A Novel Phenology Based Feature Subset Selection Technique Using Random Forest for Multitemporal PolSAR Crop Classification

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/80989
Información del item - Informació de l'item - Item information
Title: A Novel Phenology Based Feature Subset Selection Technique Using Random Forest for Multitemporal PolSAR Crop Classification
Authors: Hariharan, Siddharth | Mandal, Dipankar | Tirodkar, Siddhesh | Kumar, Vineet | Bhattacharya, Avik | Lopez-Sanchez, Juan M.
Research Group/s: Señales, Sistemas y Telecomunicación
Center, Department or Service: Universidad de Alicante. Departamento de Física, Ingeniería de Sistemas y Teoría de la Señal
Keywords: Classification | Crop | Feature selection | Multitemporal | Phenology | Polarimetric random forest (RF) | Synthetic aperture radar (SAR)
Knowledge Area: Teoría de la Señal y Comunicaciones
Issue Date: 27-Sep-2018
Publisher: IEEE
Citation: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2018, 11(11): 4244-4258. doi:10.1109/JSTARS.2018.2866407
Abstract: Feature selection techniques intent to select a subset of features that minimizes redundancy and maximizes relevancy for classification problems in machine learning. Standard methods for feature selection in machine learning seldom take into account the domain knowledge associated with the data. Multitemporal crop classification studies with full-polarimetric synthetic aperture radar (PolSAR) data ought to consider the changes in the scattering mechanisms with their phenological growth stages. Hence, it is desirable to incorporate these changes while determining a feature subset for classification. In this study, a random forest (RF) based feature selection technique is proposed that takes into account the changes in the physical scattering mechanism with crop phenological stages for multitemporal PolSAR classification. The partial probability plot, which is an attribute of RF, provides information about the marginal effect of a polarimetric parameter on the desired crop class. Moreover, it is used to identify the specific range of a parameter where the probability of the presence of a particular crop class is high. The proposed technique identifies features that change significantly with crop phenology. The selected features are the ones whose ranges show maximum separation amongst crop classes. Additionally, the feature subset is refined by eliminating correlated features. The E-SAR L-band dataset of the AgriSAR-2006 campaign over the Demmin test site in Germany is used in this study. The classification accuracy using the novel feature selection technique is 99.12%. This is nominally better than using the features obtained from a standard feature selection method used in RF, such as mean decrease Gini (98.73%) and mean decrease accuracy (98.68%) that do not take into account the information based on crop phenology.
Sponsor: This work was supported in part by the Spanish Ministry of Economy, Industry and Competitiveness, in part by the State Agency of Research (AEI), and in part by the European Funds for Regional Development under Projects TIN2014-55413-C2-2-P and TEC2017-85244-C2-1-P.
URI: http://hdl.handle.net/10045/80989
ISSN: 1939-1404 (Print) | 2151-1535 (Online)
DOI: 10.1109/JSTARS.2018.2866407
Language: eng
Type: info:eu-repo/semantics/article
Rights: © 2018 IEEE
Peer Review: si
Publisher version: https://doi.org/10.1109/JSTARS.2018.2866407
Appears in Collections:INV - SST - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2018_Hariharan_etal_IEEE-JSTARS_preprint.pdfPreprint (acceso abierto)6,08 MBAdobe PDFOpen Preview
Thumbnail2018_Hariharan_etal_IEEE-JSTARS_final.pdfVersión final (acceso restringido)5,69 MBAdobe PDFOpen    Request a copy

Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.