GeoIndustry @ ACM SIGSPATIAL 2026
The 5th International Workshop on Spatial Big Data and AI for Industrial Applications


Riverside, CA, USA
Tuesday, November 3 - Friday, November 6, 2026

Submit Now

About

With the rapid revolution and increasing availability of geospatial data not only academia, but also industry aspire for solutions to further leverage the big data and AI technologies to create new products, improve efficiencies and provide novel solutions to existing problems. However, despite the widespread interest, there is a lack of communication between the researchers in academia and industry. This limits advancements at the intersection and causes redundant or siloed efforts on both sides. Academia often has limited access to the rich and potentially useful big geospatial datasets and related real problems. In addition, the solutions proposed by the academic researchers alone are usually developed for a small scale with many assumptions, leaving a less-attended gap between methods and their applicability at scale for industrial applications. On the other hand, the industry has the data and problems at scale. However, since existing research is often not on par, industry researchers may lean towards using the traditional approaches that are developed without spatial consideration (e.g., ignoring spatial and temporal dependencies), and project teams have limited time and efforts to dive deep on the development of novel techniques that can be high-risk, but high-potential. This opens up opportunities for synergistic collaboration between industrial practitioners and academic researchers.

The goal of this workshop is to offer a forum to exchange thoughts and ideas between industry and academia and reduce those siloed efforts by exploring synergies between the researchers on both sides. We envision that the collaborations, via invited and regular talks, can not only accelerate the research-to-impact cycle, but also foster workforce development for future geospatial researchers.

Organizing Committee

Program Chairs
Heba Aly (Amazon)
Emre Eftelioglu (Amazon)
Song Gao (University of Wisconsin-Madison)
Yan Li (Amazon)
Jinmeng Rao (Google DeepMind)
Yiqun Xie (University of Maryland)

Program Committee
Minsoo Choi (Amazon) Maria Luisa Damiani (University of Milan)
Jiena He (University of Maryland) Vishal Kumar (Amazon)
Ruohan Li (University of Maryland) Zhili Li (University of Maryland)
Shengheng Liu (University of Maryland) Shaishav Maisuria (Amazon)
Arun Sharma (University of Minnesota) Weilun Shi (University of Maryland)
Armin Soltan (Pacific Disaster Center) Aohua Tian (University of Maryland)
Ruichen Wang (University of Maryland) Zeyu Wang (University of Washington)
Zhihao Wang (University of Maryland) Xin Xu (University of Maryland)
Gyanko Yussif (University of Rhode Island)

Webmaster
Zhihao Wang (University of Maryland)

Schedule

Tuesday, November 3, 2026 - Riverside, CA, USA

Time Title
08:30 - 08:35 Opening Remarks
08:35 - 09:20 [Keynote Talk 1] The Foundations of Urban Mobility Foundation Models

Speaker: Shushman Choudhury, Google Research
Session 1: Mobility & Spatio-Temporal Representation Learning
09:20 - 09:35 Bringing GeoAI to the Planning Table: Engineering and Deploying TangibleGeoAI

Full Paper · Shun Nakayama, Nozomi Ishiguro, Hikaru Ashida, Takahiro Kanamori and Wanglin Yan
09:35 - 09:50 Trustworthy Geospatial AI Workflows: Reproducible Maritime Analytics and Forecasting on Open-Source AIS Data

Full Paper · Divya Acharya, Thomas M Roehr and Arnaud Gotlieb
09:50 - 10:00 Trip-Purpose Inference with Location Trajectories and Short User Memos: Evaluating Multimodal Complementarity

Short Paper · Mizuki Miura, Zhixiong Chen and Daisuke Kamisaka
10:00 - 10:30 Coffee Break
Session 2: Location Intelligence & Site Planning
10:30 - 10:45 A Geospatial Network Planning Framework for Grocery Stores

Full Paper · Zhen Li, Yuchen Luo, Gianluca Grilli, Bruno Lopez-Videla, James Domingo, Ryan Kasserra and Louise Lindegaard
10:45 - 11:00 Logistics-Oriented Dual-Radius Incremental Siting Model: A Case Study of Rougamo Outlets in Xi’an

