Estimating the Growing Stem Volume of Coniferous Plantations Based on Random Forest Using an Optimized Variable Selection Method
| Autor: | Arbi J. Sarkissian, Mykola Kutia, Fugen Jiang, Guangxing Wang, Jiangping Long, Hua Sun, Hui Lin |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
texture feature
China 010504 meteorology & atmospheric sciences Mean squared error 0211 other engineering and technologies Red edge Feature selection 02 engineering and technology lcsh:Chemical technology 01 natural sciences Biochemistry Article Analytical Chemistry forest growing stem volume Forest ecology Statistics lcsh:TP1-1185 Electrical and Electronic Engineering Instrumentation Ecosystem Selection (genetic algorithm) red-edge band 021101 geological & geomatics engineering 0105 earth and related environmental sciences Mathematics Stepwise regression Atomic and Molecular Physics and Optics Random forest coniferous plantations Tracheophyta Variable (computer science) Remote Sensing Technology Linear Models random forest variable selection |
| Zdroj: | Sensors, Vol 20, Iss 7248, p 7248 (2020) Sensors Volume 20 Issue 24 Sensors (Basel, Switzerland) |
| ISSN: | 1424-8220 |
| Popis: | Forest growing stem volume (GSV) reflects the richness of forest resources as well as the quality of forest ecosystems. Remote sensing technology enables robust and efficient GSV estimation as it greatly reduces the survey time and cost while facilitating periodic monitoring. Given its red edge bands and a short revisit time period, Sentinel-2 images were selected for the GSV estimation in Wangyedian forest farm, Inner Mongolia, China. The variable combination was shown to significantly affect the accuracy of the estimation model. After extracting spectral variables, texture features, and topographic factors, a stepwise random forest (SRF) method was proposed to select variable combinations and establish random forest regressions (RFR) for GSV estimation. The linear stepwise regression (LSR), Boruta, Variable Selection Using Random Forests (VSURF), and random forest (RF) methods were then used as references for comparison with the proposed SRF for selection of predictors and GSV estimation. Combined with the observed GSV data and the Sentinel-2 images, the distributions of GSV were generated by the RFR models with the variable combinations determined by the LSR, RF, Boruta, VSURF, and SRF. The results show that the texture features of Sentinel-2&rsquo s red edge bands can significantly improve the accuracy of GSV estimation. The SRF method can effectively select the optimal variable combination, and the SRF-based model results in the highest estimation accuracy with the decreases of relative root mean square error by 16.4%, 14.4%, 16.3%, and 10.6% compared with those from the LSR-, RF-, Boruta-, and VSURF-based models, respectively. The GSV distribution generated by the SRF-based model matched that of the field observations well. The results of this study are expected to provide a reference for GSV estimation of coniferous plantations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|