Weather forecasting is essential in industries like agriculture, energy supply, and transportation, where accuracy in forecasting is vital. The fundamental goal of this research is to create an artificially intelligent platform for predictive modeling to aid in long-term environmental management. For regional and national weather forecasts, four standout methods are Seasonal AutoRegressive Integrated Moving Average (SARIMA), Long Short-Term Memory (LSTM) model, AutoRegressive Integrated Moving Average (ARIMA), and Temporal Convolutional Network (TCN). These models use input data such as mean temperature, pressure, humidity, and wind speed to forecast daily weather conditions. The dataset obtained from Kaggle assesses these forecasting approaches, spans four years, from 2013 to 2017, and analyzes the models based on four performance measures Mean Absolute Error (MAE), Root Mean Squared Error (RMSE) Mean Squared Error (MSE), and R-Squared ( \(R^{2}\) ) score. This study compares traditional time series models like ARIMA and SARIMA versus the modern deep learning models, LSTM and TCN, under predictive accuracy in weather forecasts and explores under what conditions each model is superior. LSTM outperforms the other three models as it integrates multiple features and adapts to different types of time series data with minimal manual intervention, having the RMSE of 0.055, MAE of 0.003, and \(R^{2}\) Score of 0.91.