The Covid-19 pandemic and its consequences have promoted rethinking of questions of public health, urban sustainability, and urban planning. Understanding the relationship among socio-spatial, environmental and cultural factors is essential to guide planning, including to prevent future pandemics or other health issues. This includes uncovering unexpected patterns of influence that are often difficult to comprehensively study. For example, the lockdown policy--implemented to curb spreading of the virus—has resulted temporarily in reduced human activity and therewith improved urban environments including through better air quality, greening and mitigation of urban heat island effects. Analyzing such complex systems is challenging as it demands digitalising and processing data on socio-cultural and environmental factors, and requires multi-disciplinary collaboration. Also, data needed for such analysis often comes from multiple heterogenous sources, calling for data integration or data fusion workflows. Additionally, such datasets tend to be very big and multi-dimensional, making manual statistical analysis hard or infeasible. Here, data science and artificial intelligence methods can provide new approaches to process such high-dimensional multi-source data to uncover yet unknown patterns. To inform future actions, results achieved with such methods need to be understandable, verifiable, and explainable.
We launch this collection to promote communication and collaboration among scholars from multiple disciplines using novel methodologies, including data science and AI, to study data from a large variety of socio-cultural, public health and environmental factors in order to inform public health management, urban planning, and urban sustainability management themes.
- Machine learning, explainable AI, statistical approaches in the context of public health or urban planning / sustainability
- Data-driven public health, urban sustainability, urban planning
- Data-driven digital humanities including changes of socio, economic and cultural features over time
- Analysis of time series of environmental factors including air quality, vegetation, land surface temperature, land cover, etc.
- Multi-source data including earth observation data, socio-economic data, citizen science data, etc.
