AI and machine learning (ML) have emerged as powerful tools for urban climate modelling, enabling more efficient model calibration, improved predictive capabilities, and integration of vast, complex datasets. Recent advances in ML algorithms have provided novel methods for simulating urban climate processes, such as energy demand, heat island effects, and air quality. However, challenges include the interpretability of AI-driven models and integrating ML approaches with physical-based models.

We encourage submissions that explore innovative applications of AI/ML in urban climate prediction, hybrid modelling approaches, and data assimilation using machine learning. Studies that leverage big data or focus on improving forecast accuracy and model interpretability are particularly welcome. Topics of interest can be AI/ML applications in urban heat, air quality, and energy demand modelling, hybrid models combining ML with physical models, real-time data assimilation using machine learning, AI-driven optimization of urban climate adaptation strategies, etc.