://doi.org/10.1093/ietcom/e89-b.8.2218
Panigrahy S, Manjunath KR, Chakraborty M, Kundu N, Parihar JS (1999) Evaluation of RADARSAT standard beam data for identification of potato and rice crops in India. ISPRS J Photogramm Remote Sens 54(4):254–262. https://doi.org/10.1016/S0924-2716(99)00020-9
Park S, Im J (2016) Classification of croplands through fusion of optical and sar time series data. Paper presented at the international archives of the photogrammetry, remote sensing and spatial information sciences – ISPRS archives
Pei Z, Zhang S, Guo L, Mc Nairn H, Shang J, Jiao X (2011) Rice identification and change detection using TerraSAR-X data. Can J Remote Sens 37(1):151–156. https://doi.org/10.5589/m11-025
Raney RK, Cahill JTS, Patterson GW, Bussey DBJ (2012) The m-chi decomposition of hybrid dual-polarimetric radar data with application to lunar craters. Journal of Geophysical Research: Planets 117(E12):n/a–n/a. https://doi.org/10.1029/2011JE003986
Rodriguez JJ, Kuncheva LI (2006) Rotation forest: a new classifier ensemble method. IEEE Trans Pattern Anal Mach Intell 28:1619–1630. https://doi.org/10.1109/TPAMI.2006.211
Shi W, Zheng S, Tian Y (2009) Adaptive mapped least squares SVM-based smooth fitting method for DSM generation of LIDAR data. Int J Remote Sens 30(21):5669–5683. https://doi.org/10.1080/01431160802709237
Singh G, Yamaguchi Y, Park SE, Boerner WM, Cui Y, Venkataraman G (2014) Categorization of the glaciated terrain of Indian Himalaya using CP and FP mode SAR. IEEE J Sel Top Appl Earth Obs Remote Sens 7(3):846–854. https://doi.org/10.1109/JSTARS.2013.2266354
Siyal AA, Dempewolf J, Becker-Reshef I (2015) Rice yield estimation using Landsat ETM+ data. J Appl Remote Sens 9(1). https://doi.org/10.1117/1.JRS.9.095986
Souyris JC, Imbo P, Fjørtoft R, Mingot S, Lee JS (2005) Compact polarimetry based on symmetry properties of geophysical media: the π/4 mode. IEEE Trans Geosci Remote Sens 43(3):634–645. https://doi.org/10.1109/TGRS.2004.842486
Suykens JAK, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Process Lett 9(3):293–300. https://doi.org/10.1023/A:1018628609742
Trisasongko BH (2015) Potential use of hybrid synthetic aperture radar polarimetry in earth surface monitoring. AIP Conf Proc 1677:060013. https://doi.org/10.1063/1.4930693
Trisasongko BH, Panuju DR, Paull DJ, Jia X, Griffin AL (2017) Comparing six pixel-wise classifiers for tropical rural land cover mapping using four forms of fully polarimetric SAR data. Int J Remote Sens 38(11):3274–3293. https://doi.org/10.1080/01431161.2017.1292072
Turkar V, De S, Rao YS, Shitole S, Bhattacharya A, Das A (2013) Comparative analysis of classification accuracy for RISAT-1 compact polarimetric data for various land-covers. Paper presented at the international geoscience and remote sensing symposium (IGARSS)
Vapnik VN (2000) The nature of statistical learning theory, 2nd edn. Springer Verlag, New York
White L, Landon A, Dabboor M, Pratt A, Brisco B (2014) Mapping and monitoring flooded vegetation and soil moisture using simulated compact polarimetry. 1568–1571. https://doi.org/10.1109/IGARSS.2014.6946739
White L, Millard K, Banks S, Richardson M, Pasher J, Duffe J (2017) Moving to the RADARSAT constellation mission: comparing synthesized compact polarimetry and dual polarimetry data with fully polarimetric RADARSAT-2 data for image classification of peatlands. Remote Sens 9(6). https://doi.org/10.3390/rs9060573
Wright PA, Quegan S, Wheadon NS, Hall CD (2003) Faraday rotation effects on L-band spaceborne SAR data. IEEE Trans Geosci Remote Sens 41(12 PART I):2735–2744. https://doi.org/10.1109/TGRS.2003.815399
Wu F, Wang C, Zhang H, Zhang B, Tang Y (2011) Rice crop monitoring in South China with RADARSAT-2 quad-polarization SAR data. IEEE Geosci Remote Sens Lett 8(2):196–200. https://doi.org/10.1109/LGRS.2010.2055830
Xu B, Huang JZ, Williams G, Wang Q, Ye Y (2012) Classifying very high-dimensional data with random forests built from small subspaces. Int J Data Warehousing Min 8(2):44–63. https://doi.org/10.4018/jdwm.2012040103
Yousefi S, Khatami R, Mountrakis G, Mirzaee S, Pourghasemi HR, Tazeh M (2015) Accuracy assessment of land cover/land use classifiers in dry and humid areas of Iran. Environ Monit Assess 187(10). https://doi.org/10.1007/s10661-015-4847-1
Acknowledgment
The author would like to thank Japan Aerospace Exploration Agency (JAXA) for data provision through RA6-3004 project. Partial funding was obtained from UNSW Australia through UIPA scholarship. Fieldworks were assisted by Dyah R. Panuju, Annisa P. Trisasongko, and Rizqi I. Sholihah; their contributions to this work, therefore, are greatly acknowledged. Finally, the author expresses his gratitude to Dr. David Paull of UNSW Canberra for his encouragement and support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Trisasongko, B.H. (2019). Hybrid Polarimetric Synthetic Aperture Radar for the Detection of Waterlogged Rice Fields. In: Kumar, P., Rani, M., Chandra Pandey , P., Sajjad, H., Chaudhary, B. (eds) Applications and Challenges of Geospatial Technology. Springer, Cham. https://doi.org/10.1007/978-3-319-99882-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-99882-4_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-99881-7
Online ISBN: 978-3-319-99882-4
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)