Cross-Disciplinary Data-Driven Research

Data revolutionizes all research fields.
I am curious how data make new discoveries across a variety of fields and how data make changes in the real world.

I develop computational techniques to release the power of data.

traffic light, traffic signal, stoplight-514932.jpg
Pioneer in the research topic on reinforcement learning for traffic signal control

Traffic Signal Control

Selected Publications
Intellilight: A reinforcement learning approach for intelligent traffic light control (KDD 2018)
Presslight: Learning max pressure control to coordinate traffic signals in arterial network (KDD 2019)
CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario (WWW 2019)
Toward a thousand lights: Decentralized deep reinforcement learning for large-scale traffic signal control (AAAI 2020)
Recent Advances in Reinforcement Learning for Traffic Signal Control: A Survey of Models and Evaluation (SIGKDD Explorations 2020)
Vikash Gayah, Civil Engineering, Penn State
Traffic policy makers in Hangzhou, Nanchang, Wuxi
Big data analysis for water quality in the area of shale gas development


Selected Publications
Searching for Anomalous Methane in Shallow Groundwater near Shale Gas Wells (Journal of Contaminant Hydrology 2016)
Contextual Spatial Outlier Detection with Metric Learning (KDD 2017)
Big groundwater data sets reveal possible rare contamination amid otherwise improved water quality for some analytes in a region of Marcellus Shale development (Environmental Science & Technology 2018)
Knowledge-based Residual Learning (IJCAI 2021)
Susan Brantley, Geosciences, Penn State
Tao Wen, Earth and Environmental Sciences, Syracuse University
boat, river, forest-6579441.jpg
chicago, beach, water-2203728.jpg
Using open city data to better understand crime rates


Selected Publications
Crime Rate Inference with Big Data (KDD 2016)
Non-Stationary Model for Crime Rate Inference Using Modern Urban Data (Transaction of Big Data 2017)
Region Representation Learning via Mobility Flow (CIKM 2017)
Network spillovers and neighborhood crime: A computational statistics analysis of employment-based networks of neighborhoods (Justice Quarterly 2021)
Corina Graif, Sociology and Criminology, Penn State
Daniel Kifer, Computer Science and Engineering, Penn State
We are among the first to study deep learning for traffic prediction

Traffic Prediction

Selected Publications
Deep multi-view spatial-temporal network for taxi demand prediction (AAAI 2018)
Revisiting spatial-temporal similarity: A deep learning framework for traffic prediction (AAAI 2019)
Learning from multiple cities: A meta-learning approach for spatial-temporal prediction (WWW 2019)
Hierarchically Structured Meta-Learning (ICML 2019)
Work in collaboration with DiDi Chuxing
taxi, road, traffic-238478.jpg
africa, south africa, wildlife-210075.jpg
Discover animal behaviors and relationships through their movement traces


Selected Publications
Mining Periodic Behaviors for Moving Objects (KDD 2010)
Swarm: Mining Relaxed Temporal Moving Object Clusters (VLDB 2010)
Mining Following Relationships in Movement Data (ICDM 2013)
Attraction and Avoidance Detection from Movements (VLDB 2014)
Roland Kays, NC Museum of Natural Sciences
Meg Crofoot, Max Planck Institute of Animal Behavior

Cross-disciplinary Collaborations

I am very fortunate to explore our world with my collaborators across the fields through the lens of data.

Susan Brantley

Penn State

Meg Crofoot

Max Planck Institute

Vikash Gayah
Civil Engineering

Penn State

Corina Graif

Penn State

Roland Kays

NC Museum of Natural Sciences

Thomas Lauvaux
Climate Science


Stephen Matthews

Penn State

Tao Wen

Syracuse University