About

Mohamed F. Mokbel is a Professor and Distinguished McKnight University Professor in the Department of Computer Science & Engineering at the University of Minnesota. He joined the department in 2005 and has since established a distinguished research career at the intersection of database systems and spatial communities. His research focuses on designing new algorithms and developing system modules that incorporate spatial awareness into various systems, including database systems, big data systems, knowledge-base systems, recommender systems, and machine learning systems. Mokbel's work supports critical applications that heavily rely on spatial data, such as urban computing, transportation, and geographic information systems (GIS). He has made significant contributions to the field, earning multiple awards including the IEEE Fellow in 2020, the ACM SIGSPATIAL 10-Year Impact Award in 2022, and being named a Distinguished McKnight University Professor in 2023. His educational background includes a Ph.D. in Computer Science from Purdue University and a master's and bachelor's degree in Computer Science and Automatic Control from Alexandria University. Mokbel has also served as the founding technical director at the Geographic Information Systems Technology Innovation Center and as the chief scientist at the Qatar Computing Research Institute.

Research topics

• Computer Science
• Artificial Intelligence
• Data Mining
• Machine Learning
• Computer Security
• Database
• Real-time computing
• Transport engineering
• Embedded system
• Geography
• Computer network
• Internet privacy
• Distributed computing
• Computer vision
• Engineering

Selected publications

• Engaging K-12 Learners in Data Annotation for AI Climate Models

  2025-02-18

  article

  Due to the climate crisis, summers in Greenland have been rapidly getting warmer, causing increasing rates of ice melt on the Greenland ice sheet and speeding up sea-level rise. Evidence of this change can be measured by the number and location (elevation) of water pools and lakes that form on the surface of the ice sheet. In addition, crevasses can cause lakes to drain extremely rapidly causing the ice to flow faster, contributing to sea-level rise. However, the lack of annotated data makes it difficult to automatically detect and track these behavioral changes in the polar ice sheet lakes. This study describes how a team of polar and data scientists actively engaged middle and high school students in their classrooms in a data annotation process through an engaging curriculum unit to identify multiple ice sheet phenomena observed in satellite imagery. The findings describe the learning outcomes from both student and teacher perspectives. It also projects learners' understanding and sentiments about climate change and the role of artificial intelligence (AI) models coupled as an extension of citizen science in addressing climate change.

  PublisherDOI

• Large Language Models for Urban Mobility

  2025-06-02

  articleSenior author

  This Advanced Seminar provides a comprehensive overview of the research landscape of employing Large Language Models (LLMs) for Urban Mobility applications. The presented work in this seminar is categorized based on how LLMs are employed to serve various urban mobility applications. This goes from employing LLMs as a black box with a bit of prompt engineering, to fine-tuning LLMs to fit urban mobility applications, to completely retrain a vanilla LLM architecture with urban mobility data, to modifying the internal LLM loss function to fit urban mobility applications. The seminar concludes by presenting a set of benchmarking and evaluation work while pointing out to research gaps, open problems, and future research directions for employing LLMs to urban mobility applications.

  PublisherDOI

• A Demonstration of Polaris: An Interactive and Scalable Data Infrastructure for Polar Science

  Proceedings of the VLDB Endowment · 2025-08-01

  articleSenior author

  This demonstration presents Polaris; a novel open-source system infrastructure for Polar science that is highly Interactive and Scalable. Polaris is designed based on three observations that distinguish the query workload of polar scientists, namely, all queries are spatio-temporal, not all data are equal, and the large majority of queries are aggregates. With this, Polaris is equipped with a hierarchical spatio-temporal index structure that stores precomputed aggregates for data of interest. Audience will be able to experience Polaris through various scenarios that show the interactivity and scalability as well as Polaris optimized query processes.

  PublisherDOI

• New Initiatives in ACM SIGSPATIAL 2025

  SIGSPATIAL Special · 2025-07-01

  article1st authorCorresponding

  The ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems 2025 (ACM SIGSPATIAL 2025), the thirty-second edition, will be held in Minneapolis, MN, USA, from November 3 to November 6, 2025 (https://sigspatial2025.sigspatial.org/org/). The conference began as a series of symposia and workshops starting in 1993 with the aim of bringing together researchers, developers, users, and practitioners in relation to novel systems based on geospatial data and knowledge, and fostering interdisciplinary discussions and research in all aspects of geographic information systems. 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 visualization to data storage and query processing and indexing. The conference is the premier annual event of the ACM Special Interest Group on Spatial Information (ACM SIGSPATIAL).

