A lot of our work uses satellite images that need to go through a series of processes before they can be in a shape that can be further analyzed to create urban data. In this case, we use a deep-unfolded method to remove clouds and their shadow obstructions from the images. Clouds, together with their shadows, usually occlude ground-cover features in optical remote-sensing images. This hinders the utilization of these images for a range of applications such as earth observation, land-cover classification, and other urban data uses. We propose a deep unfolded and prior-aided robust principal component analysis (DUPA-RPCA) network for removing clouds and recovering ground-cover information in multitemporal satellite images. This is the first deep-unfolded method for cloud removal and has been published in IEEE Signal Processing Letters.

We are recently visited the Rescue 1122 Headquarters in Lahore to present their findings and recommendations as part of the Grand Challenge Fund project. The team, led by the PI, Dr. Momin Uppal, has been working on optimized ambulance allocation and mitigating road traffic crash (RTC) hotspots in Lahore, in collaboration with Rescue 1122. Some preliminary results, recommendations, and suggestions were put forward, which the team believes are a significant milestone towards safer roads for the citizens of Lahore. The Director General of Rescue 1122, Dr. Rizwan Naseer, was in attendance among several senior officials of the organization. Dr. Naseer appreciated the efforts of Team UrbanTech, and expressed his desire to extend this fruitful collaboration. Members of Team UrbanTech also commended Dr. Naseer’s enthusiasm towards a data-centric problem-solving approach, and his willingness to lead a data revolution in Pakistan’s public sector.

The project PI, Dr. Momin Uppal was recently invited by The Management and Professional Development Department (MPDD), Government of the Punjab to conduct a training on the “Role of new technologies in management and governance”. Dr. Uppal spoke about how digital transformation along with associated technologies could be used in Pakistan’s public sector to increase citizen engagement, improve transparency, enhance coordination among different agencies, as well as improve processes, regulations, services, and policies. A major focus was on the potential of data-driven decision making in the public sector. The potential was demonstrated through specific examples from urban mobility, waste management, and emergency response services. Dr. Uppal delivered the training remotely while being quarantined at home – something that would have been unimaginable a couple of years ago. Technology has come a long way indeed.