Enhancing Weather Prediction Accuracy with Gradient Boosting: A Machine Learning Approach

This research focuses on the integration of Machine Learning (ML) in predicting the climate with the help of daily recorded weather dataset of Seattle [33] which we obtained from the Kaggle. This research focuses on implementing and analyzing multiple ML techniques such as Naive Bayes, K-Nearest Neighbors (K-NN), Support Vector Machine (SVM), Gradient Boosting, XGBoost, and Decision Tree. XGBoost able to get to the top position with an accuracy rate of 87.90% which speaks volume of its performance. This integration of ML techniques is useful in understanding the weather prediction which is highly complex due to multiple atmospheric changes. Such modern methods help in recognizing the more complex non-linear features and trends within weather data. Machine learning algorithms makes it possible to detect such tendencies from complex datasets over time. ML enhances weather prediction approaches by learning and analyzing patterns from historical data and real time data. This paper highlights the importance of extreme gradient boosting in weather forecasting by providing examples of its successful applications within the interdisciplinary field of meteorology and ML. This study compares different algorithms for best accuracy and also points to the increasing significance of ML in the enhancement of weather forecast models.