What Is The Estimation Of The Forest Femining Methods

With increase in the amount, quality and accessibility of the remote sensing data on one hand, and advancement, ease of use and capability of the open source machine learning and statistical tools, on the other hand, machine learning approaches have become very popular and powerful methods for estimation of the forest biomass in the recent years. \cite{Iftikhar} By far, linear regression is the most well understood algorithm in statistics and machine learning compared to any other machine learning tools. Table 2 summarizes the studies that has been done on estimation of the biomass using LiDAR techniques. Linear mixed effects (LME) regression is the extended version of the linear regression model and applicable for the cluster data†¦show more content†¦There are several ways to select the best features. \cite{Thomas}. Also, it has been shown that selection of the number of the features for classification, neighbors and the predictors are very deterministic in the quality of the classification \cite{NLi}. Random Forest (RF) and Support Vector Machine (SVM) are two machine learning approaches that has been successfully implemented in several studies and resulted in the significantly better results compared to KNN or other regression models. For example, in the study by Fassnacht et al.\cite{Fassnacht 2014} using LiDAR and Hyperspectral data, it has been shown that RF model produce a better forest aboveground biomass prediction compared to other tested methods. RF is the ensemble classification technique based on the many random decision trees classifiers. Decision tree is the classification approach that relate the target point to the predictor based on the simple decision criteria. Decision tree can easily become unstable and result in the very complex decision boundaries, therefore Random forests are used to improve the accuracy of the prediction and also controls the over-fitting \cite{Thomas}. It has been shown that a large number of features can be handled by RF \cite{Liai}. RF also, has been reported to have higher accuracy in predicting biomass compared to