If this sounds of interest, below you can read the abstract to our paper, see our workflow and resulting smellscape map. While the the analysis steps, along with the smell dictionary used, are documented in the research code compendium at https://figshare.com/s/8418d47cdc5c539b78ab. Finally at the bottom of the page, you can find the full reference and a link to the paper.
Abstract:
Smells can shape people’s perceptions of urban spaces, influencing how individuals relate themselves to the environment both physically and emotionally. Although the urban environment has long been conceived as a multisensory experience, research has mainly focused on the visual dimension, leaving smell largely understudied. This article aims to construct a flexible and efficient bottom-up framework for capturing and classifying perceived urban smells from individuals based on geosocial media data, thus, increasing our understanding of this relatively neglected sensory dimension in urban studies. We take New York City as a case study and decode perceived smells by teasing out specific smell-related indicator words through text mining techniques from a historical set of geosocial media data (i.e., Twitter/X). The data set consists of more than 56 million data points sent by more than 3.2 million users. The results demonstrate that this approach, which combines quantitative analysis with qualitative insights, can not only reveal “hidden” places with clear spatial smell patterns, but also capture elusive smells that might otherwise be overlooked. By making perceived smells measurable and visible, we can gain a more nuanced understanding of smellscapes and people’s sensory experiences within the urban environment. Overall, we hope our study opens up new possibilities for understanding urban spaces through an olfactory lens and, more broadly, multisensory urban experience research.
Key Words: geosocial media, multisensory urban experiences, network analysis, New York City, smellscape, text mining, urban smells.
A framework of deriving perceived smells.
An overview of research workflow.
An overview of the six dominant overlapping smells across New York City using the weaving mapping method. The weaving map uses the concept of strands to represent attributes. Each strand here represents one specific smell category, with the intensity of the color changing based on the density of that smell category within each neighborhood (i.e., grid cells).
Full Reference:
Chen, Q., Poorthuis A. and Crooks, A.T., (2025), Mapping the Invisible: Decoding Perceived Urban Smells through Geosocial Media in New York City, Annals of the American Association of Geographers. Available at https://doi.org/10.1080/24694452.2025.2485233. (pdf)
As the AAG has just wrapped up I thought I would write brief (well actually quite long) post on the talks that I was involved with at the conference. These talks would not have been possible without the many great students and colleagues who I have been collaborating with over time. Below you will find a brief summary of the talks and if any sound interesting, please reach out and we can give you more details.
First up (in order in which they were presented) was "Utilizing Streetview Images for Mapping Building Attributes with ChatGPT" with Qingqing Chen and Linda See. In this talk we discussed how multimodal Large Language Models are giving us a new way to study cities, in the sense, lowering the boundary for information extraction. Using ChatGPT andstreet view images from Mapillary as an example, we showed how one can extract building age, usage (e.g., commercial, mixed use, residential) and estimate building height which could all be used to inform urban climate models which require detailed information on buildings.
Abstract:
With increasing rates of urbanization, many challenges are emerging regarding sustainability such as the energy usage of buildings. Coinciding with this is the growing attention of urban climate models for energy demand estimation and climate adaptation strategies. However, the applicability of these models is constrained by the lack of detailed urban surface information. Therefore, creating comprehensive datasets that capture urban surface information at a granular scale is crucial for responding to our rapidly urbanizing world. Recent advancements in Large Language Models (LLMs) have opened new opportunities in urban studies, offering accessible methods for information extraction. In this talk we explore the feasibility of ChatGPT to extract building attributes from images. Taking New York City as a case study, we collect building images from Mapillary and process them through ChatGPT by posing specific questions to extract building attributes (e.g., height, functions, age). These attributes are then compared with authoritative data. The proposed method helps address the current dearth of fine-grained surface data on urban issues, therefore enhancing the accuracy and utility of urban climate models. Overall, this study demonstrates the practical applications of ChatGPT in geographic knowledge extraction, advancing the understanding of LLMs in geographic contexts, and more broadly to the discourse on Artificial Intelligence (AI) in urban modeling and climate science.
Keywords: Buildings, ChatGPT, Large Language Models (LLMs), Mapillary, Street View Images (SVI), GeoAI.
