Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Comparison of Machine Learning Algorithms for Predicting Sea Surface Temperature in the Great Barrier Reef Region

Dennis Quayesam, Jacob Akubire, Oliveira Darkwah

TL;DR

Random Forest and XGBoost significantly outperform ridge regression and ridge regression in terms of predictive accuracy, as evidenced by lower Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Prediction Error (RMSPE).

Abstract

Predicting Sea Surface Temperature (SST) in the Great Barrier Reef (GBR) region is crucial for the effective management of its fragile ecosystems. This study provides a rigorous comparative analysis of several machine learning techniques to identify the most effective method for SST prediction in this area. We evaluate the performance of ridge regression, Least Absolute Shrinkage and Selection Operator (LASSO), Random Forest, and Extreme Gradient Boosting (XGBoost) algorithms. Our results reveal that while LASSO and ridge regression perform well, Random Forest and XGBoost significantly outperform them in terms of predictive accuracy, as evidenced by lower Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Prediction Error (RMSPE). Additionally, XGBoost demonstrated superior performance in minimizing Kullback- Leibler Divergence (KLD), indicating a closer alignment of predicted probability distributions with actual observations. These findings highlight the efficacy of using ensemble methods, particularly XGBoost, for predicting sea surface temperatures, making them valuable tools for climatological and environmental modeling.

A Comparison of Machine Learning Algorithms for Predicting Sea Surface Temperature in the Great Barrier Reef Region

TL;DR

Random Forest and XGBoost significantly outperform ridge regression and ridge regression in terms of predictive accuracy, as evidenced by lower Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Prediction Error (RMSPE).

Abstract

Predicting Sea Surface Temperature (SST) in the Great Barrier Reef (GBR) region is crucial for the effective management of its fragile ecosystems. This study provides a rigorous comparative analysis of several machine learning techniques to identify the most effective method for SST prediction in this area. We evaluate the performance of ridge regression, Least Absolute Shrinkage and Selection Operator (LASSO), Random Forest, and Extreme Gradient Boosting (XGBoost) algorithms. Our results reveal that while LASSO and ridge regression perform well, Random Forest and XGBoost significantly outperform them in terms of predictive accuracy, as evidenced by lower Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Prediction Error (RMSPE). Additionally, XGBoost demonstrated superior performance in minimizing Kullback- Leibler Divergence (KLD), indicating a closer alignment of predicted probability distributions with actual observations. These findings highlight the efficacy of using ensemble methods, particularly XGBoost, for predicting sea surface temperatures, making them valuable tools for climatological and environmental modeling.

Paper Structure

This paper contains 10 sections, 10 equations, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. LASSO
  4. Ridge Regression
  5. Random Forest
  6. XGBoost
  7. Model Evaluation
  8. Discussion of results
  9. Correlation Analysis
  10. Conclusion

Figures (8)

  • Figure 1: Correlation between SST and other variables
  • Figure 2: Trajectories of Predictor Coefficients in Lasso Regression as a Function of Logarithmic Lambda for Sea Surface Temperature
  • Figure 3: Impact of Regularization Parameter on Model Performance in Lasso Regression
  • Figure 4: Evolution of Coefficients in Ridge Regression with Varying Logarithmic Lambda
  • Figure 5: Mean Squared Error as a Function of Logarithmic Lambda in Ridge Regression
  • ...and 3 more figures