Addressing climate change requires a group effort from a multitude of fields. ADSC is doing its part by using artificial intelligence (AI) to assess how natural disasters caused by climate change could impact urban infrastructure. 

“Climate change has caused an increase in the intensity and frequency of extreme weather events with severe consequences on the urban infrastructure,” says Partha Biswas, Senior Research Engineer at ADSC. “We need to be prepared for and respond to hazardous events and disturbances related to climate.”

Disaster Resilience Assessment, Modeling, and Innovation – Singapore (DREAMIN’ SG) models various infrastructure systems, assessing their resilience, identifying features, and developing solutions to improve resilience. Using AI, the project aims to predict the recovery capabilities of the urban infrastructure in case of a disaster such as flood, cyclone, etc.

“The role of ADSC is to adopt AI, machine learning algorithms to be specific, to predict resilience and interpret the machine learning models to identify features that affect resiliency the most,” says Biswas. “The involvement of the current technology like machine learning paves the path forward for assessment and prediction of system resilience and helps extract information related to system failures.”

Though the project is based in Singapore with specific focus on the climatic conditions and disasters in south-east Asia (SEA), climate change is a global phenomenon and modern urban infrastructure is somewhat similar.

“The guidelines developed by this research can be transformed into design requirements to innovate new technologies and also can be readily adapted to the local requirements for improving resilience,” says Biswas. “Moreover, an improved, resilient and robust urban infrastructure system would benefit the masses both socially and economically.”

Current models consider power, water and transport systems; however, the model can be extended by incorporating other sectors like telecommunications, manufacturing, and more.

“This model can be used as a baseline to create country-wide power grid and other infrastructure model for resilience assessment under severe climatic conditions and natural disasters,” says Biswas.

The project is hosted by the Singapore-ETH Centre in collaboration with Advanced Digital Sciences Centre (ADSC), Singapore University of Technology and Design (SUTD), National University of Singapore (NUS), University of Cambridge and Delft University of Technology.