Design and Implementation of an Intelligent Machine Learning-Based Weather Prediction Application

Design and Implementation of an Intelligent Machine Learning-Based Weather Prediction Application 1Dr.Sagarika Das, 2Nikita Shaw, 3Nabarun Naskar, 4Mith Biswas, 5Md. Raquif, 6Mayukh Santra 1Faculty , Dept.of Electronics and Communication Engineering, Haldia Institute of Technology, Haldia, Purba Medinipur, West Bengal 2,3,4,5,6UG student, Dept. of Electronics and Communication Engineering , Haldia Institute of Technology, Haldia, Purba Medinipur, West Bengal ABSTRACT Accurate weather forecasting is essential for agriculture, transportation, disaster management, and environmental planning. This study presents a comparative weather forecasting model using three time-series and deep learning approaches: Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), and Long Short-Term Memory (LSTM). Historical weather data containing variables such as temperature, humidity, atmospheric pressure, and rainfall are preprocessed to handle missing values, normalize the data, and identify temporal patterns. ARIMA is applied to capture linear trends and short-term dependencies, while SARIMA incorporates seasonal variations in weather patterns. LSTM, a recurrent neural network architecture, is employed to learn complex nonlinear relationships and long-term temporal dependencies. The models are trained and evaluated using appropriate error metrics, including Mean, Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The comparative analysis identifies the most effective approach for accurate weather prediction and demonstrates the potential of machine learning and deep learning techniques for reliable forecasting