{"id":75570,"date":"2024-04-13T12:00:00","date_gmt":"2024-04-13T04:00:00","guid":{"rendered":"https:\/\/www.jumpstartmag.com\/?p=75570"},"modified":"2024-09-24T19:42:46","modified_gmt":"2024-09-24T11:42:46","slug":"hk-polyu-employs-geoai-to-advance-urban-development","status":"publish","type":"post","link":"https:\/\/www.jumpstartmag.com\/hk-polyu-employs-geoai-to-advance-urban-development\/","title":{"rendered":"HK PolyU Employs GeoAI to Advance Urban Development\u00a0"},"content":{"rendered":"\n

PolyU’s GeoAI research aims to develop solutions for transportation, urban safety and environmental challenges.<\/em><\/p>\n\n\n\n

The Hong Kong Polytechnic University (PolyU) is leveraging geospatial artificial intelligence (GeoAI) to tackle a range of environmental and social challenges worldwide. Through its innovative application in various sectors such as transportation, urban safety, and climate change, PolyU aims to lead in transforming how societies manage and adapt to these issues.<\/p>\n\n\n\n

Prof. Qihao Weng, Chair Professor of Geomatics and Artificial Intelligence at PolyU, has founded the Research Centre for Artificial Intelligence in Geomatics (RCAIG) with the vision of making it a global research and development hub for GeoAI. Professor Weng, a recent recipient of the 2024 American Association of Geographers (AAG) Wilbanks Prize and the AAG Remote Sensing Specialty Group Lifetime Achievement Honor Award, is recognized for his transformative research in geography.<\/p>\n\n\n\n

Directions and innovations of RCAIG<\/strong><\/h2>\n\n\n\n

The research directions of RCAIG include studying human-environment interactions during urbanization and creating data products for global urban areas using Earth Observations (EO). These efforts are geared towards providing advanced urban data services and enhancing our understanding of environmental and societal changes.<\/p>\n\n\n\n

\u201cEarth observation is important as a guiding compass for understanding changes in the environment and society. Our research focuses on diverse fields including geospatial big data and AI, remote sensing, ground-based sensors, navigation and positioning, surveying and geodesy, laser scanning and photogrammetry. These technologies play a crucial role in addressing and resolving key environmental and social challenges,\u201d said Prof. Weng.<\/p>\n\n\n\n

GeoAI applications in building and environmental monitoring<\/strong><\/h2>\n\n\n\n

GeoAI technology at PolyU has significantly advanced building monitoring by enabling automatic learning to identify patterns in building features, such as color and shape. This technology is crucial for assessing disaster damage, retrieving building heights, identifying structural changes and estimating energy consumption. <\/p>\n\n\n\n

Additionally, a research team led by Ms. Wanru, an RCAIG doctoral research assistant, has created a new way to look at how cities grow. They have built a model that uses impervious surface area-based urban cellular automata (CA) to simulate changes in urban areas, providing valuable insights for sustainable development.<\/p>\n\n\n\n

The team has shared their work in an article called \u201cModeling gridded urban fractional change using the temporal context information in the urban cellular automata model\u201d, which was published in the academic journal Cities<\/em>. <\/p>\n\n\n\n

Advancing smart traffic management<\/strong><\/h2>\n\n\n\n

RCAIG is also working in the realm of smart traffic management. To enhance the efficiency of ride-hailing services, a research team led by RCAIG researcher Ms. Mingyue Xu has introduced a multi-agent order matching and vehicle repositioning system using multi-agent deep reinforcement learning. This technology can provide effective solutions to long-term spatio-temporal planning problems in transportation.<\/p>\n\n\n\n

The system addresses two important issues in the ride-hailing industry: matching ride orders with available vehicles more efficiently and sending idle cars to regions that will soon experience high demands. It promises to reduce passenger rejection rates and minimize driver idle times.<\/p>\n\n\n\n

This research was reported in the paper \u201cMulti-agent reinforcement learning to unify order-matching and vehicle-repositioning in ride-hailing services\u201d, which was published in the journal International Journal of Geographical Information Science<\/em>. <\/p>\n\n\n\n

Also read: <\/strong><\/p>\n\n\n\n