Urban areas are increasingly facing dual challenges of thermal discomfort and flooding, both aggravated by anthropogenic climate change. Addressing these hazards requires integrative computational modelling and machine learning frameworks that can assess, predict, and optimize the role of green adaptation strategies.
This session invites contributions that investigate how urban greening, from large-scale green infrastructure to fine-scale vegetation attributes such as species density and leaf morphology, can mitigate urban heat island intensity and thermal stress. We also welcome studies demonstrating how green infrastructure reduces flood impacts by attenuating flood peaks, enhancing infiltration, and protecting built environments.
We particularly encourage approaches that integrate urban climatology, hydrology, ecology, and data science, including:
Modelling of heat-flood interactions under varying green adaptation scenarios.
Machine learning and computational methods for hazard prediction and resilience assessment.
Modelling urban vegetation impacts on microclimate, runoff reduction, and biodiversity.
Urban heat island analyses and strategies for mitigation through green design.
Comparative studies across climate zones, cities, or adaptation typologies.
By bridging climate adaptation science with computational innovation, this session will highlight how nature-based solutions can build climate-resilient cities under global change.