A new online Hong Kong COVID-19 Hotspot Map has gone live which provides a visualisation of the real-time and dynamic geographic distribution of COVID-19 cases in the city. 

The interactive map was developed by a research team led by Hong Kong Baptist University (HKBU), along with the University of Macau and The University of Hong Kong.

WHAT IT'S ABOUT

The map presents territory-wide data on COVID-19 infection cases. Its real-time data comes from the Interactive Map Dashboard run by the Hong Kong government. 

It shows infection risks in different locations in a colour scheme ranging from purple for the lowest risk level to red for the highest. Evolving risk levels in each location are presented through a dynamic movement of colour patterns on the map.

Moreover, users can zoom in or zoom out to browse COVID-19 risk levels at broader or more specific geographical sites.

The colour visualisation of COVID-19 risk levels is based on the automatic, real-time updating and computation of infection case data using a computational tool for spatial-temporal data analysis called Kernel Density Visualisation (KDV). 

Using the new computation methods, the hotspot map's resolution can be increased to a high-definition resolution (1376 x 960 pixels). It can also process one million data points in less than 0.5 second of response time.

WHY IT MATTERS

Having timely and accurate information on the geographic distribution of COVID-19 cases is key to the implementation of effective infection control measures, as well as the allocation of medical resources to fight the pandemic. This information is also useful to the public in understanding health risks. 

Thus, developing a system that can update and process high-resolution images timely is also important in this endeavour. However, many existing visualisation software tools cannot support high-resolution KDV with million-scale datasets. Moreover, current computation methods of conventional KDV cannot support the real-time creation of dynamic images.

To address this need, the research team developed new computation methods to enhance the KDV's visual creation. Experiments with these novel methods have shown response time to be 100 times faster than most advanced methods currently available.

THE LARGER TREND

The launch of the interactive COVID-19 map comes as Hong Kong is seeing an increase in daily cases over the past two weeks, going above the 8,000 mark from 5,000 earlier. The city has recently relaxed social distancing protocols in a bid to further reopen its economy. 

In August, the Hong Kong University of Science and Technology unveiled its CovidInArea mobile app which also visualises COVID-19 risks. It uses open data from the Department of Health to generate a real-time heatmap of places where COVID-19 cases are reported. Available on both Android and iOS devices, the app runs an automatic check of COVID-19 hotspots by providing real-time GPS support. No user registration is required to access the mobile map and no personal information is also collected. 

ON THE RECORD

"The newly developed algorithms and solutions can support more KDV-based geospatial analysis tasks. With their application, the functionalities of the Hong Kong COVID-19 Hotspot Map were greatly enhanced, making it a useful tool to monitor the risks of COVID-19 in the community. It can assist health authorities as well as individual citizens in introducing informed, effective measures against the pandemic," said Xu Jianliang, research lead and professor and head of the Department of Computer Science at HKBU.

The research team is also looking to apply its new computation methods for KDV in traffic hotspot detection, crowd control in tourist attractions, property prices visual analysis and real-time weather resources management.