Urban Analytics Lab

Geospatial and 3D urban modelling research group at the National University of Singapore

We are a new interdepartmental multidisciplinary research group focusing on urban data analysis, geographic data science, and 3D city modelling at the National University of Singapore (NUS), the #1 ranked university in Asia and world’s #11 (QS).

Our mission is to leverage on spatially enabled data for urban applications, catalyse the development of 3D geoinformation in the context of smart cities, make sense of big geospatial data and digital twins in the built environment, and cater to disciplines such as architecture, urban planning, and real estate to make informed decisions using 3D city models and urban analytics. We appreciate the importance of geoinformation powering urban informatics, and put a particular focus on the geospatial infrastructure and technology.

The lab is led by Dr Filip Biljecki, asst prof at NUS School of Design and Environment.

We are involved in several international collaborations such as the World Economic Forum (WEF), the International Society for Photogrammetry and Remote Sensing (ISPRS), and the Open Geospatial Consortium (OGC). On the national level, we have collaborations with Singapore Government agencies and companies.

You are welcome to follow our work through Twitter and our blog.

Our interests and key words: Geographical Information Science (GIS), geospatial machine learning, geographic data science, 3D city modelling / 3D GIS (some people also call them digital twins), 3D urban analytics, spatial data quality and standardisation (CityJSON, CityGML), Volunteered geoinformation (VGI) and OpenStreetMap (OSM), Building Information modelling (BIM), Geospatial data visualisation, 3D underground data modelling, and 3D cadastre.

What’s up?

Updates from our lab

Feel free to follow us on Twitter or through our RSS feed.

Geospatial and urban data science journals

List of relevant journals with their latest metrics

Our participation at the State of the Map 2020

This year’s OpenStreetMap conference moved online retaining its full spirit

A Comparison of Spatial Functions: PostGIS, Athena, PrestoDB, BigQuery vs RedShift

We are moving our geospatial analysis to the cloud. As we are evaluating the various offerings by AWS and Google Cloud Platform, we wonder to what extent these cloud database products support spatial functions in comparison to PostGIS.

Welcome, Abraham

We are pleased to welcome Abraham Noah Wu as a new full-time researcher in the group, working on our flagship project on generating large-scale 3D city models.

Guide for open urban data in Singapore

Our curated inventory of data relevant for geospatial and urban analyses

Projects and themes

Large-scale 3D geospatial data for urban analytics

Creating country-wide 3D city models using artificial intelligence

BIM-GIS interoperability

Integration of Building Information Modelling (BIM) and GIS

Urban Modelling and Smart Cities

Harnessing geographic information in the urban context.

Big Data in Real Estate

Leveraging urban analytics in real estate

GeoBIM Benchmark

Reference study on software support for open standards of city and building models


Openings, scholarships, and fellowships

Please check the opportunities page for more information how to join us.


Our education activities

We are involved in teaching master courses and supervising dissertations. Are you looking for a thesis topic? Please check the teaching page for more information.

Recent publications

Our 10 latest papers. Enjoy

All our publications are available here.

An application-driven LOD modeling paradigm for 3D building models

The level of detail (LOD) concept for 3D building models, which indicates the degree of closeness between a model and its real-world …

The implementation of big data analysis in regulating online short-term rental business: a case of Airbnb in Beijing

With the fast expansion and controversial impacts of short-term rental platforms such as Airbnb, many cities have called for regulating …

Considerations for a contemporary 3D cadastre for our times

A significant number of studies has been carried out to establish 3D cadastre solutions to improve the registration of multi-level …

GeoBIM benchmark 2019: intermediate results

An investigation into the implementation state of open standards in software is currently ongoing through the ISPRS/EuroSDR ‘GeoBIM …

Graph transformation rules for IFC-to-CityGML attribute conversion

In model transformation, the population of attributes on the target side constitutes the last step of the conversion process that …

Quality of BIM-GIS conversion

Much work has been done on quality of geoinformation and interoperability between BIM and GIS. However, the intersection of the two – …

Raise the roof: towards generating LoD2 models without aerial surveys using machine learning

LoD2 models include roof shapes and thus provide added value over their LoD1 counterparts for some applications such as estimating the …