Zifu Wang
Zifu Wang, PhD is a Postdoctoral Research Fellow at the Center for Geographic Analysis (CGA), whose research lies at the intersection of Geographic Information Science (GIS), Artificial Intelligence (AI), and computational science. His work focuses on transforming complex spatial and textual data into evidence-based intelligence for public-policy applications in humanitarian response, crime prevention, public health, and transportation safety.
Dr. Wang develops GeoAI models that integrate natural language processing (NLP), computer vision, and remote sensing to extract, analyze, and visualize spatiotemporal patterns from unstructured and real-time data. His research advances the field of policy intelligence, leveraging AI-driven systems to translate data into actionable insights that inform decision-making at local, national, and global levels.
His contributions span three major themes:
GeoAI Models for Policy Data Extraction — Dr. Wang pioneers NLP and computer vision techniques for location and event extraction from large-scale unstructured datasets. His work on optimizing open-source large language models (LLMs) through Retrieval-Augmented Generation (RAG) for real-time conflict monitoring in the Sudan Conflict Observatory. He also applied similar GeoAI frameworks to map transnational organ-trade networks, identifying brokers, clinics, and routes that support international crime-prevention and ethical governance.
Applied GeoAI Systems for Policy Applications — Dr. Wang designs integrated systems that combine LLM-based text analysis, GIS, and remote-sensing data to support applied policy domains. At Harvard, he leads the EZRouting School-Bus Safety Project, a GeoAI-driven platform for optimizing school-bus routes and improving transportation equity. His previous work includes a School Reopening Decision-Support System that guided pandemic-era education and public-health policies by assessing spatial infection risks using multi-source data. Globally, he has applied GeoAI methods to humanitarian intelligence—automating the monitoring of conflict zones and human-rights violations through satellite imagery and multilingual information extraction.
Cloud Computing and Scalable Geospatial Analytics — Dr. Wang manages and utilizes a 600-node high-performance computing (HPC) infrastructure integrating OpenStack, Hadoop, and GPU clusters to support data-intensive GeoAI research. His computational frameworks have powered projects such as GPU-accelerated sea-ice thickness estimation for climate policy, real-time COVID-19 data integration for public-health response, and large-scale geospatial NLP pipelines for global crisis mapping.
Looking forward, Dr. Wang’s research aims to establish a new generation of multimodal GeoAI for policy reasoning—integrating textual, visual, and spatial data into unified AI systems capable of real-time interpretation and prediction. He envisions developing a Policy Intelligence Model, a foundation-scale multimodal architecture for evidence-based governance across domains including environmental protection, humanitarian response, transportation safety, and social equity.
Dr. Wang’s work has been published in leading journals such as International Journal of Digital Earth, International Journal of Health Geographics, Vaccines, GeoHealth, Big Earth Data, and IEEE Access. His research has been supported by the U.S. Department of State, National Science Foundation (NSF), and NASA, and has informed multiple data-driven policy platforms at Harvard CGA and partner institutions.