Evaluation of the Performance of Time-Series Sentinel-1 Data for Discriminating Rock Units

Yi Lu,Qigang Jiang,Changbao Yang

doi:10.3390/rs13234824

Yi Lu, Qigang Jiang + Show 1 more

Open Access

https://doi.org/10.3390/rs13234824

Copy DOI

Abstract

The potential use of time-series Sentinel-1 synthetic aperture radar (SAR) data for rock unit discrimination has never been explored in previous studies. Here, we employed time-series Sentinel-1 data to discriminate Dananhu formation, Xinjiang group, Granite, Wusu group, Xishanyao formation, and Diorite in Xinjiang, China. Firstly, the temporal variation of the backscatter metrics (backscatter coefficient and coherence) from April to October derived from Sentinel-1, was analyzed. Then, the significant differences of the time-series SAR metrics among different rock units were checked using the Kruskal–Wallis rank sum test and Tukey’s honest significant difference test. Finally, random forest models were used to discriminate rock units. As for the input features, there were four groups: (1) time-series backscatter metrics, (2) single-date backscatter metrics, (3) time-series backscatter metrics at VV, and (4) VH channel. In each feature group, there were three sub-groups: backscatter coefficient, coherence, and combined use of backscatter coefficient and coherence. Our results showed that time-series Sentinel-1 data could improve the discrimination accuracy by roughly 9% (from 55.4% to 64.4%), compared to single-date Sentinel-1 data. Both VV and VH polarization provided comparable results. Coherence complements the backscatter coefficient when discriminating rock units. Among the six rock units, the Granite and Xinjiang group can be better differentiated than the other four rock units. Though the result still leaves space for improvement, this study further demonstrates the great potential of time-series Sentinel-1 data for rock unit discrimination.

Highlights

Accurate identification of lithology is important for mineral and oil exploration [1,2].conventional field-based lithology investigation, especially in large areas or areas with substantial amounts of cover, is often time-consuming and expensive
The main aim of this study is to evaluate the potential of time-series synthetic aperture radar (SAR) metrics derived from Sentinel-1 data for rock unit discrimination
We analyzed the temporal variation of the Sentinel-1 derived metrics among six rock units from April to October

Summary

Introduction

Accurate identification of lithology is important for mineral and oil exploration [1,2].conventional field-based lithology investigation, especially in large areas or areas with substantial amounts of cover, is often time-consuming and expensive. Previous studies indicated that diagnostic spectral signatures could be affected by various physical and chemical properties such as the rock-forming compositions [5,6], structure [7], particle size [8,9], and molecular vibration [10,11,12]. These studies build a profound basis for subsequent research on distinguishing rock units using airborne/satellite remote sensing data. Lithology discrimination often suffers from low accuracy due to the overlap of the diagnostic spectral features or the spectral variability of rocks [18,19]

Objectives

Methods

Results

Discussion

Conclusion