Improving semantic knowledge of urban environment based on data fusion and machine learning methods

The first part of the project will be about understanding data fusion for complex urban environments. Data fusion can be performed at various stages of the processing pipeline, using different data and applying different methods. Due to such diversity, it is crucial to thoroughly understand the advantages and disadvantages of the methods and data used in data fusion and to select the most appropriate for further project development. An additional element discussed in this part of the work is using ontologies (grammar-based, knowledge-based) and their potential in semantic description of the urban environment elements.

One of this work's objectives is to compare various tools (commercial, open-source and programming based). Therefore, it is crucial to establish measures or indicators for work assessment. Determinants of quality used in this work refer to improving the results using data fusion in terms of quality, quantity, or semantic enrichment. The measures selection will be based on the information available in literature and/or industry requirements. The indicators may refer to accuracy performance, processing time, cost reduction, range of extracted information (as data vary with the information they deliver), and the application sector.

To compare different methods investigated in this project, the idea is to use mathematically simulated features (e.g., a vertical plane representing a wall) as the reference. Next, a point cloud generated from these features will be used to test how different tools (open source and commercial) and segmentation methods (based on machine learning and deep learning solutions) perform in recreating/extracting these features. This step will allow me to understand how good the reference dataset is for comparing each method against. Along with point cloud processing, several approaches will be used to detect features in image data. This will give an insight into how well data from various sensors can represent a feature and how this information can complement.

The final step will be to use selected methods (with best performance based on the established indicators) on real-world data (point cloud and images). Data will represent the same area of interest to allow the fusion of information collected through the data processing. The result should deliver semantically reach information to enrich knowledge of the city environment (or selected object classes)

We have identified the potential impact of the CDT in consultation with 44 partner organisations, ensuring we are meeting the needs of potential beneficiaries. The impacts that we will develop robust pathways to achieve include:

Economic:
Our graduates will be a key pool of knowledge and skills to deliver the annual £11bn of economic benefit to the UK from 'opening-up' geospatial data. Their advanced skills in a rapidly changing technological field will help the UK geospatial industry realise the predicted global annual growth of 13.8% and transform the use of geospatial data and technology in smart cities, urban-infrastructure resilience, energy systems and structural monitoring.
Through continuous two-way engagement with our partners we will shape and deliver industry relevant PhD projects that apply students' unique training. Ongoing knowledge exchange with industry will be facilitated through regular interaction with the centre, the Industrial Advisory Board and partner participation at the Innovation Festival, CDT Assembly and Challenge Week events. We will work with the recently announced £80m Geospatial Commission to ensure the translation of new methods, techniques and technology to the broadest possible user base; using our partnerships with professional bodies to recognise the opportunities and challenges to realising the economic benefits of geospatial data.
SME and start-ups are will be major drivers of global geospatial industry growth. Innovation and entrepreneurial training will position our graduates to act as a catalyst of the growth needed in the UK to remain internationally competitive. Working with Satellite and Digital Catapults, and the £30million National Innovation Centre for Data, we will foster a 'full-circle' engagement with SME's and start-ups; to ensure our graduates understand the drivers for innovation, facilitate co-production and ensure the timely adoption of academic driven advances for economic growth.

Societal:
We have recognised the significant role geospatial data will play in providing the evidence for improved planning and response to significant global societal problems. The interdisciplinary PhD research conducted within the CDT will provide new insight and understanding in climate impacts and adaption, sustainable cities, and healthy living and aging. Our graduates will engage with key international and national organisations (e.g., Cities Resilience Programme of the World Bank, UK National Infrastructure Commission) to ensure the widest adoption of their research.

Academic:
Our graduates will form the next generation of geospatial scientists and engineers vital for interdisciplinary research at the engineering-societal-environment nexus. Their combined skills in geospatial technology and methods, along with advanced mathematical, statistical and computing skills, will provide the UK with a unique resource pool of academic leaders. The research produced by the centre, sustained and embedded by the skilled workforce it creates, will help address the Grand Challenges of the UK Industrial Strategy; AI and the Data Driven Economy, Future Mobility and an Aging Society.

To maximize academic outreach we will provide a Geospatial Systems Resource Portal that will allow researchers to access the new techniques and methods developed. Software and related methods will be open source, and tutorials and training guides will be developed as a matter of routine. We will organise CPD courses based on our unique integrated training in Geospatial Systems, open to cohorts from other CDTs within the digital economy space. We will foster cross-UKRI translation and learning by working with related CDTs; the ESRC CDT in Data Analytics and Society and NERC CDT in Data, Risks and Environmental Analytical Methods. Via our 9 international research partners our unique training approach and strong emphasis on interdisciplinary research will become internationally impactful.