Polarimetric SAR Time-Series for Identification of Winter Land Use.

Julien Denize,Laurence Hubert-Moy,Eric Pottier

doi:10.3390/s19245574

Abstract

In the past decade, high spatial resolution Synthetic Aperture Radar (SAR) sensors have provided information that contributed significantly to cropland monitoring. However, the specific configurations of SAR sensors (e.g., band frequency, polarization mode) used to identify land-use types remains underexplored. This study investigates the contribution of C/L-Band frequency, dual/quad polarization and the density of image time-series to winter land-use identification in an agricultural area of approximately 130 km² located in northwestern France. First, SAR parameters were derived from RADARSAT-2, Sentinel-1 and Advanced Land Observing Satellite 2 (ALOS-2) time-series, and one quad-pol and six dual-pol datasets with different spatial resolutions and densities were calculated. Then, land use was classified using the Random Forest algorithm with each of these seven SAR datasets to determine the most suitable SAR configuration for identifying winter land-use. Results highlighted that (i) the C-Band (F1-score 0.70) outperformed the L-Band (F1-score 0.57), (ii) quad polarization (F1-score 0.69) outperformed dual polarization (F1-score 0.59) and (iii) a dense Sentinel-1 time-series (F1-score 0.70) outperformed RADARSAT-2 and ALOS-2 time-series (F1-score 0.69 and 0.29, respectively). In addition, Shannon Entropy and SPAN were the SAR parameters most important for discriminating winter land-use. Thus, the results of this study emphasize the interest of using Sentinel-1 time-series data for identifying winter land-use.

Highlights

The importance of vegetation cover during winter to preserve soil quality and water resources is well-recognized by scientists, decision makers and citizens, and land-use mapping is considered a relevant input into decision-making to implement appropriate policy responses [1]
Results highlight that the C-Band outperformed the L-Band, the quad-polarization mode outperformed the dual-polarization mode and S-1 dense time-series outperformed RST-2 and Advanced Land Observing Satellite 2 (ALOS-2) time-series
C-Band RST-2 dataset showed potential to identify winter land-use, with accuracies similar to those obtained using the dense dual-pol C-Band S-1 dataset. This result is consistent with the studies of [54,55], which showed the potential of polarimetric RST-2 data for monitoring and classifying crops

Summary

Introduction

The importance of vegetation cover during winter to preserve soil quality and water resources is well-recognized by scientists, decision makers and citizens, and land-use mapping is considered a relevant input into decision-making to implement appropriate policy responses [1]. Identifying land use in agricultural areas is a major environmental and scientific issue [2], it remains challenging due to its high spatio-temporal dynamics [3]. In this context, remotely sensed time-series data are a valuable tool to identify land use by providing precise and timely information about the phenological status and development of vegetation at different scales, from local to global extents [4,5]. Using optical time-series to identify land use in winter is limited by cloud cover and/or low solar irradiance [9], and late winter is a critical period during which vegetation begins to grow [3].

Objectives

Methods

Results

Discussion

Conclusion