Mapping Paddy Rice with Sentinel-1/2 and Phenology-, Object-Based Algorithm—A Implementation in Hangjiahu Plain in China Using GEE Platform

• Published in: Remote sensing (Basel, Switzerland) Vol. 13; no. 5; p. 990
• Main Authors: Xiao, Wu, Xu, Suchen, He, Tingting
• Format: Journal Article
• Language: English
• Published: MDPI AG 01.03.2021
• Subjects: algorithms; case studies; China; Google Earth Engine; Internet; landscapes; monsoon region; monsoon season; object-based; paddy rice; phenology; rough rice; Sentinel-1/2; time series analysis; vegetation index; China
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs13050990

In tropical/subtropical monsoon regions, accurate rice mapping is hampered by the following factors: (1) The frequent occurrence of clouds in such areas during the rice-growing season interferes strongly with optical remote sensing observations; (2) The agro-landscape in such regions is fragmented and scattered. Rice maps produced using low spatial resolution data cannot well delineate the detailed distribution of rice, while pixel-based mapping using medium and high resolutions has significant salt-and-pepper noise. (3) The cropping system is complex, and rice has a rotation schedule with other crops. Therefore, the Phenology-, Object- and Double Source-based (PODS) paddy rice mapping algorithm is implemented, which consists of three steps: (1) object extraction from multi-temporal 10-m Sentinel-2 images where the extracted objects (fields) are the basic classification units; (2) specifying the phenological stage of transplanting from Savitzky–Golay filtered enhanced vegetation index (EVI) time series using the PhenoRice algorithm; and (3) the identification of rice objects based on flood signal detection from time-series microwave and optical signals of the Sentinel-1/2. This study evaluated the potential of the combined use of the Sentinel-1/2 mission on paddy rice mapping in monsoon regions with the Hangzhou-Jiaxin-Huzhou (HJH) plain in China as the case study. A cloud computing approach was used to process the available Sentinel-1/2 imagery from 2019 and MODIS images from 2018 to 2020 in the HJH plain on the Google Earth Engine (GEE) platform. An accuracy assessment showed that the resultant object-based paddy rice map has a high accuracy with a producer (user) accuracy of 0.937 (0.926). The resultant 10-m paddy rice map is expected to provide unprecedented detail, spatial distribution, and landscape patterns for paddy rice fields in monsoon regions.