Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Earth Science

ISSN 2095-0195

ISSN 2095-0209(Online)

CN 11-5982/P

Postal Subscription Code 80-963

2018 Impact Factor: 1.205

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Earth Sci.    2024, Vol. 18 Issue (1) : 30-43    https://doi.org/10.1007/s11707-022-1011-4
Fine classification of rice paddy using multitemporal compact polarimetric SAR C band data based on machine learning methods
Xianyu GUO1, Junjun YIN1, Kun LI2, Jian YANG3, Huimin ZOU4, Fukun YANG4()
1. School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
2. Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
3. Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
4. College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, China
 Download: PDF(9124 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

Rice is an important food crop for human beings. Accurately distinguishing different varieties and sowing methods of rice on a large scale can provide more accurate information for rice growth monitoring, yield estimation, and phenological monitoring, which has significance for the development of modern agriculture. Compact polarimetric (CP) synthetic aperture radar (SAR) provides multichannel information and shows great potential for rice monitoring and mapping. Currently, the use of machine learning methods to build classification models is a controversial topic. In this paper, the advantages of CP SAR data, the powerful learning ability of machine learning, and the important factors of the rice growth cycle were taken into account to achieve high-precision and fine classification of rice paddies. First, CP SAR data were simulated by using the seven temporal RADARSAT-2 C-band data sets. Second, 20-two CP SAR parameters were extracted from each of the seven temporal CP SAR data sets. In addition, we fully considered the change degree of CP SAR parameters on a time scale (ΔCPDoY). Six machine learning methods were employed to carry out the fine classification of rice paddies. The results show that the classification methods of machine learning based on multitemporal CP SAR data can obtain better results in the fine classification of rice paddies by considering the parameters of ΔCPDoY. The overall accuracy is greater than 95.05%, and the Kappa coefficient is greater than 0.937. Among them, the random forest (RF) and support vector machine (SVM) achieve the best results, with an overall accuracy reaching 97.32% and 97.37%, respectively, and Kappa coefficient values reaching 0.965 and 0.966, respectively. For the two types of rice paddies, the average accuracy of the transplant hybrid (T-H) rice paddy is greater than 90.64%, and the highest accuracy is 95.95%. The average accuracy of direct-sown japonica (D-J) rice paddy is greater than 92.57%, and the highest accuracy is 96.13%.
Keywords compact polarimetric (CP) SAR      rice paddy      machine learning      fine classification      multitemporal     
Corresponding Author(s): Fukun YANG   
Online First Date: 12 June 2023    Issue Date: 15 July 2024
 Cite this article:   
Xianyu GUO,Junjun YIN,Kun LI, et al. Fine classification of rice paddy using multitemporal compact polarimetric SAR C band data based on machine learning methods[J]. Front. Earth Sci., 2024, 18(1): 30-43.
 URL:  
https://academic.hep.com.cn/fesci/EN/10.1007/s11707-022-1011-4
https://academic.hep.com.cn/fesci/EN/Y2024/V18/I1/30
Fig.1  Color composite images (CP SAR RR (red), RV (green), RH (blue)) of the backscattering coefficients of simulated CP SAR data in the study area on August 28, 2012.
Fig.2  Image of seven phenological periods of rice growth for the T-H rice paddy in the study area. (a) 2012-6-27 seedling stage; (b) 2012-7-11 tillering stage; (c) 2012-7-21 elongation stage; (d) 2012-8-4 heading stage; (e) 2012-8-28 flowering stage; (f) 2012-9-21 milk stage; (g) 2012-10-15 dough stage.
