This PhD research harnesses weather, air quality data, and walkability metrics to provide insights into urban planning's multifaceted impacts, emphasizing the importance of emergency preparedness. Despite the plethora of data, including satellite measurements, accessing it is complex due to the lack of inter-departmental collaboration, standardized data-sharing protocols, and incentives to improve data pipelines. Our eforts form foundational components of an 'Urban Scale Digital Twin', pushing the boundaries of traditional urban planning towards a more holistic, data-informed approach that encapsulates the evolving needs of urban residents. The project includes a comprehensive mapping study on Digital Twins (DTs) for city and territory management.
CEUR
ceur-ws.org the accuracy of the resulting dashboards, which is pivotal for any urban planning decision in such vulnerable territories. This project seeks to develop a comprehensive strategy that spans multiple public departments, promoting standardization and seamless data utilization across various platforms. What approaches can be developed to equip local administrations with tools for disaster preparedness? The project investigates the development of a simulation toolkit for disaster preparedness that surpasses existing solutions by utilizing open-source tools and flexible data inputs. The toolkit is designed to be interactive and customizable, with many settable parameters, making it adaptable for various personas and scenarios. Unlike previous studies, which often provide static or narrowly focused tools, this project aims to create a dynamic and multi-persona toolkit that enhances collaboration and preparedness at the local administration level. The focus on open-source tools and optional data inputs ensures broad accessibility and applicability, addressing gaps in current disaster preparedness methodologies.
Methods and evaluation: To address these research questions, we combined data visualization,
automated data extraction, and comprehensive data preprocessing as partially outlined in Figure 2 and
described in this section. We automated the extraction of information from reputable Public Sector data
lakes (Data Gathering Figure 2) without manual intervention, ensuring the comprehensiveness and
reliability of our dataset. Key datasets included: Reconstruction Data-sets from USRA and USRC,
providing information on post-earthquake reconstruction activities; Air Quality Data-sets from CeTEMPS,
ARPA, and ESA, ofering insights into air quality through high-resolution pollutant measurements
and weather summaries; Walkability and Service Accessibility Dataset, developed by ESA and local
entities, evaluating pedestrian-friendliness and service accessibility in urban areas. In urban
environments, variations in aerosols were measured using satellite data and on-the-ground measurements,
serving as an indicator for air quality assessment. The larger goal was to develop a dashboard for
city sustainability indices, providing real-time information about air quality and its impact on public
projects and emergency situations. Preprocessing the diverse data involved data pivoting, imputation,
and normalization to ensure consistency, quality, and usability. Challenges included temporal and
spatial granularity diferences, inconsistent data formats, missing values, and difering units. Accurate
merging required sophisticated algorithms, domain expertise, and iterative refinement using Python
libraries (Preprocessing Phase Figure 2) Data interpolation using Machine Learning models helped
to produce reliable sustainability dashboards in areas less covered by sensors, we then overlayed a
mapping schema with intuitive aliases and comprehensive explanations. Plotly and Grafana have been
interchangeably used depending on the plotting requirements and the resulting dashboards are easily
deployable on SoBigData [
Discussion and future work: Overcoming human bottlenecks in public sector data gathering remains
a challenge, as web portals are sometimes updated with delays of up to six months. For public
administrations with limited resources, automating this process is cost-efective and ensures a consistent flow of
accurate, up-to-date information. Implementing thematic dashboards can enhance citizen engagement
by providing real-time, easily interpretable data, aiding in better decision-making so future work will
consist in integrating systems for automatic alerts and actionable items within the platform. On a more
specific note, during emergencies, real-time data availability is crucial. And simulators like the one
proposed [
Acknowledgment: This work has been funded by ”ICSC – Centro Nazionale di Ricerca in High Performance Computing, Big Data and Quantum Computing”, funded by European Union – NextGenerationEU. The views and opinions expressed are solely those of the authors and do not necessarily reflect those of the European Union or the European Commission. Neither the European Union nor the European Commission can be held responsible for them.