Evaluation of Crop Type Classification with Different High Resolution Satellite Data Sources

Abstract

Crop type classification with satellite imageries is widely applied in support of crop production management and food security strategy. The abundant supply of these satellite data is accelerating and blooming the application of crop classification as satellite data at 10 m to 30 m spatial resolution have been made accessible easily, widely and free of charge, including optical sensors, the wide field of viewer (WFV) onboard the GaoFen (GF, high resolution in English) series from China, the MultiSpectral Instrument (MSI) onboard Sentinel 2 (S2) from Europe and the Operational Land Imager (OLI) onboard Landsat 8 (L8) from USA, thanks to the implementation of the open data policy. There are more options in using the satellite data as these three data sources are available. This paper explored the different capability of these three data sources for the crop type mapping in the same area and within the same growing season. The study was executed in a flat and irrigated area in Northwest China. Nine types of crop were classified using these three kinds of time series of data sources in 2017 and 2018, respectively. The same suites of the training samples and validation samples were applied for each of the data sources. Random Forest (RF) was used as the classifier for the crop type classification. The confusion error matrix with the OA, Kappa and F1-score was used to evaluate the accuracy of the classifications. The result shows that GF-1 relatively has the lowest accuracy as a consequence of the limited spectral bands, but the accuracy is at 93–94%, which is still excellent and acceptable for crop type classification. S2 achieved the highest accuracy of 96–98%, with 10 available bands for the crop type classification at either 10 m or 20 m. The accuracy of 97–98% for L8 is in the middle but the difference is small in comparison with S2. Any of these satellite data may be used for the crop type classification within the growing season, with a very good accuracy if the training datasets were well tuned.