Linear regression with Fibonacci-derived polynomials for temperature prediction model

This research work explores the integration of Fibonacci-derived polynomial and linear equations from Fibonacci numbers into a machine learning framework for predictive modeling of environmental datasets, such as wind speed, temperature, and humidity. The research aims to evaluate the effectiveness of combining deterministic mathematical equations with traditional machine learning techniques to improve prediction accuracy and uncover hidden patterns in natural datasets. This novel approach was implemented on a number of models which showed a good result for further research. The linear and Fibonacci-derived polynomial equations showed features of machine learning and since the Fibonacci pattern have been adopted in natural science, this technique of using the deterministic mathematical equation for feature engineering became fitting for natural dataset, the option of working with time series and environmental dataset have shown encouraging result and an above average accuracy.