A Novel Approach to Weather Forecasting using Regression Analysis

The impact of weather on our lives can be significant. Variations in weather can impact a broad spectrum of human endeavors, including transportation and agriculture. An extensive number of researchers have expressed interest in weather forecasting because of its impact on human life globally. Since deep learning techniques have emerged in the last ten years, massive weather observation data has become widely available, and information and computer technology have advanced, a variety of research interests have led researchers to explore hidden hierarchical patterns in the vast amounts of weather datasets used for weather forecasting. Because Decision Tree Regression can simulate intricate relationships between input characteristics and the target variable, it is a popular non-linear machine learning approach for weather prediction. Regression analysis is a powerful statistical technique used in weather forecasting to forecast constants like humidity, temperature, and precipitation amounts based on historical weather data. This section covers various regression methods used in weather forecasting, including their implementation and advantages. Since time series analysis predicts future values based on previously observed values throughout time, it is essential to weather forecasting. Weather data inherently forms a time series, making this approach particularly suitable for forecasting. This section provides an overview of time series analysis and its application in weather forecasting. This paper’s primary goal is to track and report on weather conditions so that people can be prepared and take the appropriate precautions to lessen the damage caused by natural disasters by forecasting them. The study is mostly done for short-term forecasting. Due to the high non-linear dynamic atmospheric phenomena, intelligent systems perform a far better analysis of these phenomena’ behaviour than can conventional methods. We will forecast the weather by examining temperature, pollution, humidity, and pressure using different methods.