A stepwise regression tree for nonlinear approximation: applications to estimating subpixel land cover
نویسندگان
چکیده
A stepwise regression tree (SRT) algorithm was developed for approximating complex nonlinear relationships. Based on the regression tree of Breiman et al. (BRT) and a stepwise linear regression (SLR) method, this algorithm represents an improvement over SLR in that it can approximate nonlinear relationships and over BRT in that it gives more realistic predictions. The applicability of this method to estimating subpixel forest was demonstrated using three test data sets, on all of which it gave more accurate predictions than SLR and BRT. SRT also generated more compact trees and performed better than or at least as well as BRT at all 10 equal forest proportion interval ranging from 0 to 100%. This method is appealing to estimating subpixel land cover over large areas.
منابع مشابه
Automatic QoS-aware Web Services Composition based on Set-Cover Problem
By definition, web-services composition works on developing merely optimum coordination among a number of available web-services to provide a new composed web-service intended to satisfy some users requirements for which a single web service is not (good) enough. In this article, the formulation of the automatic web-services composition is proposed as several set-cover problems and an approxima...
متن کاملA Strategy for Estimating Tree Canopy Density Using Landsat 7 ETM+ and High Resolution Images Over Large Areas
Forest cover is of great interest to a variety of scientific and land management applications, many of which require not only information on forest categories, but also tree canopy density. In previous studies, large area tree canopy density had been estimated at spatial resolutions of 1km or coarser using coarse resolution satellite images. In this study, a strategy is developed for estimating...
متن کاملLand Cover Subpixel Change Detection using Hyperspectral Images Based on Spectral Unmixing and Post-processing
The earth is continually being influenced by some actions such as flood, tornado and human artificial activities. This process causes the changes in land cover type. Thus, for optimal management of the use of resources, it is necessary to be aware of these changes. Today’s remote sensing plays key role in geology and environmental monitoring by its high resolution, wide covering and low cost...
متن کاملSubpixel Urban Land Cover Estimation: Comparing Cubist, Random Forests, and Support Vector Regression
Three machine learning subpixel estimation methods (Cubist, Random Forests, and support vector regression) were applied to estimate urban cover. Urban forest canopy cover and impervious surface cover were estimated from Landsat-7 ETM imagery using a higher resolution cover map resampled to 30 m as training and reference data. Three different band combinations (reflectance, tasseled cap, and bot...
متن کاملLandsat Etm Sub-pixel Analysis of Urban Landscape Using Fuzzy C- Means Clustering and Differentiated Impervious Surface Classes
Fuzzy c-means clustering (FCM) algorithm has been used to analyze the sub-pixel composition of medium spatialresolution satellite image (i.e., Landsat ETM). As urban landscape shows complex patterns of land cover composition and setting, it is difficult to have high accuracy in estimating urban land cover composition from Landsat image because of the mixed pixel problem. This study evaluates th...
متن کامل