Multi-scale multi-domain geospatial data modelling

本博士学位由英国工程与物理科学研究委员会（EPSRC资助号EP/S023577/1）和英国地形测量局资助。本课题旨在将交通、水、环境和社会等不同的空间领域联系起来，从而实现跨领域、跨尺度的分析和模拟。其目的是为统一的事件响应系统开发地理空间数据基础设施和数据模型。根据联合国可持续发展目标11（建设包容、安全、有韧性和可持续的城市），城市和环境需要具备更好地应对突发事件并为之做好准备的能力。利用在智能环境中部署的物联网（IoT）和传感器，该博士将探索如何将原始数据转化为智能，支持利益相关者实时响应并提高弹性。开发一个用例，包括来自不同领域的事件类型，例如洪水、交通事故或公用事业故障，这些事件可能导致跨不同系统的中断，触发警报，并要求在涉及不同涉众的响应链上采取行动。因此，本博士的目标是利用云计算能力和空间大数据分析来处理由传感器、CCTV数据馈送和社交媒体作为数据馈送传输的大量地理空间数据。通过将来自不同涉众的知识集成到一个公共本体中，该博士学位将有助于更好地理解事件响应的未来数据模型的需求。

This PhD is funded by the Engineering and Physical Sciences Research Council of Great Britain under EPSRC grant number EP/S023577/1, and Ordnance Survey of Great Britain. This topic aims to link different spatial domains of interest such as transport, water, environment, and society and thereby enable cross-domain and cross-scale analytics and simulation. The aim is to develop a geospatial data infrastructure and data model for a unified incident response system. In line with the United Nations Sustainable Development Goal 11 to make cities inclusive, safe, resilient, and sustainable, cities and the environment need to be equipped with the ability to better respond to and be prepared for unforeseen events. Using Internet of Things (IoT) and sensors deployed in a smart environment, this PhD will explore how to transform raw data into intelligence, support stakeholders in real-time response and improve resilience. A use case is developed including incident types from different domains, such as flooding, traffic incidents or utility failures that can cause a disruption across different systems, trigger an alarm, and require actions along the response chain involving different stakeholders. Therefore, this PhD aims to use cloud computing capabilities and spatial big data analytics to process the vast amounts of geospatial data collected by sensors, CCTV data feeds and social media transmitted as data feeds. By integrating knowledge from different stakeholders into a common ontology, this PhD will contribute to a better understanding of the requirements for future data models for incident response.