Time Series Methods in Meteorology: A Review of Predictive Models and Applications

Abstract

The accurate prediction of time series data holds substantial significance in various fields, enabling informed decision-making and resource optimization. In this study, temperature variations over time are predicted using the Autoregressive Integrated Moving Average (ARIMA) model. Reliable temperature projections are more important now than ever because of climate change and its effects. For time series prediction problems, the ARIMA model—which is well-known for its ability to capture temporal dependencies in data—can be applied. It is possible to apply and adjust this model to take into account the unique features of temperature data, like trends and seasonality. To ensure quality and consistency, historical temperature data is gathered and pre-processed. Using machine learning algorithms, the suggested works forecast the weather based on variables like temperature, wind, and humidity. The weather prediction industry has had success with computer-aided prediction systems that use machine learning models. The experiment emphasises the value of applying cutting-edge data analysis methods to practical problems and shows how larger prediction systems may be refined even further.