Abhishek Kallarappayi

• Machine learning and artificial intelligence in renewable energy
• Predictive maintenance systems for wind turbines
• Cold climate engineering and ice mitigation strategies
• Wind energy optimization and performance modelling
• Sustainable energy infrastructure

Abhishek Kallarappayi is a Doctoral Researcher at Coventry University within the Research Centre for Computational Science and Mathematical Modelling. His academic background is in data science and computational modelling, with a particular focus on the application of artificial intelligence to real-world engineering challenges.

He holds a Master of Science in Data Science from Coventry University, awarded with distinction, where he developed strong expertise in statistical learning, predictive analytics, and data-driven modelling. His research interests lie at the intersection of machine learning, time-series forecasting, and renewable energy systems.

Abhishek’s current doctoral research explores intelligent modelling approaches for improving wind turbine reliability in cold climates. Through interdisciplinary collaboration and industry engagement, his work aims to bridge methodological advances in artificial intelligence with practical applications in sustainable energy systems.

Title: Intelligent Wind Turbines for Cold Climates

This doctoral research investigates the development of artificial intelligence frameworks to predict atmospheric icing events and quantify their impact on wind turbine power production in cold climate environments. Atmospheric icing remains a significant operational challenge, leading to reduced energy yield, increased mechanical stress, and unplanned shutdowns. The project integrates turbine SCADA data, meteorological measurements, and ice sensor information to construct predictive time-series models capable of forecasting icing occurrence across multiple horizons.

The research adopts a systematic modelling approach, comparing machine learning and deep learning architectures while ensuring strict chronological validation to preserve operational realism. In addition to event prediction, the project examines the relationship between icing severity and power loss to support improved operational decision-making. The overall objective is to develop a robust early warning system that enhances reliability, optimises energy production, and strengthens the resilience of wind energy infrastructure operating in cold climates.