The simplicity of XGBoost algorithm versus the complexity of Random Forest, Support Vector Machine, and Neural Networks algorithms in urban forest classification

Abstract

Background: The availability of urban forest is under serious threat, especially in developing countries where urbanization is taking place rapidly. Meanwhile, there are many classifier algorithms available to monitor the extent of the urban forest. However, we need to assess the performance of each classifier to understand its complexity and accuracy. Methods: This study proposes a novel procedure using R language with RStudio software to assess four different classifiers based on different numbers of training datasets to classify the urban forest within the campus environment. The normalized difference vegetation indices (NDVI) were then employed to compare the accuracy of each classifier. Results: This study found that the Extreme Gradient Boosting (XGBoost) classifier outperformed the other three classifiers, with an RMSE value of 1.56. While the Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM) were in second, third, and fourth place with RMSE values of 4.33, 6.81, and 7.45 respectively. Conclusions: The XGBoost algorithm is the most suitable for urban forest classification with limited data training. This study is easy to reproduce since the code is available and open to the public.

The Effect of Climate Change on Organic Honey Efficiency in Türkiye via Machine Learning

“…Furthermore, the comprehensive packages and tools provided by RStudio create an appropriate environment for data analysis and machine learning. The XGBoost algorithm is widely recognized for its superior performance on large datasets and its ability to identify complex relationships and interactions, particularly through its gradient boosting method [28][29][30]. In comparison, other commonly used machine learning algorithms, such as Random Forest and Support Vector Machine (SVM), may have slower training times and lower performance when compared to XGBoost.…”

“…In comparison, other commonly used machine learning algorithms, such as Random Forest and Support Vector Machine (SVM), may have slower training times and lower performance when compared to XGBoost. Therefore, based on the data and analysis requirements, it was determined that the combination of RStudio and XGBoost was the most suitable option [28][29][30].…”

Automated Built-Up Infrastructure Land Cover Extraction Using Index Ensembles with Machine Learning, Automated Training Data, and Red Band Texture Layers

“…Abdi [52] found similar OA results across four dates over one site when comparing SVM (0.758), extreme gradient boosting (0.751), RF (0.739), and deep learning (0.733). Ramdani and Furqon [53] found better RMSE values when using XGBoost than Artificial Neural Network (ANN), RF, and SVM (respectively 1.56, 4.33, 6.81, and 7.45) when classifying urban forest at a single site. Georganos et al [54] found that Xgboost, when parameterized with a Bayesian procedure, systematically outperformed RF and SVM, mainly with larger sizes of training data, over three sites.…”