AIWFF: A Machine Learning based Framework for Automatic Weather Forecasting

Abstract

In the contemporary era witnessing global warming effects, weather is a dynamic phenomenon which is highly uncertain. The conventional approaches that rely on certain physical processes governing atmosphere are capable of serving a great deal in weather forecasting. However, robustness to perturbations is still desired. In this content Artificial Intelligence (AI) innovations assume significance to bring about more reliable forecasting alternative which may complement conventional methods. In this paper, we proposed a framework known as AI-enabled Weather Forecasting Framework (AIWFF) which exploits machine learning (ML) models that are robust to time series data and underlying perturbations for improving forecasting performance. An algorithm known as Learning based Intelligent Weather Forecasting (LIWF) is proposed and implemented. This algorithm has required pre-processing, feature section and a pipeline of ML models to learn from data and then forecast weather more accurately. Another algorithm known as Hybrid Method for Feature Selection (HMFS) is proposed to leverage training quality in LIWF algorithm. The framework results in three trained knowledge models saved to secondary storage. These models are known as Random Forest Regressor, Linear Regressor and Decision Tree Regressor. An application with Graphical User Interface (GUI) is developed to make use of these knowledge models and provide forecasting on user requests. The empirical results revealed that the proposed framework shows better performance.