Using Data Mining Techniques for Predicting Individual Tree Mortality in Tropical Rain Forest : with Optimized Parameters in Logistic Regression and Decision Trees Approach

Computer Engineering

Forest ecosystem dynamics uses tree mortality. It is one of the most common facts due to species rich in tropical rain forests. Individual tree mortality model was developed for predicting the probability of mortality in dipterocarpaceae tree family group in Koh Kong province, Cambodia. It is a big challenge of finding appropriate methods for modeling mortality. There two data mining methods here; Logistic regression and decision trees. To chose for decision trees method, Chi squared Automatic Interaction Detector method was selected which always chooses independent variables. With increasing individual tree basal area, the probability of mortality gets decreased. Using calibration and discrimination the performance was compared of each model. The study presented that logistic regression outperformed decision trees for both calibration and discrimination. To improve the accuracy of the stand forecast the model developed.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.