Example of Workflow.
Reference:
Chen, Q., See, L. and Crooks, A.T. (2025), Utilizing Streetview Images for Mapping Building Attributes with ChatGPT, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)
This was followed by a talk by lead by Qingqing Chen entitled "Multi-sensory Experiences: The Connection Between the Smell and Vision in Understanding Urban Environments" where we explored to what extent can visual data from street view imagery be used as a proxy for capturing large-scale urban smell perceptions when compared to geosocial media. Such as what visual cues evoke specific smell perceptions.
Abstract:
Smell is a crucial transversal sense, which bridges the tangible aspects of urban environments, such as exhaust and garbage, with their intangible impacts on emotions, social interactions and well-being. Despite its crucial role in our everyday life, many urban studies primarily focus on the visual dimension, potentially introducing biases in our understanding of urban spaces. This research transcends this visual-centric bias by integrating the olfactory perceptions to investigate the nuanced relationship between smell and vision in urban environments. Specifically, we utilize advanced semantic segmentation to extract visual elements from street view imagery (i.e., Mapillay) and apply casual forest analysis to examine their causal effects on smell expectations recorded from human participants. These expectations, often tied to personal experiences and/or cultural associations, are compared with real-environment smell experiences derived from geosocial media (i.e., Twitter/X). The results show that visual cues can predict smells in straightforward urban settings, such as small parks or less densely populated areas. However, in complex urban environments, the predictive power of visual cues diminishes as diverse and overlapping scents obscure specific smells, even in visually distinct areas. These findings underscore the importance of a multisensory approach in urban studies, enhancing our understanding of the complex interplay between sensory experiences and informing urban design strategies that integrate multiple senses to create more engaging and inclusive environments. This is especially important for individuals with sensory impairments, such as anosmia or visual impairments, who rely on other senses to compensate for their perception of urban environments.
Keywords: Multi-sensory Experiences, Smell and Vision; Semantic Segmentation, Causal Effects, Geosocial Media, Street View Imagery (SVI).
Workflow
Reference:
Chen, Q. and Crooks, A.T. (2025), Multi-sensory Experiences: The Connection Between the Smell and Vision in Understanding Urban Environments, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)
In the Geosimulation session that we organized, we had a talk entitled "Large Language Models for Conceptualizing, Designing, and Generating Agent-based Models" where Na Jiang, Boyu Wang and myself presented our work on exploring using multimodal Large Language Models (LLMs) to create age-based models. In the sense as modelers, we spend a lot of time developing and writing code and we were curious what could be done though the use of LLMs.
To give a sense of what is possible, below is an example of using ChatGPT for creating a model from a published paper.
Abstract:
Large language models (LLMs) play an important role in AI-powered code assistants such as code completion, debugging, and documentation. Such models can be further fine-tuned on smaller amount of data for specific tasks, often with the improvement of performance compared to generic LLMs. However, such fine-tuning techniques are seldomly used in generating sophisticated agent-based models (ABMs), because they are often implemented as software that demands extra standards such as the “Overview, Design concepts, and Details” (ODD) protocol. This research examines how we can bridge this gap by utilizing LLMs in designing or conceptualizing, building, and running agent-based models in the form of user prompts. . In this work, two models are created to demonstrate the proposed method. Specifically, Sakoda’s checkerboard model of social interaction is created by LLM from explicit design and description through prompts. The other model stimulates consumer preferences and restaurant visits as designed and implemented by a LLM. These models are evaluated by human experts on their code correctness and quality for both verification and validation purposes. This work serves as a first step towards fine-tuned LLMs on existing models and documentations to create high-quality and functional ABMs based on either user prompts or standard protocols, contributing to further exploration on the future of AI-assisted geospatial simulation development.
Keywords: Agent-Based Modeling, Large Language Models, Geospatial Simulation
Reference:
Jiang, N., Wang, B. and Crooks, A.T. (2025), Large Language Models for Conceptualizing, Designing, and Generating Agent-based Models, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)
Next up was Ying Zhou who presented our work entitled "Identifying Environmental Characteristics That Influence Perceived Safety in Urban Spaces." In this work we explored how using social media data can be used to study the fear and how this relates to actual crimes within New York city. Broadly speaking we find through our analysis, that fear sentiment may spread out between the neighborhoods and their surrounding areas and that neighborhoods surrounded by crime-clusters may have high sentiments of fear.
