Seasonal Land Cover Dynamics in Beijing Derived from Landsat 8 Data Using a Spatio-Temporal Contextual Approach

Abstract

Seasonal dynamic land cover maps could provide useful information toecosystem, water-resource and climate modelers. However, they are rarely mapped morefrequent than annually. Here, we propose an approach to map dynamic land cover types withfrequently available satellite data. Landsat 8 data acquired from nine dates over Beijingwithin a one-year period were used to map seasonal land cover dynamics. A two-stepprocedure was performed for training sample collection to get better results. Sample setswere interpreted for each acquisition date of Landsat 8 image. We used the random forestclassifier to realize the mapping. Nine sets of experiments were designed to incorporatedifferent input features and use of spatial temporal information into the dynamic land coverclassification. Land cover maps obtained with single-date data in the optical spectral regionwere used as benchmarks. Texture, NDVI and thermal infrared bands were added as newfeatures for improvements. A Markov random field (MRF) model was applied to maintainthe spatio-temporal consistency. Classifications with all features from all images wereperformed, and an MRF model was also applied to the results estimated with all features.The best overall accuracies achieved for each date ranged from 75.31% to 85.61%.