Embedded Files
Engr. Dr Ihsan Ullah Khalil
Assistant Professor of Artificial Intelligence and Energy Policy
Pakistan Navy Engineering College, PNS Jauhar, Karachi
Engr. Dr Ihsan Ullah Khalil
Assistant Professor of Artificial Intelligence and Energy Policy
Pakistan Navy Engineering College, PNS Jauhar, Karachi
National University of Sciences and Technology, NUST, Pakistan
National University of Sciences and Technology, NUST, Pakistan
Dr. Ihsan Ullah Khalil received his PhD with a specialization in artificial intelligence from the NUST College of Electrical and Mechanical Engineering, where he developed robust, data-driven methodologies for fault forecasting and classification in photovoltaic systems using state-of-the-art deep learning models, including transformer architectures and Gaussian process regression. His approaches emphasize early prediction and model interpretability, positioning statistical machine learning and geometric deep learning as a cornerstone for intelligent condition monitoring and decision support. These innovations have been published in prestigious, peer-reviewed journals, reflecting high scholarly impact and methodological relevance.
Dr. Ihsan Ullah Khalil received his PhD with a specialization in artificial intelligence from the NUST College of Electrical and Mechanical Engineering, where he developed robust, data-driven methodologies for fault forecasting and classification in photovoltaic systems using state-of-the-art deep learning models, including transformer architectures and Gaussian process regression. His approaches emphasize early prediction and model interpretability, positioning statistical machine learning and geometric deep learning as a cornerstone for intelligent condition monitoring and decision support. These innovations have been published in prestigious, peer-reviewed journals, reflecting high scholarly impact and methodological relevance.
Dr. Khalil’s academic portfolio also encompasses advanced research on intelligent algorithms for adaptive system forecasting, hybrid machine learning frameworks, and model-agnostic explainability techniques that align with global trends in autonomous learning systems. He actively shapes the theoretical foundations and practical implementations of physics-informed large language models and hybrid AI agents that integrate domain physics with deep representation learning for autonomous reasoning and prediction.
Dr. Khalil’s academic portfolio also encompasses advanced research on intelligent algorithms for adaptive system forecasting, hybrid machine learning frameworks, and model-agnostic explainability techniques that align with global trends in autonomous learning systems. He actively shapes the theoretical foundations and practical implementations of physics-informed large language models and hybrid AI agents that integrate domain physics with deep representation learning for autonomous reasoning and prediction.
Beyond algorithm development, Dr. Khalil’s work critically intersects with energy policy research, addressing how AI-driven technologies influence energy planning, reliability, and renewable adoption pathways. His research work offers rigorous insights into optimising renewable energy performance under policy constraints and regulatory frameworks, informing both academic debate and industry practice.
Beyond algorithm development, Dr. Khalil’s work critically intersects with energy policy research, addressing how AI-driven technologies influence energy planning, reliability, and renewable adoption pathways. His research work offers rigorous insights into optimising renewable energy performance under policy constraints and regulatory frameworks, informing both academic debate and industry practice.
Dr Khalil has published 35+ high-impact research articles in leading international journals and top peer-reviewed conferences, and he serves as an active reviewer for several esteemed journals, including IEEE Transactions on Energy Conversion, IEEE Latin America Transactions, Energy Reports, and other high-impact journals.
Dr Khalil has published 35+ high-impact research articles in leading international journals and top peer-reviewed conferences, and he serves as an active reviewer for several esteemed journals, including IEEE Transactions on Energy Conversion, IEEE Latin America Transactions, Energy Reports, and other high-impact journals.
His core research interests include machine learning, deep learning, natural language processing, physics-informed LLM-based autonomous systems, intelligent forecasting models, and the intersection of AI with energy policy analysis.
His core research interests include machine learning, deep learning, natural language processing, physics-informed LLM-based autonomous systems, intelligent forecasting models, and the intersection of AI with energy policy analysis.
Page updated
Google Sites
Report abuse