Extracting distribution and expansion of rubber plantations from Landsat imagery using the C5.0 decision tree method

Abstract. Natural tropical rainforests in China’s Xishuangbanna region have undergone dramatic conversion to rubber plantations in recent decades, resulting in altering the region’s environment and ecological systems. Therefore, it is of great importance for local environmental and ecological protection agencies to research the distribution and expansion of rubber plantations. The objective of this paper is to monitor dynamic changes of rubber plantations in China’s Xishuangbanna region based on multitemporal Landsat images (acquired in 1989, 2000, and 2013) using a C5.0-based decision-tree method. A practical and semiautomatic data processing procedure for mapping rubber plantations was proposed. Especially, haze removal and deshadowing were proposed to perform atmospheric and topographic correction and reduce the effects of haze, shadow, and terrain. Our results showed that the atmospheric and topographic correction could improve the extraction accuracy of rubber plantations, especially in mountainous areas. The overall classification accuracies were 84.2%, 83.9%, and 86.5% for the Landsat images acquired in 1989, 2000, and 2013, respectively. This study also found that the Landsat-8 images could provide significant improvement in the ability to identify rubber plantations. The extracted maps showed the selected study area underwent rapid conversion of natural and seminatural forest to a rubber plantations from 1989 to 2013. The rubber plantation area increased from 2.8% in 1989 to 17.8% in 2013, while the forest/woodland area decreased from 75.6% in 1989 to 44.8% in 2013. The proposed data processing procedure is a promising approach to mapping the spatial distribution and temporal dynamics of rubber plantations on a regional scale.

[1]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[2]  David T. Potere,et al.  Horizontal Positional Accuracy of Google Earth's High-Resolution Imagery Archive , 2008, Sensors.

[3]  E. C. Chapman.  The expansion of rubber in southern Yunnan, China , 1991 .

[4]  Hongmei Li,et al.  Past, present and future land-use in Xishuangbanna, China and the implications for carbon dynamics , 2008 .

[5]  Huang Chong,et al.  Analysis of distribution characteristics of Hevea brasiliensis in the Xishuangbanna area based on HJ-1 satellite data , 2011 .

[6]  Yang Hongwe.  Distribution Information Extraction of Rubber Woods Using Remote Sensing Images with High Resolution , 2014 .

[7]  Bin Zhao,et al.  Mapping tropical forests and deciduous rubber plantations in Hainan Island, China by integrating PALSAR 25-m and multi-temporal Landsat images , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[8]  Bangqian Chen,et al.  Mapping deciduous rubber plantations through integration of PALSAR and multi-temporal Landsat imagery , 2013 .

[9]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[10]  Li Ya,et al.  Analysis of distribution characteristics of Hevea brasiliensis in the Xishuangbanna area based on HJ-1 satellite data , 2011 .

[11]  G. Foody.  Assessing the Accuracy of Remotely Sensed Data: Principles and Practices , 2010 .

[12]  Zhengwei He,et al.  Extracting rubber plant in Quickbird imagery based on Support Vector Machines , 2010, 2010 2nd International Conference on Industrial and Information Systems.

[13]  LI Zeng-Jia,et al.  RELATION OF LAND USE AND COVER CHANGE TO TOPOGRAPHY IN XISHUANGBANNA,SOUTHWEST CHINA , 2008 .

[14]  Steven Vanonckelen,et al.  Performance of atmospheric and topographic correction methods on Landsat imagery in mountain areas , 2014 .

[15]  James Hammond,et al.  Land-use change impact on time-averaged carbon balances: rubber expansion and reforestation in a biosphere reserve, South-West China. , 2016 .

[16]  Xinwu Li,et al.  Estimating urban impervious surfaces from Landsat-5 TM imagery using multilayer perceptron neural network and support vector machine , 2011 .

[17]  Charles C Mann,et al.  Addicted to rubber. , 2009, Science.

[18]  C. Alados,et al.  Improving the Accuracy of Vegetation Classifications in Mountainous Areas , 2013 .

[19]  Peter A. Troch,et al.  Hydrologic effects of the expansion of rubber (Hevea brasiliensis) in a tropical catchment , 2010 .

