An Evaluation of Different Training Sample Allocation Schemes for Discrete and Continuous Land Cover Classification Using Decision Tree-Based Algorithms
Open Access
- 29 July 2015
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 7 (8) , 9655-9681
Abstract
Land cover mapping for large regions often employs satellite images of medium to coarse spatial resolution, which complicates mapping of discrete classes. Class memberships, which estimate the proportion of each class for every pixel, have been suggested as an alternative. This paper compares different strategies of training data allocation for discrete and continuous land cover mapping using classification and regression tree algorithms. In addition to measures of discrete and continuous map accuracy the correct estimation of the area is another important criteria. A subset of the 30 m national land cover dataset of 2006 (NLCD2006) of the United States was used as reference set to classify NADIR BRDF-adjusted surface reflectance time series of MODIS at 900 m spatial resolution. Results show that sampling of heterogeneous pixels and sample allocation according to the expected area of each class is best for classification trees. Regression trees for continuous land cover mapping should be trained with random allocation, and predictions should be normalized with a linear scaling function to correctly estimate the total area. From the tested algorithms random forest classification yields lower errors than boosted trees of C5.0, and Cubist shows higher accuracies than random forest regression.Keywords
This publication has 49 references indexed in Scilit:
- Impervious surface quantification using a synthesis of artificial immune networks and decision/regression trees from multi-sensor dataRemote Sensing of Environment, 2012
- Land cover classification with coarse spatial resolution data to derive continuous and discrete maps for complex regionsRemote Sensing of Environment, 2011
- MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasetsRemote Sensing of Environment, 2010
- On the Suitability of MODIS Time Series Metrics to Map Vegetation Types in Dry Savanna Ecosystems: A Case Study in the Kalahari of NE NamibiaRemote Sensing, 2009
- The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVMRemote Sensing of Environment, 2006
- Towards an operational MODIS continuous field of percent tree cover algorithm: examples using AVHRR and MODIS dataRemote Sensing of Environment, 2002
- Global land cover mapping from MODIS: algorithms and early resultsRemote Sensing of Environment, 2002
- Feature selection and land cover classification of a MODIS-like data set for a semiarid environmentInternational Journal of Remote Sensing, 1999
- Global land cover classifications at 8 km spatial resolution: The use of training data derived from Landsat imagery in decision tree classifiersInternational Journal of Remote Sensing, 1998
- NDVI-derived land cover classifications at a global scaleInternational Journal of Remote Sensing, 1994