Full Paper · Xiaoyu Fan, Haojian Liang, Yang Ding, Fanghan Dang, He Li, Huiwen Deng, Nanmu Su, Xiaoxiao Guo and Shaohua Wang
11:00 - 11:15 Spatial Information as Proxy for Synthesizing Customer Brand Perception

Full Paper · Jiaxin Du, Liye Ma and Baohong Sun
11:15 - 11:30 What Survives a Matched Backtest? Auditing Spatiotemporal Evaluation Leakage in UK House Price Prediction

Full Paper · Nakul Gupta and Shreya Singla
Session 3: Agentic & Explainable GeoAI
11:30 - 11:45 Agentic AI Orchestration Framework for Spatial Intelligence: Supply Chain Deployment

Full Paper · Constantinos Papantoniou and Brian Hilton
11:45 - 12:00 GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks

Full Paper · Gabriel Diaz Ireland, Diego Prieto Herráez, Mario García Peces, Javier Velázquez Saornil, Benjamin Zaitchik and Devika Jain
12:00 - 12:15 A Multi-Agent Text-to-SQL Chatbot over Spatio-Temporal Transit Data

Full Paper · Luca Fantin, Marco Antonelli, Daniele Irto, Bruno Zamengo, Denis Cappellari and Francesco Silvestri
12:15 - 12:30 EXPERT-FR: Explainable AI for Emergency Response Time Prediction in Urban Fire Rescue Operations

Full Paper · Dilli Prasad Sharma, Nasim Beigi-Mohammadi, Praveen Soni, Rob Madro, Phil Emmenegger, Carlos Tobar, Xiaoqi Tan and Alberto Leon-Garcia
12:30 - 14:00 Lunch Break
14:00 - 14:45 [Keynote Talk 2] City Intelligence: When Cars Write the Rules of the Road

Speaker: Zhenhui (Jessie) Li, The Hong Kong Polytechnic University
Session 4: Routing & On-Demand Mobility
14:45 - 15:00 Scalable Route and Shared-Stop Optimization for On-Demand Single-Destination Shuttles

Full Paper · Yonghwan Kim, Kazuho Takahashi and Daisuke Yamamoto
15:00 - 15:15 Prompt-Configurable Vehicle Routing for Industrial Logistics

Full Paper · Hadi Aghazadeh and Xin Wang
15:15 - 15:30 RHPS: A Production-Validated Marketplace Simulator for Spatial Decision-Making at Scale

Full Paper · Haifeng Yuan, Yongjian Tek, Zuwei Li, Lam Raga Anggara Markely, Chek Hui Ho and Alexandre Montecucco
15:30 - 16:00 Coffee Break
Session 5: Geospatial Data, Infrastructure & Spatio-Temporal Modeling
16:00 - 16:15 The Circuity of North American Rideshare Trips

Full Paper · James Murphy
16:15 - 16:30 Intersection Is Not Enough: Bridging the Research–Practice Gap in Building Footprint Conflation

Full Paper · Florian Nachtigall, Felix Wagner, Jakob Napiontek and Felix Creutzig
16:30 - 16:45 Reconstructing Missing Dwelling Area from Census Room Counts and Overhead Imagery for Residential Occupancy Modeling

Full Paper · Carson Woody and Sarah Walters
16:45 - 17:00 ROS2 to GIS: An Interoperability Layer for Robotic Spatial Big Data Pipelines

Full Paper · Maciej Krupka, Antoni Sopata, Jakub Pilarski, Łukasz Grobelny, Robert Wrembel, Piotr Skrzypczynski, Simon Baud, Anouk Jégo-Dufau and Jean-Paul Kasprzyk
17:00 - 17:15 Spatio-Temporal Dual Link Prediction from Hydrogen Bond Formation in Molecular Dynamics

Full Paper · Md Hasan Anowar, Goce Trajcevski, Sohail Murad, Cynthia Jameson and Ashfaq Khokhar
17:15 - 17:25 Heat Exposure as a Routing Attribute: Integrating Satellite Thermal Layers into Trip-Planning Data Pipelines

Short Paper · Hamid Norouzi
17:25 - 17:35 The Rise of Personal Trackers as the Next Infrastructure for Ubiquitous Positioning

Short Paper · Mohamed Ibrahim, Hamada Rizk and Moustafa Youssef
17:35 - 17:55 Panel Discussion
17:55 - 18:00 Closing Remarks

Keynote Talks

The Foundations of Urban Mobility Foundation Models

Speaker: Shushman Choudhury, Google Research

Geospatial artificial intelligence (GeoAI) has largely treated the built environment as static, relying on satellite imagery, street-level photos, and textual or structured map metadata. Human mobility represents an essential but under-explored modality, especially in urban GeoAI: it reveals how communities actively navigate and use physical spaces over time, capturing dynamic functions that static modes tend to miss.

