Accurate weather forecasting with dominant gradient boosting using machine learning

Abstract

This Paper examines the interesting topic of weather forecasting using ML. From kaggle.com, there is an extensive list of daily weather records for a Seattle dataset. In this chapter, gradient boosting outcomes are revealed as a result of careful data preparation and thorough examination of several machine learning models such as K-Nearest Neighbors, Support vector machine, Gradient Boosting, XGBOOST, logistic regression, and random forest class Its 80.95% accuracy was outstanding. ML traverses atmospheric dynamics that form a basis for weather predictions. It uses a highly developed method that enables it to predict the complex trends in the weather. In addition, machine learning algorithms are increasingly important for detecting non-linear relationships and patterns from large sets of complex data with time. It is critical for meteorologists in overcoming uncertainties associated with atmospheric dynamics to improve prediction. Gradient Boosting – a weather forecasting perspective in an interdisciplinary landscape involving weather science and machine learning. The current research on ML for weather forecasting has been very useful.