  PublisherDOI

• Large Language Models for Spatial Analysis Queries

  Proceedings of the VLDB Endowment · 2025-08-01 · 1 citations

  articleSenior author

  This tutorial provides a comprehensive overview of the research landscape of employing Large Language Models (LLMs) to spatial analysis queries. The tutorial categorizes the research in this area based on how LLMs are employed to serve such queries. This goes from employing LLMs as is, to fine-tuning LLMs, to completely retrain LLM architectures, to modifying the LLM internals to fit spatial queries. The tutorial concludes by a set of benchmarks and pointing out to research gaps and future research directions.

  PublisherDOI

• Polaris: An Interactive and Scalable Data Infrastructure for Polar Science

  Proceedings of the VLDB Endowment · 2025-07-01

  articleSenior author

  Though polar scientists entertain having huge amounts of publicly available datasets, they face the challenge that working with such data is a cumbersome process that requires downloading tons of unnecessary data and writing various scripts on top of it. This hinders their ability to perform any kind of interactive analysis. This paper presents Polaris; a novel open-source system infrastructure for Polar science that is highly Interactive and Scalable. Polaris is designed based on three observations that distinguish the query workload of polar scientists, namely, all queries are spatio-temporal, not all data are equal, and the large majority of queries are aggregates. Polaris is equipped with a hierarchical spatio-temporal index structure that stores precomputed aggregates for data of interest. Experimental results with a real Polaris prototype and real scientific data show that it achieves highly interactive and scalable data access, enabling interactive analysis of polar science data.

  PublisherDOI

• Large Language Models for Spatial Analysis Tasks

  2025-11-03

  articleOpen accessSenior author

  Spatial analysis tasks are fundamental to many applications, such as urban planning, navigation, and mobility analysis. Traditional solutions often rely on techniques tailored to specific tasks for trajectory, traffic, or point-of-interest (PoI) data. With the rapid advances in machine learning especially Large Language Models (LLMs), the spatial data community has begun exploring their potential for addressing spatial analysis tasks. In this paper, we present a taxonomy of existing approaches that leverage LLMs for spatial data analysis, organized along two dimensions: the type of spatial data (traffic, multi-modal, trajectory, and PoI) and the approach in which LLMs are employed (using pretrained models, fine-tuning, architecture-only training, and internal modifications). We also outline open challenges for future work.

  PublisherOA PDFDOI

• TrajSplit: Scalable and Accurate Trip Extraction from Raw GPS Trajectories

  2025-06-02

  article

  The evolution of data-driven algorithms for trajectory analysis operations relies heavily on the availability of trajectory data. Unfortunately, most of the available trajectory datasets are not suitable for use by analysis operations. A main reason is that such trajectories are released in their raw form: A sequence of locations coming from the same device over a time period (e.g.: hours or years), whereas trajectory analysis operations need trip trajectories. Hence, existing trajectory analysis techniques preprocess the raw trajectories by applying simple rules to extract trips out of each trajectory. However, such basic rules miss too many realistic scenarios and result in low accuracy which negatively affects down-stream trajectory applications. This paper presents TrajSplit: an accurate and scalable algorithm for trip extraction from raw GPS trajectories. TrajSplit goes beyond the basic simple rules to introduce a realistic definition of a trip, which can be realized through a computationally expensive brute force approach. Therefore, TrajSplit offers two scalable heuristic approaches, that still achieve a very similar accuracy to its brute force. Experimental results, based on two real datasets, show that TrajSplit: (a) is far more accurate than the basic rules, and (b) is highly scalable when employing either of the heuristics.

  PublisherDOI

• A Framework for Continuous kNN Ranking of EV Chargers with Estimated Components

  2024-05-13 · 1 citations

  article

  In this paper, we present an innovative framework whose objective is to allow drivers to recharge their Electric Vehicles (EVs) from the most environmentally friendly chargers using an intelligent hoarding approach. These chargers maximize renewable (e.g., solar) self-consumption, minimizing this way CO2 production and also the need for expensive stationary batteries on the electricity grid to store renewable energy that cannot be used otherwise. We model our problem as a Continuous k-Nearest Neighbor query, where the distance function is computed using Estimated Components (ECs), i.e., a query we term CkNN-EC. An EC defines a function that can have a fuzzy value based on some estimates. Specific ECs used in this work are: (i) the (available clean) power at the charger, which depends on the estimated weather; (ii) the charger availability, which depends on the estimated busy timetables that show when the charger is crowded; and (iii) the derouting cost, which is the time to reach the charger depending on estimated traffic. We devise the EcoCharge framework that combines these multiple non-conflicting objectives into an optimization task providing user-defined ranking means through an intuitive mobile GIS application. Particularly, our core algorithm uses lower and upper values derived from the ECs to recommend the top ranked EV chargers and present them through an intuitive map user interface to users. Our experimental evaluation with extensive synthetic and real traces from Germany, China, and USA along with EV charger data from Plugshare shows that EcoCharge meets the objective functions in an efficient manner, allowing continuous recomputation on the edge devices (e.g., Android Automotive OS, Android Auto or Apple Carplay).

