Description:

Weather patterns in cities and their surroundings are changing due to modifications in land surface characteristics and a warming planet. As a result, people living in urban areas are at higher risk due to the extreme weather events which are happening more frequently.  In the coming decades, more people are expected to move to urban areas and the construction of new high-rise buildings and highways are expected to expand.  Hence, the demand on built infrastructure and its vulnerability to weather-related events would increase in the future warmer climate. Due to the advancement of the field of urban meteorology with the development of urban canopy models, observing systems and creation of resilient solutions which take into account both simulation and instrumentation frameworks, and feedback from the community and stakeholders, we are currently in a better position to understand and evaluate the risk from extreme weather events in urban areas. This has led to more effective dissemination of urban weather information to decision makers.  For example, recently, the US Department of Energy (DOE) has funded four Urban Integrated Field Laboratories for the advancement of urban science and to better understand the two-way interactions between cities and climate, especially from the perspective of impacts on disadvantaged communities.  Independently of this progress in the field of urban science, has been the maturation of openly available Artificial Intelligence (AI) technology in both deep learning and generative (e.g., large language) models.  Their potential application to further improve urban-scale modeling or enabling more effective decision making under uncertainty needs to be explored, which could lead to the development of new resilient solutions.

For this proposed session, we would like to have abstracts submitted on the following topics:

Use of high-resolution building morphology and other urban land use/land cover data sets in urban weather and climate models

Coupling of atmospheric models from global to urban scales and their applications, including but not limited to those related to weather impacts such as water availability, energy use, air quality, infrastructure damage, etc.

Applications of Generative AI and deep learning models to urban-scale modeling and applications

Applications of machine learning tools for decision support in urban planning, city operations and creation of sustainable cities

Innovative techniques combining physical and data-driven models at fine scale/urban scale

Projects supported by the US Department of Energy Integrated Urban Integrated Field Laboratories program

For further information, please contact:

Dr Mukul Tewari (mtewari@us.ibm.com)

Dr Francisco Salamanca (fsalaman@asu.edu)