EGU2020-4512
https://doi.org/10.5194/egusphere-egu2020-4512
EGU General Assembly 2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Fusion of Sentinel-1 radar and Sentinel-2 MSI imagery for water extraction in Tibetan plateau

Dan Li1, Baosheng Wu1, Bowei Chen2, Yanjun Wang3, Yi Zhang1, Yuan Xue1, and Chao Qin1
Dan Li et al.
  • 1State Key Laboratory of Hydroscience and Engineering, Tsinghua University, Beijing 100084, PR China (glqinchao@nwsuaf.edu.cn)
  • 2Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China (chenbw@aircas.ac.cn)
  • 3Changjiang River Scientific Research Institute; and Key Laboratory of River Regulation and Flood Control of the Ministry of Water Resources, Wuhan 430010, China (yanjun1113@126.com)

Abstract: Water plays a vital role in plants, animals and human survival, as well as water resources planning and protection. The spatial and temporal changes of rivers have a profound impact on climate change and the scientific protection of the regional ecological environment in Qingzang-Tibet plateau. Due to the influence of snow and cloud cover, optical remote sensing images in this region have less effective coverage. Many researches in the past mainly faced the challenge of misclassification caused by shadows from cloud and mountain. In this study, we proposed a method to improve the extraction of rivers by reducing the effect of shadows by fusing Sentinel-1 radar data and Sentinel-2 optical imagery. For the optical imagery, water indices including MNDWI (Modified Normalized Difference Water Index) and RNDWI (Revised Normalized Difference Water Index) and morphological operations were used to extract the river coverage. In addition, radar data is used to extract water in areas where there is no optical image coverage or where optical images are misclassified by using a combination of both the histogram and Otsu threshold methods. The GEE (Google Earth Engine) platform is used to implement the analysis using two classification datasets at a regional level. Relevant results from Sentinel-1 and Sentinel-2 data showed that the RNDWI has a more accurate water extraction results in this region. We further compared the final river width results with the manually measured samples from Google Earth and situ data of hydrological stations for accuracy assessment. The R2 value is 0.90, and the standard deviation is 18.663m. The river width can be estimated well by this method, which can provide basic data for the study of water in depopulated zone.

Keywords: Remote sensing, shadow removal, water extraction, water index, Otsu threshold, Google Earth Engine

How to cite: Li, D., Wu, B., Chen, B., Wang, Y., Zhang, Y., Xue, Y., and Qin, C.: Fusion of Sentinel-1 radar and Sentinel-2 MSI imagery for water extraction in Tibetan plateau, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-4512, https://doi.org/10.5194/egusphere-egu2020-4512, 2020