Dr Zhou Zhou

I am a Lecturer (Assistant Professor) in Data-Centric Engineering in the Department of Engineering at the University of Exeter, where I am a member of the Autonomy, Decision and Control (ADC) group. My research focuses on the development of machine learning methods for spatiotemporal data analytics, with particular emphasis on forecasting methodologies and their applications in energy, transportation, robotics, and earth sciences. More broadly, my work seeks to explore how data-driven machine learning can support the engineering of a greener and more sustainable future, in alignment with Exeter's strategy 2030.

Prior to joining the University of Exeter, I was a Postdoctoral Researcher in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST), where I was in the DeepForecast group led by Professor Dit-Yan Yeung. My work there included an ITF-funded project in collaboration with the Hong Kong Observatory, focusing on extreme weather prediction using state-of-the-art deep learning methods. I also contributed to an RIF-funded project in partnership with Hongkong Electric, where we developed spatiotemporal graph neural network models for electricity load and trend forecasting.

I received my PhD in Electrical Engineering from Xi’an Jiaotong University, where my research focused on data analysis and management for power equipment systems, advised by Professor Gangquan Si. During my doctoral studies, I was also a Visiting PhD Researcher at the Leiden Institute of Advanced Computer Science, Leiden University. There, as a member of the ADA research group, I worked under the supervision of Professor Holger Hoos and Professor Mitra Baratchi on automated machine learning and data mining methods for spatiotemporal data analytics.

My research interests include:

• Spatiotemporal data analytics: spatiotemporal modelling, multimodal data fusion
• Time-series data mining: compression, clustering, forecasting, anomaly detection
• Machine learning: supervised/unsupervised learning, continual learning, physics-informed machine learning, distributed machine learning, automated machine learning 
• Deep learning: spatiotemporal graph neural networks, generative models
• AI for science and engineering: traffic forecasting, extreme weather prediction, renewable energy forecasting, power load forecasting and monitoring, predictive maintenance

PhD Opportunities:

I welcome enquiries from prospective PhD candidates whose interests align with my research areas. Please feel free to reach out with your CV and research plan if you are interested in working with me.