Abstract

High temporal resolution of synthetic aperture radar (SAR) imagery (e.g., Sentinel-1 (S1) imagery) creates new possibilities for monitoring green vegetation in urban areas and generating land-cover classification (LCC) maps. This research evaluates how different pre-processing steps of SAR imagery affect classification accuracy. Machine learning (ML) methods were applied in three different study areas: random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB). Since the presence of the speckle noise in radar imagery is inevitable, different adaptive filters were examined. Using the backscattering values of the S1 imagery, the SVM classifier achieved a mean overall accuracy (OA) of 63.14%, and a Kappa coefficient (Kappa) of 0.50. Using the SVM classifier with a Lee filter with a window size of 5×5 (Lee5) for speckle reduction, mean values of 73.86% and 0.64 for OA and Kappa were achieved, respectively. An additional increase in the LCC was obtained with texture features calculated from a grey-level co-occurrence matrix (GLCM). The highest classification accuracy obtained for the extracted GLCM texture features using the SVM classifier, and Lee5 filter was 78.32% and 0.69 for the mean OA and Kappa values, respectively. This study improved LCC with an evaluation of various radiometric and texture features and confirmed the ability to apply an SVM classifier. For the supervised classification, the SVM method outperformed the RF and XGB methods, although the highest computational time was needed for the SVM, whereas XGB performed the fastest. These results suggest pre-processing steps of the SAR imagery for green infrastructure mapping in urban areas. Future research should address the use of multitemporal SAR data along with the pre-processing steps and ML algorithms described in this research.

Highlights

  • Forests are the most widely distributed terrestrial vegetation type, and play an important role in ecology and shaping the dynamics of regional and global ecosystem processes (Wulder 1998)

  • Classifications were computed for a radiometric classification on backscatter values (VV, VH); a radiometric classification on speckled VV, VH polarisations with different adaptive filters (SPK); and an integrated radiometric and texture feature classification with speckle noise filtering (SPK) polarisations (GLCM)

  • In the SPK classification in Zagreb, Hannover and Porto, the highest accuracy was achieved with the Lee5 filter with overall accuracy (OA) of 77.04%, 72.17% and 72.36% and using the support vector machine (SVM) classifier, respectively

Read more

Summary

Introduction

Forests are the most widely distributed terrestrial vegetation type, and play an important role in ecology and shaping the dynamics of regional and global ecosystem processes (Wulder 1998). The monitoring of green urban areas using remote sensing (RS) techniques can be used as a tool for integrated spatial planning (Gašparović and Dobrinić 2020). Using satellite imagery, urban areas with different characteristics and densities can be determined (Zhang et al 2014). Benefits of green infrastructure (GI) in ­urban environments, such as mitigation of heat island effects and flood alleviation, are burdened by severe anthropogenic impacts that can diminish. The European Commission adopted the European Green Infrastructure Strategy, which aims to address the increasing fragmented nature of Europe urban areas as a result of human activities. Optical satellite imagery is historically mostly used for monitoring the urban forest areas. As a result of easier interpretation and pre-processing methods, optical data is usually preferred to synthetic aperture radar (SAR) data.

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call