In-season crop classification using elements of the Kennaugh matrix derived from polarimetric RADARSAT-2 SAR data

Abstract Accurate spatio-temporal classification of crops is of prime importance for in-season crop monitoring. Synthetic Aperture Radar (SAR) data provides diverse physical information about crop morphology. In the present work, we propose a day-wise and a time-series approach for crop classification using full-polarimetric SAR data. In this context, the 4 × 4 real Kennaugh matrix representation of a full-polarimetric SAR data is utilized, which can provide valuable information about various morphological and dielectric attributes of a scatterer. The elements of the Kennaugh matrix are used as the parameters for the classification of crop types using the random forest and the extreme gradient boosting classifiers. The time-series approach uses data patterns throughout the whole growth period, while the day-wise approach analyzes the PolSAR data from each acquisition into a single data stack for training and validation. The main advantage of this approach is the possibility of generating an intermediate crop map, whenever a SAR acquisition is available for any particular day. Besides, the day-wise approach has the least climatic influence as compared to the time series approach. However, as time-series data retains the crop growth signature in the entire growth cycle, the classification accuracy is usually higher than the day-wise data. Within the Joint Experiment for Crop Assessment and Monitoring (JECAM) initiative, in situ measurements collected over the Canadian and Indian test sites and C-band full-polarimetric RADARSAT-2 data are used for the training and validation of the classifiers. Besides, the sensitivity of the Kennaugh matrix elements to crop morphology is apparent in this study. The overall classification accuracies of 87.75% and 80.41% are achieved for the time-series data over the Indian and Canadian test sites, respectively. However, for the day-wise data, a ∼6% decrease in the overall accuracy is observed for both the classifiers.

[1]  D. Bargiel,et al.  A new method for crop classification combining time series of radar images and crop phenology information. , 2017 .

[2]  Fernando Vicente-Guijalba,et al.  Polarimetric Response of Rice Fields at C-Band: Analysis and Phenology Retrieval , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Hui Lin,et al.  Monitoring Sugarcane Growth Using ENVISAT ASAR Data , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Hao Jiang,et al.  Early Season Mapping of Sugarcane by Applying Machine Learning Algorithms to Sentinel-1A/2 Time Series Data: A Case Study in Zhanjiang City, China , 2019, Remote. Sens..

[5]  Thomas Jagdhuber,et al.  Scattering Characteristics of X-, C- and L-Band PolSAR Data Examined for the Tundra Environment of the Tuktoyaktuk Peninsula, Canada , 2017 .

[6]  Heather McNairn,et al.  The Contribution of ALOS PALSAR Multipolarization and Polarimetric Data to Crop Classification , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Nataliia Kussul,et al.  Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data , 2017, IEEE Geoscience and Remote Sensing Letters.

[8]  Henning Skriver,et al.  Crop Classification by Multitemporal C- and L-Band Single- and Dual-Polarization and Fully Polarimetric SAR , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Stefan Hinz,et al.  The Kennaugh element framework for multi-scale, multi-polarized, multi-temporal and multi-frequency SAR image preparation , 2015 .

[10]  E. Pottier,et al.  Polarimetric Radar Imaging: From Basics to Applications , 2009 .

[11]  Christopher O. Justice,et al.  No pixel left behind: Toward integrating Earth Observations for agriculture into the United Nations Sustainable Development Goals framework , 2019 .

[12]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[13]  R. J. Brown,et al.  Providing crop information using RADARSAT-1 and satellite optical imagery , 2002 .

[14]  Fabio Del Frate,et al.  Crop classification using multiconfiguration C-band SAR data , 2003, IEEE Trans. Geosci. Remote. Sens..

[15]  Saygin Abdikan,et al.  A Booster Analysis of Extreme Gradient Boosting for Crop Classification using PolSAR Imagery , 2019, 2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics).

[16]  Heather McNairn,et al.  RADARSAT-2 Polarimetric SAR Response to Crop Biomass for Agricultural Production Monitoring , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[17]  S. Cloude.  Polarisation: Applications in Remote Sensing , 2009 .

[18]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[19]  Andreas Schmitt,et al.  Multi-sensor wetland mapping over the Peace Athabasca Delta , 2016 .

[20]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[21]  Johannes R. Sveinsson,et al.  Random Forests for land cover classification , 2006, Pattern Recognit. Lett..

[22]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[23]  Jean Richard Huynen,et al.  Stokes matrix parameters and their interpretation in terms of physical target properties , 1990, Other Conferences.

[24]  J. Kovacs,et al.  Object-oriented crop mapping and monitoring using multi-temporal polarimetric RADARSAT-2 data , 2014 .

[25]  Andreas Schmitt,et al.  Monitoring of the Lac Bam Wetland Extent Using Dual-Polarized X-Band SAR Data , 2016, Remote. Sens..

[26]  Hong Zhang,et al.  A unified framework for crop classification in southern China using fully polarimetric, dual polarimetric, and compact polarimetric SAR data , 2015 .

[27]  Jihua Meng,et al.  Crop classification using multi-configuration SAR data in the North China Plain , 2012 .

[28]  Eric Pottier,et al.  Quantitative comparison of classification capability: fully polarimetric versus dual and single-polarization SAR , 2001, IEEE Trans. Geosci. Remote. Sens..

[29]  Heather McNairn,et al.  TerraSAR-X and RADARSAT-2 for crop classification and acreage estimation , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[30]  Andreas Schmitt,et al.  Wetland Monitoring Using the Curvelet-Based Change Detection Method on Polarimetric SAR Imagery , 2013 .

[31]  Luis Alonso,et al.  A RADARSAT-2 Quad-Polarized Time Series for Monitoring Crop and Soil Conditions in Barrax, Spain , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Eric Pottier,et al.  Introduction to the Polarimetric Target Decomposition Concept , 2017 .

[33]  Rick L. Lawrence,et al.  Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest) , 2006 .