Land use and land cover classification using Chinese GF-2 multispectral data in a region of the North China Plain

The newly launched GF-2 satellite is now the most advanced civil satellite in China to collect high spatial resolution remote sensing data.This study investigated the capability and strategy of GF?2 multispectral data for land use and land cover (LULC) classification in a region of the North China Plain.The pixel-based and object-based classifications using maximum likelihood (MLC) and support vector machine (SVM) classifiers were evaluated to determine the classification strategy that was suitable for GF?2 multispectral data.The validation results indicated that GF-2 multispectral data achieved satisfactory LULC classification performance,and object-based classification using the SVM classifier achieved the best classification accuracy with an overall classification accuracy of 94.33% and kappa coefficient of 0.911.Therefore,considering the LULC classification performance and data characteristics,GF-2 satellite data could serve as a valuable and reliable high-resolution data source for land surface monitoring.Future works should focus on improving LULC classification accuracy by exploring more classification features and exploring the potential applications of GF-2 data in related applications.

Fractional vegetation cover estimation in heterogeneous areas by combining a radiative transfer model and a dynamic vegetation model

A fractional vegetation cover(FVC)estimation method incorporating a vegetation growth model and a radiative transfer model was previously developed,which was suitable for FVC estimation in homogeneous areas because the finer-resolution pixels corresponding to one coarseresolution FVC pixel were all assumed to have the same vegetation growth model.However,this assumption does not hold over heterogeneous areas,meaning that the method cannot be applied to large regions.Therefore,this study proposes a finer spatial resolution FVC estimation method applicable to heterogeneous areas using Landsat 8 Operational Land Imager reflectance data and Global LAnd Surface Satellite(GLASS)FVC product.The FVC product was first decomposed according to the normalized difference vegetation index from the Landsat 8 OLI data.Then,independent dynamic vegetation models were built for each finer-resolution pixel.Finally,the dynamic vegetation model and a radiative transfer model were combined to estimate FVC at the Landsat 8 scale.Validation results indicated that the proposed method(R^(2)=0.7757,RMSE=0.0881)performed better than either the previous method(R^(2)=0.7038,RMSE=0.1125)or a commonly used method involving look-up table inversions of the PROSAIL model(R^(2)=0.7457,RMSE=0.1249).