Mapping Tea Plantations from Multi-seasonal Landsat-8 OLI Imageries Using a Random Forest Classifier
It is very challenging to extract tea plantations from medium-resolution satellite imageries. This paper presents a new methodological framework based on the random forest classifier for extracting tea plantations from Landsat-8 OLI imageries. Analysis is facilitated by a dataset of three Landsat-8 OLI images (spring, autumn and winter) in 2014 covering the Anji County, one of the major tea production regions in China. More specifically, in order to determine the relative importance of spectra, texture, vegetation index and seasonality on classification accuracy, we design a series of classification feature sets, including: initial feature sets for different seasons, feature selection feature sets for different seasons and multi-seasonal feature sets. The results show that the multi-seasonal feature selection set has the best feature set performance (PA = 0.88; OA = 0.92; Kappa = 0.90). Our study demonstrates that the random forest classifier is reliable and practical for extracting tea plantations from medium-resolution images. Highlights of this study are: mapping tea plantations, an important cash crop to local agriculture, in a fragmented landscape; integrating textual, vegetational, and seasonal features, which were helpful for improving tea plantation mapping accuracy in combination; taking advantage of the feature selection function of random forest, supporting high-dimensional data classification, which leads to a higher classification accuracy.
KeywordsTea plantations Random forest classifier Land cover mapping Landsat 8
We acknowledge the funding support from the Technological Innovation and Application Demonstration Program of Chongqing (cstc2018jscx-mszdX0067), National Key R&D Program of China (2018YFB0505400) and the Chongqing Postdoctoral Science Foundation (Rc201515).
- Ahmad, A., Hashim, U. K. M., Mohd, O., Abdullah, M. M., Sakidin, H., Rasib, A. W., et al. (2018). Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data. International Journal of Advanced Computer Science and Applications, 9, 529–537.Google Scholar
- Zhao, W., & Cui, S. M. (2008). Land covers classification for remote sensing images based on spectral and textural information. In Proceeding of the 11th joint conference on information sciences. Atlantis, France.Google Scholar