In order to better understand, mitigate the effect of climate change on cities and urban areas, there is a need to sense, capture and analyse heterogeneous and multi-modal data sources for monitoring its immediate and longer-term effects. The development and application of Machine Learning (ML), quantum computing frameworks and computational optimisation approaches can offer a range of possible solutions. More effective and innovate pervasive data-driven ML models and integrated systems need to be developed focusing on topics such as though not limited to:

To facilitate solutions for managing the effects of climate change on city infrastructures there is a need to leverage the power of AI and ML methodologies for handling highly complex, uncertain and stochastic problems to create explainable insights and integrated systems. ML approaches such as deep learning neural networks can enable feature extraction, predictive modelling with applications such as detection of objects (cars, pedestrians) localising weather events and effects or identifying incidents. Generative AI solutions created using high dimensional multi-modal data and leveraging foundation AI models (large transformer network based models) can be used to generate unique domain specific solutions spanning interactive conversational and recommendation systems to generate planning and decision support. Representational learning and reasoning methodologies for handling imprecise and uncertain data (sensory, user-rated or defined concepts, subjective opinions) providing an approach for approximate reasoning and modelling based on the use of human interpretable rules, graph and causal models that can be used for inference and decision-making. Deep learning and meta heuristic optimisation algorithms based on the processes of natural selection, collective and cooperative intelligence and reinforcement can be used for modelling and optimsing complex and stochastic systems. These and new emerging AI approaches can be co-designed and developed as part of embedded AI systems, IoT, edge and fog computing based typologies, federated learning frameworks, data driven digital twins and intelligence augmentation virtual and augmented reality. The effective application, co-design of solutions with domain stakeholders and adoption of human centered architectures will provide robust, effective and scalable solutions for making cities digitally resilient to climate change effects.