Abstract:
One goal of creating livable cities is to enhance health and safety. While previous research in spatial analysis and urban planning has focused on correlations between physical environments and crime, typically relying on police-reported crime data from sources like the Crime Open Database (CODE), safety perception is inherently subjective and cannot be fully represented by objective crime statistics alone. Also, urban planning today has gradually shifted its focus from a top-down mechanism to a bottom-up mechanism, so understanding and fostering spaces where residents feel safe is essential. This research examines factors that contribute to residents’ perceived insecurity in New York City. In addition to spatial analysis of the open crime data, the research used social media data to acquire people’s perceptions. The result indicates that the aggregations of perceived unsafe locations overlapped with aggregations of crime data's locations, such as in Manhattan’s neighborhoods, but they do not overlap with each other entirely. By adopting Latent Dirichlet Allocation (LDA), a method of topic modeling, the research filtered and summarized the posted texts and contents related to the negative descriptions of places or spaces in the city, and then it identified the related characteristics of the environments. The characteristics are investigated by the method of local Moran’s I, which indicates their spatial autocorrelation in some neighborhoods in the city of New York. This research offers “bottom’s views” about urban safety for both urban planning and decision-makers, which contributes to people-centered consideration for future development and urban resource distribution.
Zhou, Y. and Crooks, A.T. (2025), Identifying Environmental Characteristics That Influence Perceived Safety in Urban Spaces, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)
The last day of the conference was another busy day with two talks. First was entitled "PySGN: A Python Package for Constructing Synthetic Geo-social Networks" where Boyu Wang presented our work (with Taylor Anderson and Andreas Züfle) on a Python package that can be used to generate synthetic geo-social networks. As readers of this blog might know we have a an interest in social networks and using them in modeling and this package provides a toolkit for others to easily create their own geosocial networks (e.g., Geospatial Erdős-Rényi, Barabási–Albert and Watts-Strogatz models). For interested readers, the source code available at: https://github.com/wang-boyu/pysgn.
Abstract:
Synthetic population has been widely used in social simulations such as traffic modeling, pedestrian movements, and the spread of infectious diseases. In recent years, much attention was focused on generating synthetic population with social networks, that captures social connections between individuals. While synthetic populations are often geographically explicit, various algorithms have been proposed to create realistic geographic social (geo-social) networks, aiming to integrate spatial information into people’s social links. We build an open-source Python package, namely PySGN, for constructing synthetic geo-social networks that incorporates position information, exhibits small-world network properties, and can be scaled to hundreds of thousands and potentially millions of nodes. We discuss different ways of parametrizing the method, by either a global average node degree, or an expected degree for each individual node. It is demonstrated through a case study with synthetic population in Buffalo, NY. By doing so, we aim to illustrate how such synthetic geo-social networks can be created, utilized, and analyzed in downstream agent-based modeling and network analysis tasks. This work is available as an open-source Python package and integrated with the PyData ecosystem (e.g., GeoPandas, NetworkX), and can be further extended with more synthetic geo-social network algorithms in the future.
Wang, B., Crooks, A.T., Anderson, T. and Züfle, A. (2025), PySGN: A Python Package for Constructing Synthetic Geo-social Networks. The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)
The final talk (well for me) was presented by Fuzin Yin who presented our work with Lucie Laurian and Emmanuel Frimpong Boamah entitled "Analysis of Online Mutual Aid Network during Buffalo Blizzard 2022: Actors and Weak Ties." In this work we explored what kind of support was offered and requested over Facebook groups along with their network structures durring and shortly after the event utilizing machine learning.