Number (i) Data acquisition date (D/M/Y) DoY (Day of Year) Image mode Pixel Spacing (A × R, m) Incidence Angle/(° ) Product
1 27 June 2012 179 FQ20W1) 5.2 × 7.6 38–41 SLC2)
2 11 July 2012 193 FQ9W 5.2 × 7.6 27–30 SLC
3 21 July 2012 203 FQ20W 5.2 × 7.6 38–41 SLC
4 4 August 2012 217 FQ9W 5.2 × 7.6 27–30 SLC
5 28 August 2012 241 FQ9W 5.2 × 7.6 27–30 SLC
6 21 September 2012 265 FQ9W 5.2 × 7.6 27–30 SLC
7 15 October 2012 289 FQ9W 5.2 × 7.6 27–30 SLC
Tab.1  Full-polarization SAR data parameters of multitemporal RADARSAT-2
Fig.3  Specific flow chart of the methodology.
Fig.4  Line diagram of ΔCPDoY ((a) ΔRHDoY, (b) ΔRVDoY, (c) ΔRRDoY, and (d) ΔRLDoY) for two types of rice classes on a time scale for four polarization modes (RH, RV, RR, and RL).
Fig.5  Classification results based on six machine learning methods. (a) RF; (b) QDA; (c) MLP; (d) GNB; (e) SVM; (f) DT.
Fig.6  Classification results based on the six machine learning methods in Region 1. (a) RF; (b) QDA; (c) MLP; (d) GNB; (e) SVM; (f) DT.
Fig.7  Same as Fig. 6 but in Region 2. (a) RF; (b) QDA; (c) MLP; (d) GNB; (e) SVM; (f) DT.
Fig.8  Same as Fig. 6 but in Region 3. (a) RF; (b) QDA; (c) MLP; (d) GNB; (e) SVM; (f) DT.
Method Overall Accuracy (OA)/% Kappa T-H D-J Shoal Water Urban
UA/% PA/% UA/% PA/% UA/% PA/% UA/% PA/% UA/% PA/%
RF 97.32 0.9656 98.78 88.83 98.48 93.70 97.05 99.64 92.97 99.45 99.81 100.00
QDA 95.92 0.9476 98.92 92.98 97.49 87.65 85.95 98.57 97.42 98.1 98.34 100.00
MLP 97.15 0.9634 98.12 90.12 97.69 94.56 94.75 99.48 94.52 98.98 99.98 98.70
GNB 96.10 0.9499 98.57 84.39 96.25 92.38 92.61 97.98 94.2 99.01 98.68 99.91
SVM 97.37 0.9662 98.14 90.52 98.74 93.12 95.22 99.92 94.28 99.36 99.99 99.77
DT 95.05 0.9365 95.97 85.30 98.50 88.16 89.26 97.98 90.85 98.80 99.28 99.24
Tab.2  Accuracy table of classification
Study authors Data type OA/% Kappa Classnumbers Rice classes Rice 1 Rice 2 Rice 3
UA3)/% PA4)/% UA/% PA/% UA/% PA/%
Guo et al. (2018) CP SAR 92.57 0.897 5 3 69.57 96.25 88.53 86.39 68.06 45.74
Yang et al. (2014) CP SAR 93.01 0.932 5 2 94.23 90.61 86.38 95.51 – –
Brisco et al. (2013) FP1) SAR – – 2 1 95 – – – – –
Uppala et al. (2021) CP SAR 89.41 0.86 5 1 86.21 89.29 – – – –
Uppala et al. (2015) CP SAR 90 0.856 5 1 96 100 – – – –
Li (2012a) FP SAR 91.45 0.85 4 1 92.3 96.51 – – – –
Wang et al. (2020) DP2) SAR andOptical Sensors 91 0.83 2 2 91 91 92 91 – –
This paper CP SAR 97.37 0.966 5 2 98.14 90.52 98.74 93.12 – –
Tab.3  Accuracy table of rice paddy classification of certain researchers
1 G A, Abubakar K, Wang A, Shahtahamssebi X, Xue M, Belete A J A, Gudo Shuka K A, Mohamed M Gan (2020). Mapping maize fields by using multi-temporal Sentinel-1A and Sentinel-2A images in Makarfi, Northern Nigeria, Africa.Sustainability (Basel), 12(6): 2539
https://doi.org/10.3390/su12062539
2 J Betbeder, S Rapinel, T Corpetti, E Pottier, S Corgne, L Hubert-Moy (2013). Multi-temporal classification of TerraSAR-X data for wetland vegetation mapping. In: Remote Sensing for Agriculture, Ecosystems, and Hydrology XV part of the 20th International Symposium on Remote Sensing, Dresden, Germany, 2013 Sep 23–26
https://doi.org/10.1117/12.2029092