In this talk, I will establish that building general-purpose urban mobility foundation models rests on three interacting pillars: multimodal datasets and models, geospatial representations, and large-scale self-supervised learning. I will discuss three works that rest on these pillars. First, the conceptual vision of Geospatially Embedded Objects (GEOs), which frames spatial geometries as semantic tokens enriched by human movement. Next, I will present two technical instantiations of the GEOs vision: ME-POIs, which uncovers dynamic place function from human visit patterns, and TrajGANR, which aligns irregular trajectory streams with street-view imagery via continuous neural fields. Together, these works illustrate how foundation models that learn from human mobility can enable improved urban understanding and spatial reasoning.

Back to schedule

City Intelligence: When Cars Write the Rules of the Road

Speaker: Zhenhui (Jessie) Li, The Hong Kong Polytechnic University

Over five years of building Hangzhou's City Brain — one of the largest deployments of spatial big data and AI in a real city — I saw firsthand why urban traffic is such a stubborn challenge. It is as much a social and economic problem as a technical one. Drawing on real city cases and real data, this talk looks at what makes it so hard, including the economics behind it, and why many of its problems are not ones technology alone can solve. One constraint runs through all of them: today's traffic system is shaped by human drivers. Signals, lanes and fixed directions of travel exist because drivers can't coordinate with each other in real time. These rules serve us well, but in compensating for that limitation they leave much of the road's capacity unused — and that is a large part of why our cities are so congested.

Autonomous vehicles remove that limit, yet today they still follow rules written for human drivers. So I invite you to imagine a city full of autonomous vehicles and no traffic rules at all: no signals, no lanes, no fixed directions. With the old rules set aside, what could the road network do? Starting from a single intersection, I will show that simple local rules let vehicles invent a roundabout on their own, and that this coordination holds not just at one intersection but across a whole city's road network, as reported in our KDD 2026 paper. Once the old rules are gone, new ones are needed: rules of the road written for machines rather than people, so that vehicles coordinate safely and put the road's full capacity to use. For industry, the question changes from how to optimize traffic within today's rules to how much more our existing roads can carry once the rules can be rewritten.

Back to schedule

Call for Papers

Download the Call for Papers (PDF)

The workshop seeks high-quality regular (8-10 pages) and short (4 pages) papers that have not been published in other academic outlets and are not concurrently under peer review. Interested participants should submit a paper in the ACM format. Once accepted, at least one author is required to register for the workshop and the ACM SIGSPATIAL conference, as well as attend the workshop to present the accepted work which will then appear in the ACM Digital Library.

Because this workshop focuses heavily on practical and industrial relevance, we encourage every submission to include a brief discussion about the potential impact to industrial applications.

The topics include but are not limited to (in the context of industrial or related problems, such as delivery, routing, recommendation, mapping, resource allocation, and more):

  • Agentic AI

  • Applications of AI

  • Big Data systems

  • Geospatial AI foundation models

  • Problems and benchmark datasets

  • Machine learning and deep learning

  • Computer vision and earth observation

  • Generative models and simulation

  • Map generation techniques

  • Heterogeneous data integration and analysis

  • Small data learning approaches

  • Citizen science and data collection

  • Spatial query processing

  • Spatial data management and integration

  • Ethical issues in geospatial data and research

  • Perspectives on the future of geospatial data and research

  • Emerging topics and trends

Important Dates

Submission deadline

August 28 September 4, 2026, 11:59 PM AoE

Acceptance notification

September 15 September 20, 2026

Camera-ready deadline

October 2, 2026

Workshop day

November 3, 2026

Submission site

https://easychair.org/conferences/?conf=geoindustry2026