Abstract

Tea plantations expansion has occurred in the major tea planting area of Yunnan province, China, however, it is a big challenge to extract and map the distribution of tea plantations due to their non-obvious phenological characteristics in the tropical and subtropical regions. Firstly, we demonstrated the pruning phenological phase of tea plantations by using field hyperspectral data. Secondly, we analyzed the optical features of typical land cover types from the available time series Landsat imagery with the Google Earth Engine (GEE) platform. We proposed a pixel and phenology- based approach to extract and map tea plantations distribution at the 30-m resolution of the historical time period of 2015 to 2019. The resultant map had high user/producer accuracies of 91.07% and 86.90%, respectively. Our study provides a promising new approach to extract and map tea plantations in complex tropical landscapes at fine spatial resolution by using only free historical Landsat imagery.