  PublisherDOI

• Introduction to the Special Issue on Machine Learning and Location Data

  ACM Transactions on Spatial Algorithms and Systems · 2024-09-30 · 1 citations

  articleOpen accessSenior author

  Introduction to the Special Issue on Machine Learning and Location DataDue to the rapid development of location acquisition technologies, big location data are being collected from various data sources such as connected cars, sharing bikes, smartphones, sensors, social media, and Wi-Fi access points.This led to the proposal of various spatial algorithms, models, and systems to understand and model these data for intelligent transportation, business intelligence, public health, social economics, urban planning, urban resilience, and environmental sustainability.This ACM TSAS special issue on Machine Learning and Location Data includes 14 articles introducing novel and innovative techniques applied to location data.We received 36 submissions in total, and 14 of 36 were accepted for publication after at least one revision cycle.These 14 articles are organized and published in two separate issues.In this issue, we have 7 exciting articles covering the fundamental issues in location data-those include the intricacies of the underlying spatio-temporal network representations, the dynamic correlation of spatio-temporal data, including the sequential and causal behaviors, and, finally, the anomalies due to location dynamics during extreme events.The first 2 articles in this issue deal with the spatio-temporal characteristics of the road network, the complexity and the varying resolutions of the network.The first article, titled "Spatio-temporal Dual Graph Neural Networks for Travel Time Estimation, " presents a graph-based model that incorporates node-and edge-wise graphs to characterize adjacency of intersections and capture the network architecture at multiple scale to solve travel time estimation problem.The second article, titled "Deformation Gated Recurrent Network for Lane-level Abnormal Driving Behavior Recognition, " presents conditional random field model to detect anomalous behavior at lane-level granularity, rather than at road-level.The next 2 articles tackle the complex spatio-temporal correlations in location data.The third article, titled "Adaptive Spatio-temporal Graph Learning for Bus Station Profiling, " aims to model the interactions between spatio-temporal correlations, capture the shift of distributions, and model the long-term patterns of bus station profiles.The fourth article, titled "Adaptive Joint Spatiotemporal Graph Learning Network for Traffic Data Forecasting, " aims at modeling the dynamic spatio-temporal correlations in long-term intervals towards more effective traffic forecasting.The next 2 articles focus on a set of sequential prediction and recommendation tasks.In the fifth article, titled "Geography-aware Heterogeneous Graph Contrastive Learning for Travel Recommendation, " a multi-view contrastive learning method is proposed to fuse the heterogeneous information from the user and the travel product representation to handle sparsity and provide more diverse views.In the sixth article, titled "Causal Probabilistic Spatio-temporal

  PublisherOA PDFDOI

Recent grants

• CAREER: Extensible Personalization of Spatial and Spatio-temporal Database Management Systems

  NSF · $530k · 2010–2017

• II-NEW: Research Infrastructure for Big Spatial and Temporal Data

  NSF · $392k · 2015–2020

• III: Small: Indexing, Querying, and Visualizing Big Spatial and Spatio-temporal Data

  NSF · $500k · 2015–2020

• III: Small: Adopting Machine Learning Techniques for Big Spatial and Spatio-temporal Data and Applications

  NSF · $500k · 2019–2023

• III-COR-Small: Collaborative Research: Preference- And Context-Aware Query Processing for Location-based Database Servers

  NSF · $254k · 2008–2012

Frequent coauthors

• Walid G. Aref

  80 shared

• Ahmed Eldawy

  University of California, Riverside

  67 shared

• Mohamed Sarwat

  43 shared

• Jie Bao

  Nanjing University of Aeronautics and Astronautics

  40 shared

• Lei Chen

  The First Affiliated Hospital, Sun Yat-sen University

  38 shared

• China Becker

  Hong Kong University of Science and Technology

  36 shared

• Amr Magdy

  University of California, Riverside

  29 shared

• Justin J. Levandoski

  Google (United States)

  28 shared

Labs

• Mohamed F. MokbelPI

Awards & honors

• 2023: Distinguished McKnight University Professor
• 2022: ACM SIGSPATIAL 10-Year Impact Award
• 2020: IEEE Fellow
• 2017: ACM Distinguished Engineers, Scientists, and Members