Best Paper Award at the International Conference on Advances in Geographic Information Systems 2025
Author ADM+S Centre
Date 24 December 2025
Researchers from the ARC Centre of Excellence for Automated Decision-Making and Society at UNSW have received the Best Research Paper Award at the ACM SIGSPATIAL Conference 2025 for their traffic forecasting dataset featuring over 22 years of data from California, USA and Transport for NSW.
The research “XXL Traffic Expanding and Extremely Long Traffic forecasting beyond test adaptation” was authored by PhD student Du Yin, Dr Hao Xue, and Prof Flora Salim from the ADM+S alongside colleagues Arian Prabowo and Shuang Ao.
The ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems 2025 (ACM SIGSPATIAL 2025) is an annual event that brings together researchers, developers, users, and practitioners in relation to novel systems based on geospatial data and knowledge, and fosters interdisciplinary discussions and research in all aspects of geographic information systems.
Held in Minneapolis, USA, the conference provides a forum for original research contributions covering all conceptual, design, and implementation aspects of geospatial data ranging from applications, user interfaces, and visualisation to data storage and query processing and indexing. The Best Paper Award is only awarded to one paper during the entire conference.
ADM+S researchers and UNSW colleagues were the largest group from non-US universities attending the conference with the following papers presented:
STOAT: Spatial-Temporal Probabilistic Causal Inference Network
Yang Yang, Du Yin, Hao Xue, Flora Salim (UNSW)
A Probabilistic Framework for Imputing Genetic Distances in Spatiotemporal Pathogen Models
Haley Stone, Jing Du, Hao Xue (UNSW), Matthew Scotch (ASU), David Heslop (UNSW), Andreas Züfle (Emory), Raina MacIntyre (UNSW), Flora Salim
Dynamic Budgeted Reinforcement Learning for Fairness in Spatial-Temporal Resource Allocation
Yufan Kang (RMIT, Monash), Jie Zhang (UESTC), Wei Shao (UNSW, Data61), Rui Tang (Fuzhou University), Mark Andrejevic (Monash), Jeffrey Chan (RMIT), Flora Salim (UNSW).
FairDRL-ST: Disentangled Representation Learning for Fair Spatio-Temporal Mobility Prediction
Sichen Zhao (RMIT), Wei Shao (UNSW, Data61), Jeffrey Chan (RMIT), Ziqi Xu (RMIT), Flora Salim (UNSW).
GenUP: Generative User Profilers as In-Context Learners for Next POI Recommender Systems
Wilson Wongso, Hao Xue, Flora Salim
Classical Feature Embeddings Help in BERT-Based Human Mobility Prediction.
Yunzhi Liu , Haokai Tan, Rushi Kanjaria, Lihuan Li, Flora Salim (UNSW)
EpiScale: Large-Scale Simulation of Infectious Disease Based on Human Mobility
Ruochen Kong (Emory), Taylor Anderson (George Mason University), David Heslop (UNSW), Matthew Scotch (ASU), Flora Salim (UNSW), Raina MacIntyre (UNSW), Andreas Züfle (Emory).
