I am a third-year PhD student at UCL’s SpaceTimeLab, supervised by Dr James Haworth, Dr Aldo Lipani, and Dr Stefano Cavazzi. My research is funded by UKRI (EPSRC) and Ordnance Survey (OS).

I work on bridging natural language intent and structured geospatial data to enable complex, context-aware spatial reasoning. My research focuses on quantifying how LLMs and VLMs reason about the physical world using crowdsourced data and street-level imagery. I am particularly interested in integrating qualitative environmental features into routing algorithms – optimizing for subjective perception and non-utilitarian movement – and developing automated frameworks to extract geographic concepts from web-scale, non-traditional datasets.

I am co-founder and CTO of Safest Way, a Geovation-backed startup developing safety-centric pedestrian navigation.

Selected publications

• CLIP the Landscape: Automated Tagging of Crowdsourced Landscape Images
  🖼️ Remote Sensing Applications: Society and Environment · GitHub · 📄 arXiv

• Into the Unknown: Applying Inductive Spatial-Semantic Location Embeddings for Predicting Individuals’ Mobility Beyond Visited Places
  📸 SIGSPATIAL'25 · GitHub · 📄 arXiv

• V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?
  📸 CV4DC @ ICCVW'25 · GitHub · 📄 arXiv

• Quantifying Geospatial in the Common Crawl Corpus
  📸 SIGSPATIAL'24 · 📄 arXiv

• CC-GPX: Extracting High-Quality Annotated Geospatial Data from Common Crawl
  📸 SIGSPATIAL'24 · GitHub · 📄 arXiv

• CycleTrajectory: An End-to-End Pipeline for Enriching and Analyzing GPS Trajectories to Understand Cycling Behavior and Environment
  📸 SuMob @ SIGSPATIAL'24 · GitHub · 📄 arXiv

• Do Sentence Transformers Learn Quasi-Geospatial Concepts from General Text?
  📸 GeoExT @ ECIR 2024 · 📄 arXiv

Hands-On Data Visualization

Hands-On Data Visualization: Interactive Storytelling from Spreadsheets to Code (O’Reilly), co-authored with Jack Dougherty. Available open-access in English, and translated into Korean and Traditional Chinese.

Since 2022, all royalties (currently over $3,000) have been donated to humanitarian relief efforts in Ukraine, including Save Life in Ukraine, the Ukraine Humanitarian Appeal and The HALO Trust.

Teaching support

At UCL, I have supported teaching in Geospatial Programming, Spatial Analysis and Computation, Spatial-Temporal Data Analysis and Data Mining, and Surveying and Field Studies. At Birkbeck, I demonstrate in labs for Information Security, Data and Knowledge Management, Data Analytics using R, Computer Networking, and Mobile Computing.

Professional experience

Prior to my PhD, I spent five years in industry, first as a full-stack developer for an open data consultancy CTData Collaborative, and then as a data engineer for the location planning firm Geolytix.

Education

• PhD in Geomatic Engineering / Spatial AI – University College London (UCL), 2023–2027

• MSc in Geographic Information Science (Distinction) – University of Leeds, 2019–2022

• BSc in Computer Science and Studio Arts (summa cum laude, Phi Beta Kappa) – Trinity College (Connecticut), 2014–2018

• Worcester College, University of Oxford – Visiting student focusing on machine learning and game theory, 2016–2017