Comparative Study on Variable Selection Approaches in Establishment of Remote Sensing Model for Forest Biomass Estimation

In the field of quantitative remote sensing of forest biomass, a prominent phenomenon is the increasing number of explanatory variables. Then how to effectively select explanatory variables has become an important issue. Linear regression model is one of the commonly used remote sensing models. In the process of establishing the linear regression model, a vital step is to select explanatory variables. Focusing on variable selection and model stability, this paper conducts a comparative study on the performance of eight linear regression parameter estimation methods (Stepwise Regression Method (SR), Criterions Based on The Bayes Method (BIC), Criterions Based on The Bayes Method (AIC), Criterions Based on Prediction Error (Cp), Least Absolute Shrinkage and Selection Operator (Lasso), Adaptive Lasso, Smoothly Clipped Absolute Deviation (SCAD), Non-negative garrote (NNG)) in the subtropical forest biomass remote sensing model development. For the purpose of comparison, OLS and RR, are commonly used as methods with no variable selection ability, and are also compared and discussed. The performance of five aspects are evaluated in this paper: (i) Determination coefficient, prediction error, model error, etc., (ii) significance test about the difference between determination coefficients, (iii) parameter stability, (iv) variable selection stability and (v) variable selection ability of the methods. All the results are obtained through a five ten-fold CV. Some evaluation indexes are calculated with or without degrees of freedom. The results show that BIC performs best in comprehensive evaluation, while NNG, Cp and AIC perform poorly as a whole. Other methods show a great difference in the performance on each index. SR has a strong capability in variable selection, although it is poor in commonly used indexes. The short-wave infrared band and the texture features derived from it are selected most frequently by various methods, indicating that these variables play an important role in forest biomass estimation. Some of the conclusions in this paper are likely to change as the study object changes. The ultimate goal of this paper is to introduce various model establishment methods with variable selection capability, so that we can have more choices when establishing similar models, and we can know how to select the most appropriate and effective method for specific problems.

Download Full-text

Influence of Variable Selection and Forest Type on Forest Aboveground Biomass Estimation Using Machine Learning Algorithms

Forests ◽

10.3390/f10121073 ◽

2019 ◽

Vol 10 (12) ◽

pp. 1073 ◽

Cited By ~ 10

Author(s):

Li ◽

Liu

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Variable Selection ◽

Aboveground Biomass ◽

Forest Type ◽

Learning Algorithms ◽

Forest Biomass ◽

Machine Learning Algorithms ◽

Biomass Estimation ◽

Landsat 8

Forest biomass is a major store of carbon and plays a crucial role in the regional and global carbon cycle. Accurate forest biomass assessment is important for monitoring and mapping the status of and changes in forests. However, while remote sensing-based forest biomass estimation in general is well developed and extensively used, improving the accuracy of biomass estimation remains challenging. In this paper, we used China’s National Forest Continuous Inventory data and Landsat 8 Operational Land Imager data in combination with three algorithms, either the linear regression (LR), random forest (RF), or extreme gradient boosting (XGBoost), to establish biomass estimation models based on forest type. In the modeling process, two methods of variable selection, e.g., stepwise regression and variable importance-base method, were used to select optimal variable subsets for LR and machine learning algorithms (e.g., RF and XGBoost), respectively. Comfortingly, the accuracy of models was significantly improved, and thus the following conclusions were drawn: (1) Variable selection is very important for improving the performance of models, especially for machine learning algorithms, and the influence of variable selection on XGBoost is significantly greater than that of RF. (2) Machine learning algorithms have advantages in aboveground biomass (AGB) estimation, and the XGBoost and RF models significantly improved the estimation accuracy compared with the LR models. Despite that the problems of overestimation and underestimation were not fully eliminated, the XGBoost algorithm worked well and reduced these problems to a certain extent. (3) The approach of AGB modeling based on forest type is a very advantageous method for improving the performance at the lower and higher values of AGB. Some conclusions in this paper were probably different as the study area changed. The methods used in this paper provide an optional and useful approach for improving the accuracy of AGB estimation based on remote sensing data, and the estimation of AGB was a reference basis for monitoring the forest ecosystem of the study area.

Download Full-text

Forest Biomass Estimation Based on Remote Sensing Method for North Daxingan Mountains

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.339.336 ◽

2011 ◽

Vol 339 ◽

pp. 336-341 ◽

Cited By ~ 1

Author(s):

Yuan Yuan Zhang ◽

Feng Ri Li ◽

Fu Xiang Liu

Keyword(s):

Remote Sensing ◽

Linear Regression ◽

Regression Model ◽

Multiple Linear Regression ◽

Linear Regression Model ◽

Forest Biomass ◽

Multiple Linear Regression Model ◽

Biomass Estimation ◽

Individual Tree ◽

Forest Region

Using the Landsat 5 TM images in 2002 as source data，the paper constructed individual tree biomass models of seven principal species based on the data from field surveying and fixed Plots in Tahe and Amur forest Region in Daxiangan Mountains. The remote sensing biomass model between TM images and data from forest fixed Plots was developed by the methods of multiple linear regression and BP neutral net. The result showed that R in multiple linear regression model was 0.764 and the model passed the F test, D-W test and multi-collinearity test. In the independent sample estimation，The neutral net model with the precision of 91.25% was significantly higher than multiple linear regression model with the precision of 81.02%. Although the“black-box”neutral net model could not give the concrete analytical equation, this kind of model with high precision might be applied to estimate the forest biomass in large level forest biomass.

Download Full-text