Loading...
Dr. M. Leelavathi is an Assistant Professor in the Department of Electrical and Electronics Engineering at NPR College of Engineering and Technology, Dindigul, Tamil Nadu, India. Her research interests include Artificial Intelligence, renewable energy systems, electrical engineering, intelligent control systems, and predictive analytics. She actively contributes to research and academic development in advanced engineering technologies.
Meteorological forecasting and climate modelling are essential scientific fields that aid agriculture, disaster response, aviation, transportation, water resource administration, renewable energy development, and ecological sustainability. Traditional numerical weather forecasting models depend on intricate physical equations and advanced processing capabilities, yet frequently fail to precisely represent nonlinear atmospheric dynamics and swiftly evolving climatic trends. The amalgamation of Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), Internet of Things (IoT), satellite remote sensing, cloud computing, and Big Data Analytics has markedly improved forecasting precision through the facilitation of astute analysis of extensive meteorological datasets. Deep learning frameworks including Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Transformer Networks, and Graph Neural Networks (GNN) have exhibited remarkable efficacy in forecasting meteorological phenomena, precipitation, temperature, wind velocity, air quality, and prolonged climate fluctuations. This chapter delineates the principles, framework, artificial intelligence methodologies, applications, obstacles, and prospective research avenues related to AI-driven weather forecasting and climate prediction.