3 A, Bouvet Toan T, Le N Lam-Dao (2009). Monitoring of the rice cropping system in the Mekong Delta using ENVISAT/ASAR dual polarization data.IEEE Trans Geosci Remote Sens, 47(2): 517–526
https://doi.org/10.1109/TGRS.2008.2007963
4 L Breiman (2001). Random forests.Mach Learn, 45(1): 5–32
https://doi.org/10.1023/A:1010933404324
5 M Bressan, J Vitria (2002). Improving naive Bayes using class-conditional ICA. In: Garijo F J, Riquelme J C, Toro M, eds. Advances in Artificial Intelligence - Iberamia 2002
6 B, Brisco K, Li B, Tedford F, Charbonneau S, Yun K Murnaghan (2013). Compact polarimetry assessment for rice and wetland mapping.Int J Remote Sens, 34(6): 1949–1964
https://doi.org/10.1080/01431161.2012.730156
7 H Chen, H Li (2008). Rice recognition using multi-temporal and dual polarized synthetic aperture radar images. In: International Colloquium on Computing, Communication, Control and Management, Guangzhou, China, 2008 Aug 04–05
https://doi.org/10.1109/CCCM.2008.34
8 S R, Cloude D G, Goodenough H Chen (2012). Compact decomposition theory.IEEE Geosci Remote Sens Lett, 9(1): 28–32
https://doi.org/10.1109/LGRS.2011.2158983
9 Castro Filho H C, de Carvalho O A Junior, de de Carvalho O L, Ferreira Bem P P, de Moura R S, de Albuquerque A O, de C R, Silva Ferreira P H, Guimaraes R F, Guimaraes Gomes R A Trancoso (2020). Rice crop detection using LSTM, Bi-LSTM, and machine learning models from Sentinel-1 time series.Remote Sens (Basel), 12(16): 2655
https://doi.org/10.3390/rs12162655
10 P, Dusseux T, Corpetti L, Hubert-Moy S Corgne (2014). Combined use of multi-temporal optical and radar satellite images for grassland monitoring.Remote Sens (Basel), 6(7): 6163–6182
https://doi.org/10.3390/rs6076163
11 M, Gašparović D Dobrinic (2021). Green infrastructure mapping in urban areas using Sentinel-1 imagery.Croat J For Eng, 42(2): 337–356
https://doi.org/10.5552/crojfe.2021.859
12 X, Guo K, Li Z, Wang H, Li Z Yang (2018). Fine classification of rice with multi-temporal compact polarimetric SAR based on SVM + SFS strategy.Remote Sens Land Resour, 30(4): 20
https://doi.org/10.6046/gtzyyg.2018.04.04
13 N S, Harzevili S H Alizadeh (2021). Analysis and modeling conditional mutual dependency of metrics in software defect prediction using latent variables.Neurocomputing, 460: 309–330
https://doi.org/10.1016/j.neucom.2021.05.043
14 K He, X Zhang, S Ren, J ( Sun2015). Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE International Conference on Computer Vision, Santiago, CHILE, 2015 Dec 11–18
https://doi.org/10.1109/ICCV.2015.123
15 T K Ho (1998). The random subspace method for constructing decision forests.IEEE Trans Pattern Anal Mach Intell, 20(8): 832–844
https://doi.org/10.1109/34.709601
16 G B, Huang H, Zhou X, Ding R Zhang (2012). Extreme learning machine for regression and multiclass classification.IEEE Trans Syst Man Cybern B Cybern, 42(2): 513–529
https://doi.org/10.1109/TSMCB.2011.2168604 pmid: 21984515
17 Y, Inoue E Sakaiya (2013). Relationship between X-band backscattering coefficients from high-resolution satellite SAR and biophysical variables in paddy rice.Remote Sens Lett, 4(3): 288–295
https://doi.org/10.1080/2150704X.2012.725482
