UAE: New AI system shows what streets, communities likely to fare worst in rains

Abu Dhabi-based Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) is currently researching how artificial intelligence (AI) can be used to address urban planning challenges worldwide, particularly in response to the increasing frequency of extreme weather events caused by climate change.

In the wake of the recent unprecedented weather system on April 16 across the Gulf region, including the UAE, a team of researchers and students at MBZUAI, led by Associate Professor of Computer Vision Dr. Salman Khan, has developed an automated satellite data analysis prototype for flood assessment by combining AI and computer vision techniques.

The researchers focused on three specific areas: the Palm Jumeirah in Dubai, the Musaffah area in Abu Dhabi, and the Al Buraimi region in Oman. They utilized available satellite data to compare remotely sensed imagery before and after the storm. The goal of the analysis is to provide a valuable change detection tool for local municipalities and authorities to quickly assess the impact of heavy rains.

The analysis tool can accurately identify roads heavily affected by water accumulation following extreme rain events (highlighted as yellow lines overlapping flooding areas) and pinpoint critical infrastructure such as hospitals, schools, restaurants, malls, industrial complexes, residential areas, and population clusters that may be at risk.

The university intends to collaborate with UAE government authorities such as the Environment Agency – Abu Dhabi (EAD) and the Department of Municipalities and Transport (DMT), as well as with municipalities, local developers, and the UAE flood assessment committee to present their findings.