Forest cover classification using Landsat ETM+ data and time series MODIS NDVI data

Abstract

Forest cover plays a key role in climate change by influencing the carbon stocks, the hydrological cycle andthe energy balance. Forest cover information can be determined from fine-resolution data, such as LandsatEnhanced Thematic Mapper Plus (ETM+). However, forest cover classification with fine-resolution datausually uses only one temporal data because successive data acquirement is difficult. It may achievemis-classification result without involving vegetation growth information, because different vegetationtypes may have the similar spectral features in the fine-resolution data. To overcome these issues, a forestcover classification method using Landsat ETM+ data appending with time series Moderate-resolutionImaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) data was proposed.The objective was to investigate the potential of temporal features extracted from coarse-resolution timeseries vegetation index data on improving the forest cover classification accuracy using fine-resolutionremote sensing data. This method firstly fused Landsat ETM+ NDVI and MODIS NDVI data to obtain timeseries fine-resolution NDVI data, and then the temporal features were extracted from the fused NDVIdata. Finally, temporal features combined with Landsat ETM+ spectral data was used to improve forestcover classification accuracy using supervised classifier. The study in North China region confirmed thattime series NDVI features had significant effects on improving forest cover classification accuracy of fineresolution remote sensing data. The NDVI features extracted from time series fused NDVI data couldimprove the overall classification accuracy approximately 5% from 88.99% to 93.88% compared to onlyusing single Landsat ETM+ data. © 2014 Elsevier B.V.