18 R Kohavi, G H John (1997). Wrappers for feature subset selection. Artif Intell, 97(1–2): 273–324
https://doi.org/10.1016/S0004-3702(97)00043-X
19 C, Kucuk G, Taskin E Erten (2016). Paddy-rice phenology classification based on machine-learning methods using multitemporal Co-Polar X-Band SAR images.IEEE J Sel Top Appl Earth Obs Remote Sens, 9(6): 2509–2519
https://doi.org/10.1109/JSTARS.2016.2547843
20 T, Kurosu M, Fujita K Chiba (1995). Monitoring of rice crop growth from space using the ERS-1 C-Band SAR.IEEE Trans Geosci Remote Sens, 33(4): 1092–1096
https://doi.org/10.1109/36.406698
21 C, Lardeux P L, Frison C, Tison J C, Souyris B, Stoll B, Fruneau J P Rudant (2009). Support vector machine for multifrequency SAR polarimetric data classification.IEEE Trans Geosci Remote Sens, 47(12): 4143–4152
https://doi.org/10.1109/TGRS.2009.2023908
22 C, Lardeux P L, Frison C, Tison J C, Souyris B, Stoll B, Fruneau J P Rudant (2011). Classification of tropical vegetation using multifrequency partial SAR polarimetry.IEEE Geosci Remote Sens Lett, 8(1): 133–137
https://doi.org/10.1109/LGRS.2010.2053836
23 Y, LeCun Y, Bengio G Hinton (2015). Deep learning.Nature, 521(7553): 436–444
https://doi.org/10.1038/nature14539 pmid: 26017442
24 Toan T, Le H, Laur E, Mougin A Lopes (1989). Multitemporal and dual-polarization observations of agricultural vegetation covers by X-Band SAR images.IEEE Trans Geosci Remote Sens, 27(6): 709–718
https://doi.org/10.1109/TGRS.1989.1398243
25 Toan T, Le F, Ribbes L F, Wang N, Floury K H, Ding J A, Kong M, Fujita T Kurosu (1997). Rice crop mapping and monitoring using ERS-1 data based on experiment and modeling results.IEEE Trans Geosci Remote Sens, 35(1): 41–56
https://doi.org/10.1109/36.551933
26 K, Li F, Zhang Y, Shao A, Cai J, Yuan R Touzi (2011). Polarization signature analysis of paddy rice in southern China.Can J Rem Sens, 37(1): 122–135
https://doi.org/10.5589/m11-018
27 K, Li B, Brisco S, Yun R Touzi (2012a). Polarimetric decomposition with RADARSAT-2 for rice mapping and monitoring.Can J Rem Sens, 38(2): 169–179
https://doi.org/10.5589/m12-024
28 W, Li S, Prasad J E, Fowler L M Bruce (2012b). Locality-preserving dimensionality reduction and classification for hyperspectral image analysis.IEEE Trans Geosci Remote Sens, 50(4): 1185–1198
https://doi.org/10.1109/TGRS.2011.2165957
29 E, Ndikumana Tong Minh D, Ho N, Baghdadi D, Courault L Hossard (2018). Deep recurrent neural network for agricultural classification using multitemporal SAR Sentinel-1 for Camargue, France.Remote Sens (Basel), 10(8): 1217
https://doi.org/10.3390/rs10081217
30 A O, Onojeghuo G A, Blackburn Q, Wang P M, Atkinson D, Kindred Y Miao (2018). Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data.Int J Remote Sens, 39(4): 1042–1067
https://doi.org/10.1080/01431161.2017.1395969
31 S, Park J, Im S, Park C, Yoo H, Han J Rhee (2018). Classification and mapping of paddy rice by combining Landsat and SAR time series data.Remote Sens (Basel), 10(3): 447
https://doi.org/10.3390/rs10030447
32 F, Pedregosa G, Varoquaux A, Gramfort V, Michel B, Thirion O, Grisel M, Blondel P, Prettenhofer R, Weiss V, Dubourg J, Vanderplas A, Passos D, Cournapeau M, Brucher M, Perrot E Duchesnay (2011). Scikit-learn: machine learning in python.J Mach Learn Res, 12: 2825