[20]  Hongbo Shao,et al.  Spatial-temporal succession of the vegetation in Xishuangbanna, China during 1976-2010: A case study based on RS technology and implications for eco-restoration , 2014 .

[21]  Xia Li,et al.  A novel algorithm for land use and land cover classification using RADARSAT-2 polarimetric SAR data , 2012 .

[22]  Jean-Claude Souyris,et al.  Support Vector Machine for Multifrequency SAR Polarimetric Data Classification , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Zhuang-Fang Yi,et al.  Developing indicators of economic value and biodiversity loss for rubber plantations in Xishuangbanna, southwest China: A case study from Menglun township , 2014 .

[24]  Kitsanai Charoenjit,et al.  Estimation of biomass and carbon stock in Para rubber plantations using object-based classification from Thaichote satellite data in Eastern Thailand , 2015 .

[25]  Dirk Pflugmacher,et al.  Mapping Rubber Plantations and Natural Forests in Xishuangbanna (Southwest China) Using Multi-Spectral Phenological Metrics from MODIS Time Series , 2013, Remote. Sens..

[26]  Jefferson Fox,et al.  Rubber Tree Distribution Mapping in Northeast Thailand , 2011 .

[27]  Zhe Li,et al.  Integrating Mahalanobis typicalities with a neural network for rubber distribution mapping , 2011 .

[28]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[29]  Jinwei Dong,et al.  A comparison of forest cover maps in Mainland Southeast Asia from multiple sources: PALSAR, MERIS, MODIS and FRA , 2012 .

[30]  Huadong Guo,et al.  Synergistic Use of Optical and PolSAR Imagery for Urban Impervious Surface Estimation , 2014 .

[31]  Zhang Jinghua,et al.  Rubber Plantations in Xishuangbanna: Remote Sensing Identification and Digital Mapping , 2012 .

[32]  N. Mizoue,et al.  Estimation of rubberwood production in Cambodia , 2011, New Forests.

[33]  Xin Yang,et al.  The extraction of rubber spatial distributing information in hainan province based on FY-3a satellite data , 2010, 2010 World Automation Congress.

[34]  Zheng Zhang,et al.  Phenology-Based Vegetation Index Differencing for Mapping of Rubber Plantations Using Landsat OLI Data , 2015, Remote. Sens..

[35]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[36]  Zhiming Feng,et al.  Mapping rubber tree plantations using a Landsat-based phenological algorithm in Xishuangbanna, southwest China , 2015 .

[37]  Eric F. Lambin,et al.  Evaluation and parameterization of ATCOR3 topographic correction method for forest cover mapping in mountain areas , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[39]  Jianchu Xu,et al.  The Rubber Juggernaut , 2009, Science.

[40]  Alex Smajgl,et al.  Environmental stratification to model climate change impacts on biodiversity and rubber production in Xishuangbanna, Yunnan, China , 2014 .

[41]  Anton J. J. van Rompaey,et al.  he effect of atmospheric and topographic correction methods on land cover lassification accuracy , 2013 .

[42]  Jane Qiu,et al.  Where the rubber meets the garden , 2009, Nature.

[43]  Dietrich Schmidt-Vogt,et al.  Pushing the Limits: The Pattern and Dynamics of Rubber Monoculture Expansion in Xishuangbanna, SW China , 2016, PloS one.

[44]  F. Evrendilek,et al.  Boosted decision tree classifications of land cover over Turkey integrating MODIS, climate and topographic data , 2011 .

[45]  J. Ross Quinlan,et al.  Bagging, Boosting, and C4.5 , 1996, AAAI/IAAI, Vol. 1.

[46]  Jinwei Dong,et al.  Mapping tropical forests and rubber plantations in complex landscapes by integrating PALSAR and MODIS imagery , 2012 .

[47]  Stefan Dech,et al.  Characterisation of land surface phenology and land cover based on moderate resolution satellite data in cloud prone areas — A novel product for the Mekong Basin , 2013 .

[48]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[49]  Li Li,et al.  Mapping Deciduous Rubber Plantation Areas and Stand Ages with PALSAR and Landsat Images , 2015, Remote. Sens..

[50]  Jefferson Fox,et al.  Mapping rubber tree growth in mainland Southeast Asia using time-series MODIS 250 m NDVI and statistical data , 2012 .