Abstract:
In December 2022, Buffalo, NY encountered a once-in-a-generation blizzard that dropped over 4 feet of snow. This four-day snow event halted emergency services and left 47 dead. In the face of the devastating blizzard, Buffalonian demonstrated resilience and solidarity by establishing Facebook (FB) groups to share information and coordinate behaviors including donations, wellness checks, and snow removals. These spontaneous behaviors created an essential layer of protection when the major infrastructure was down. This research has collected data from Buffalo blizzard FB groups to analyze community-led self-help behaviors. We have used machine learning to classify FB messages into four categories (e.g., requesting help, offering help, emotional support, and other), and social network analysis to explore users’ communication patterns. Results show that out of all messages (n=9,988), 37% of them express emotional support, which is followed by messages offering help (25%). While requests for help constitute a small proportion (8%), they stimulate more replies than other categories. Network statistics suggest that the mutual aid network is low-density but with a high clustering coefficient. This implies that most group members are strangers with weak ties, but their connections are in the right place to allow efficient communication. However, users do not equally benefit where people requesting or offering help are central in online conversation while pure emotional supporters are at the periphery. We conclude that during the Buffalo blizzard 2022, online interactions translate into offline mutual assistance by establishing weak ties among disconnected users to facilitate the flow of information and resources.
Keywords: crisis informatics, mutual aid, social network analysis, machine learning, social media
Results of Mutual Aid Network during Buffalo Blizzard 2022
Reference:
Yin, F., Laurian, L., Crooks, A.T. and Boamah, E.F. (2025), Analysis of Online Mutual Aid Network during Buffalo Blizzard 2022: Actors and Weak Ties, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)
While this is a rather longer post than normal, we hope you found it interesting and also as noted at the top of the post, if any of these talks/topics are of interest to you please feel free to reach out.
There is an urgent need for research that promotes sustainability in an era of societal challenges ranging from climate change, population growth, aging and wellbeing to that of pandemics. These need to be directly fed into policy. We, as a Geosimulation community, have the skills and knowledge to use the latest theory, models and evidence to make a positive and disruptive impact. These include agent-based modeling, microsimulation and increasingly, machine learning methods. However, there are several key questions that we need to address which we seek to cover in this session. For example, What do we need to be able to contribute to policy in a more direct and timely manner? What new or existing research approaches are needed? How can we make sure they are robust enough to be used in decision making? How can geosimulation be used to link across citizens, policy and practice and respond to these societal challenges? What are the cross-scale local trade-offs that will have to be negotiated as we re-configure and transform our urban and rural environments? How can spatial data (and analysis) be used to support the co-production of truly sustainable solutions, achieve social buy-in and social acceptance? And thereby co-produce solutions with citizens and policy makers.
The call generated enough interest to allow us to organize two sessions with respect to geosimulations. With the AAG ongoing we thought we would post the session details and talks. Both sessions will take place in on Thursday the 27th of March in Room 420B, Level 4, Huntington Place.
Geosimulations for Addressing Societal Challenges (2); Time: 8:30 AM - 9:50 AM
In the past I have blogged about disasters, but mainly from a social media or agent-based modeling perspective. However, after the devastating wildfires that impacted parts of Los Angeles County earlier this year led me to wonder how resilient are cities to such events? Or more generally, what role could urban analytics play on the various stages of disaster management (i.e., preparation, response, recovery, and mitigation), or how can data, models, and methods at the disposal of researchers be leveraged to better prepare us for future disasters and be linked to policy?
We are delighted to announce a special track on “Integrating Large-Language Models and Geospatial Foundation Models to Enhance Spatial Reasoning in ABMs” as part of the Social Simulation Conference 2025, 25th to 29th August 2025 at Delft University of Technology, the Netherlands. Full conference details can be found at the end of this email.
Abstract for the Special Track:
Recent developments in the use of large language models (LLMs) offer exciting opportunities to control agent behaviour in potentially more realistic and nuanced ways than has previously been possible. However, an LLM-backed agent can only interface with their surroundings through text prompts, which is severely limiting. The integration of large language models (LLMs) and geospatial foundation models (GFMs) presents an exciting opportunity to use AI techniques to advance agent-based modelling for spatial applications, potentially allowing for agents with more comprehensive behavioural realism, as well as an improved perception of their environment.
This special track invites papers that explore how AI techniques, such as LLMs and GFMs, can enrich spatial agent based models, raising new questions about their feasibility in modelling human behaviour, in comparison to conventional approaches. There are huge challenges around computational efficiency, sustainability, bias, model validation, and integration frameworks, and we welcome papers that consider these issues as well.