33 A, Pérez P, Larranaga I Inza (2009). Bayesian classifiers based on kernel density estimation: flexible classifiers.Int J Approx Reason, 50(2): 341–362
https://doi.org/10.1016/j.ijar.2008.08.008
34 R K Raney (2006). Dual-polarized SAR and Stokes parameters.IEEE Geosci Remote Sens Lett, 3(3): 317–319
https://doi.org/10.1109/LGRS.2006.871746
35 R K Raney (2007). Hybrid-polarity SAR architecture.IEEE Trans Geosci Remote Sens, 45(11): 3397–3404
https://doi.org/10.1109/TGRS.2007.895883
36 R K, Raney J T S, Cahill G W, Patterson D B J Bussey (2012a). The m-chi decomposition of hybrid dual-polarimetric radar data with application to lunar craters.J Geophys Res, 117(E12): E00H21
https://doi.org/10.1029/2011JE003986
37 R K Raney, J T S Cahill, G W Patterson, D B J ( Bussey2012b). The m-chi decomposition of hybrid dual-polarimetric radar data. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Munich, GERMANY, 2012 Jul 22–27
https://doi.org/10.1109/IGARSS.2012.6352465
38 A K, Ranjan B R Parida (2019). Paddy acreage mapping and yield prediction using sentinel-based optical and SAR data in Sahibganj District, Jharkhand (India).Spatial Inform Res, 27(4): 399–410
https://doi.org/10.1007/s41324-019-00246-4
39 P, Réfrégier J Morio (2006). Shannon entropy of partially polarized and partially coherent light with Gaussian fluctuations.J Opt Soc Am A Opt Image Sci Vis, 23(12): 3036–3044
https://doi.org/10.1364/JOSAA.23.003036 pmid: 17106459
40 J Schlechtriemen, A Wedel, J Hillenbrand, G Breuel, K-D Kuhnert (2014). A lane change detection approach using feature ranking with maximized predictive power. In: IEEE Intelligent Vehicles Symposium (IV), Dearborn, MI, 2014 Jun 08–11
https://doi.org/10.1109/IVS.2014.6856491
41 Y, Shao X T, Fan H, Liu J H, Xiao S, Ross B, Brisco R, Brown G Staples (2001). Rice monitoring and production estimation using multitemporal RADARSAT.Remote Sens Environ, 76(3): 310–325
https://doi.org/10.1016/S0034-4257(00)00212-1
42 J A K, Suykens J Vandewalle (1999). Least squares support vector machine classifiers.Neural Process Lett, 9(3): 293–300
https://doi.org/10.1023/A:1018628609742
43 K R, Thorp D Drajat (2021). Deep machine learning with Sentinel satellite data to map paddy rice production stages across West Java, Indonesia.Remote Sens Environ, 265: 112679
https://doi.org/10.1016/j.rse.2021.112679
44 R, Touzi W M, Boerner J S, Lee E Lueneburg (2004). A review of polarimetry in the context of synthetic aperture radar: concepts and information extraction.Can J Rem Sens, 30(3): 380–407
https://doi.org/10.5589/m04-013
45 M L, Truong-Loi A, Freeman P C, Dubois-Fernandez E Pottier (2009). Estimation of soil moisture and faraday rotation from bare surfaces using compact polarimetry.IEEE Trans Geosci Remote Sens, 47(11): 3608–3615
https://doi.org/10.1109/TGRS.2009.2031428
46 D, Uppala R V, Kothapalli S, Poloju S S V R, Mullapudi V K Dadhwal (2015). Rice crop discrimination using single date RISAT1 hybrid (RH, RV) polarimetric data.Photogramm Eng Remote Sensing, 81(7): 557–563
