Exploring the potential of Chinese GF-6 images for crop mapping in regions with complex agricultural landscapes



View results in:
https://reader.elsevier.com/reader/sd/pii/S0303243422000289?token=36ACE4E0ED986515014BE37568E37F41CB2E260B873D0383E790E95D38CEC0B7B4F0C4DAB8825FC489982E4CAF0901BA&originRegion=us-east-1&originCreation=20220523162954
Countries: 
Region: 
DOI: 
https://doi.org/10.1016/j.jag.2022.102702
Provider: 
Licensing of resource: 
Creative Commons Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)
Type: 
journal article
Journal: 
International Journal of Applied Earth Observation and Geoinformation
Volume: 
107
Year: 
2022
Author(s): 
Xia T.
He Z.
Cai Z.
Wang C.
Wang W.
Wang J.
Hu Q.
Song Q.
Publisher(s): 
Description: 

Accurate and timely crop mapping is crucial for environment assessment, food security and agricultural production. However, for the areas with high landscape heterogeneity and frequent cloudy and rainy weather, the insufficient high-quality satellite images limit the accuracy of crop classification. The recently launched Chinese GF-6 wide field-of-view camera (WFV) with a revisit cycle of 4-day and spatial resolution of 16-meter shows great potential for agricultural monitoring. In this study, Qianjiang City characterized by complex agricultural landscapes was selected as the research area to assess the potential of GF-6 data in identifying crop types. Firstly, the pairwise and global separability were calculated to analyze the effect of different spectral-temporal features of GF-6 images on crop classification. A total of 255 spectral-temporal features derived from 15 GF-6 tiles were then used to perform random forest classification. Furthermore, the classification results were evaluated based on 671 field samples and then compared the accuracy between GF-6 data and Sentinel-2 or Landsat-8 data. In addition, the earliest identifiable time of crop types was also determined by iteratively using all available GF-6 data during each time period. The results suggested that the overall accuracy (OA) of all available GF-6 images was 91.55%, which was significantly higher than that of Landsat-8 data (OA = 85.97%) and was slightly lower than that of Sentinel-2 data (OA = 93.10%). The newly added red-edge bands (0.69 ∼ 0.73 μm, 0.73 ∼ 0.77 μm) and their derivative vegetation indices were important spectral features, and the period from mid-March to early-April was the best temporal window for crop identification in our research area. Moreover, late July was the earliest crop identifiable time with overall accuracy of 90% for the first time of the year. These results indicated the great potential of GF-6 images for classifying crop types in the areas with complex cropping system and fragmented agricultural landscapes, particularly when integrating other satellite data with comparable spatial resolution (e.g. Chinese GF-1 data and Sentinel-2 data).

Publication year: 
2022
Keywords: 
Spectral-temporal separability
Random forest
Early season
Crop mapping
GF-6 wide field-of-view