https://doi.org/10.14358/PERS.81.7.557
47 D, Uppala V, Somepalli R K, Venkata S M V Rama (2021). Identification of optimal single date for rice crop discrimination and relationships between backscatter and biophysical parameters using RISAT-1 hybrid polarimetric SAR data.Geocarto Int, 36(17): 2010–2022
https://doi.org/10.1080/10106049.2019.1687589
48 Beijma S, van A, Comber A Lamb (2014). Random forest classification of salt marsh vegetation habitats using quad-polarimetric airborne SAR, elevation and optical RS data.Remote Sens Environ, 149: 118–129
https://doi.org/10.1016/j.rse.2014.04.010
49 J, Wang K, Li Y, Shao F, Zhang Z, Wang X, Guo Y, Qin X Liu (2020). Analysis of combining SAR and optical optimal parameters to classify typhoon-invasion lodged rice: a case study using the random forest method.Sensors (Basel), 20(24): 7346
https://doi.org/10.3390/s20247346 pmid: 33371381
50 S, Wang R, Gao L Wang (2016). Bayesian network classifiers based on Gaussian kernel density.Expert Syst Appl, 51: 207–217
https://doi.org/10.1016/j.eswa.2015.12.031
51 B, Waske M Braun (2009). Classifier ensembles for land cover mapping using multitemporal SAR imagery.ISPRS J Photogramm Remote Sens, 64(5): 450–457
https://doi.org/10.1016/j.isprsjprs.2009.01.003
52 Z, Yang K, Li L, Liu Y, Shao B, Brisco W Li (2014). Rice growth monitoring using simulated compact polarimetric C band SAR.Radio Sci, 49(12): 1300–1315
https://doi.org/10.1002/2014RS005498
53 J Yin, J Yang (2014). Ship detection by using the m-chi and m-delta decompositions. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Quebec City, Canada, 2014 Jul 13–18
https://doi.org/10.1109/IGARSS.2014.6947042
54 Y, Yu M, Li Y Fu (2018). Forest type identification by random forest classification combined with SPOT and multitemporal SAR data.J For Res, 29(5): 1407–1414
https://doi.org/10.1007/s11676-017-0530-4
55 M Q Zhang (1997). Identification of protein coding regions in the human genome by quadratic discriminant analysis.Proc Natl Acad Sci USA, 94(2): 565–568
https://doi.org/10.1073/pnas.94.2.565 pmid: 9012824
56 X, Zhang J, Xu Y, Chen K, Xu D Wang (2021). Coastal wetland classification with GF-3 polarimetric SAR imagery by using object-oriented random forest algorithm.Sensors (Basel), 21(10): 3395
https://doi.org/10.3390/s21103395 pmid: 34068106
[1] Yanqin TIAN, Chenghai YANG, Wenjiang HUANG, Jia TANG, Xingrong LI, Qing ZHANG. Machine learning-based crop recognition from aerial remote sensing imagery[J]. Front. Earth Sci., 2021, 15(1): 54-69.
[2] Kevin C. Tse, Hon-Chim Chiu, Man-Yin Tsang, Yiliang Li, Edmund Y. Lam. An unsupervised learning approach to study synchroneity of past events in the South China Sea[J]. Front. Earth Sci., 2019, 13(3): 628-640.
[3] Kevin C. TSE, Hon-Chim CHIU, Man-Yin TSANG, Yiliang LI, Edmund Y. LAM. Unsupervised learning on scientific ocean drilling datasets from the South China Sea[J]. Front. Earth Sci., 2019, 13(1): 180-190.
[4] T. PERROU, A. GARIOUD, I. PARCHARIDIS. Use of Sentinel-1 imagery for flood management in a reservoir-regulated river basin[J]. Front. Earth Sci., 2018, 12(3): 506-520.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed