Krzysztof Janowicz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Krzysztof Janowicz has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Gengchen Mai
SEAI Lab, Department of Geography and the Environment, University of Texas at Austin, Austin, TX, USA
5 shared publications - Mina Karimi
University of Vienna
4 shared publications - Song Gao
University of Wisconsin–Madison
4 shared publications - Zilong Liu
University of Vienna
4 shared publications - Ivan Majic
Department of Geography and Regional Research University of Vienna Vienna Austria
3 shared publications - Zhangyu Wang
School of Computing and Information Science, University of Maine, ME, USA
3 shared publications
Latest Publications
- Open Access
- 19 November 2026
- Published by Taylor & Francis in Spatial Cognition & Computation
- p. 1-40
Through the eyes of the machine: how foundation models represent vague cognitive regions
- 19 November 2026
- Published by Taylor & Francis in Spatial Cognition & Computation
- p. 1-40
Open AccessThrough the eyes of the machine: how foundation models represent vague cognitive regions
- Open Access
- 3 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 133-143
How Geographic Information Influences Vision-Language Model Judgments of Urban Scenes
- 3 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 133-143
Open AccessHow Geographic Information Influences Vision-Language Model Judgments of Urban Scenes
- Open Access
- 21 May 2026
- Published by IOS Press
- p. 215-232
On the Ethics of Generative GeoAI: Explainability, Bias, Hallucination, Accountability, Privacy, and Trust
With the rapid development of generative artificial intelligence (GenAI), multiple ethical problems emerge, many of which have distinct implications for geography and geospatial artificial intelligence (GeoAI). With a focus on GeoAI and its impact on humans’ perception of geography, this chapter reviews key ethical issues in the conceptualization, development, and deployment of generative AI systems. Our discussion will address key challenges, including model explainability, bias, hallucination, accountability, privacy, and trust, which influence both model training and user interaction. We will conclude by recommending best practices for developing generative GeoAI models that align with established ethical guidelines.
- 21 May 2026
- Published by IOS Press
- p. 215-232
Open AccessOn the Ethics of Generative GeoAI: Explainability, Bias, Hallucination, Accountability, Privacy, and Trust
With the rapid development of generative artificial intelligence (GenAI), multiple ethical problems emerge, many of which have distinct implications for geography and geospatial artificial intelligence (GeoAI). With a focus on GeoAI and its impact on humans’ perception of geography, this chapter reviews key ethical issues in the conceptualization, development, and deployment of generative AI systems. Our discussion will address key challenges, including model explainability, bias, hallucination, accountability, privacy, and trust, which influence both model training and user interaction. We will conclude by recommending best practices for developing generative GeoAI models that align with established ethical guidelines.
- Open Access
- 23 March 2026
- Published by Wiley in Transactions in GIS
- Vol. 30 (2)
Golden Gate Bridge, as Always? Eliciting Prototypical Places From Autoregressive Large Language Models via Category Production
Among the various theories of categorization, Eleanor Rosch's prototype theory stands out as both influential and contested. In contrast to the classical theory of concepts, prototype theory posits that humans conceptualize the world using category structures where exemplars vary in their degree of membership. While this theory remains well‐regarded among cognitive psychologists as an account of human cognition, we know little about whether artificial agents—particularly large language models (LLMs)—also use a similar type of categorization. Given that these models have shown to mirror human‐like cognitive abilities, an important question arises: Do they also encode categories with graded membership? This question also invites a broader ethical reflection: While substantial research has documented a lack of diversity in LLM outputs, few has realized that such bias can be understood as a graded structure in the model's internal representations of categories. In this study, we explore this possibility by examining the geographical conceptualizations of 11 autoregressive LLMs. Guided by prior work that advocated empirical, inductive testing for studying geographic categories, we employ a cognitive‐psychology experiment known as category production . It prompts a model to generate exemplars of a given category. This approach yields an extensive list of category norms (i.e., typical items associated with a category) across 297 geographic categories, revealing their graded structures both encoded within individual models and collectively. Notably, we discover a strong presence of prototypical places shared across different sampling temperatures, geographic categories, and models. Furthermore, we observe and explain a lack of geographic diversity in LLM outputs through the lens of prototype theory.
- 23 March 2026
- Published by Wiley in Transactions in GIS
- Vol. 30 (2)
Open AccessGolden Gate Bridge, as Always? Eliciting Prototypical Places From Autoregressive Large Language Models via Category Production
Among the various theories of categorization, Eleanor Rosch's prototype theory stands out as both influential and contested. In contrast to the classical theory of concepts, prototype theory posits that humans conceptualize the world using category structures where exemplars vary in their degree of membership. While this theory remains well‐regarded among cognitive psychologists as an account of human cognition, we know little about whether artificial agents—particularly large language models (LLMs)—also use a similar type of categorization. Given that these models have shown to mirror human‐like cognitive abilities, an important question arises: Do they also encode categories with graded membership? This question also invites a broader ethical reflection: While substantial research has documented a lack of diversity in LLM outputs, few has realized that such bias can be understood as a graded structure in the model's internal representations of categories. In this study, we explore this possibility by examining the geographical conceptualizations of 11 autoregressive LLMs. Guided by prior work that advocated empirical, inductive testing for studying geographic categories, we employ a cognitive‐psychology experiment known as category production . It prompts a model to generate exemplars of a given category. This approach yields an extensive list of category norms (i.e., typical items associated with a category) across 297 geographic categories, revealing their graded structures both encoded within individual models and collectively. Notably, we discover a strong presence of prototypical places shared across different sampling temperatures, geographic categories, and models. Furthermore, we observe and explain a lack of geographic diversity in LLM outputs through the lens of prototype theory.
- Open Access
- 2 February 2026
- Published by Elsevier in Computers, Environment and Urban Systems
- Vol. 126
Semantic data enrichment for maintenance of foundation spatial data
- 2 February 2026
- Published by Elsevier in Computers, Environment and Urban Systems
- Vol. 126
Open AccessSemantic data enrichment for maintenance of foundation spatial data
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 799-803
Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 799-803
Open AccessWhose Truth? Pluralistic Geo-Alignment for (Agentic) AI
- Top Cited PapersOpen Access
- 9 August 2025
- Published by Taylor & Francis in International Journal of Geographical Information Science
- Vol. 39 (9) , 1849-1865
GeoFM: how will geo-foundation models reshape spatial data science and GeoAI?
- 9 August 2025
- Published by Taylor & Francis in International Journal of Geographical Information Science
- Vol. 39 (9) , 1849-1865
Top Cited PapersOpen AccessGeoFM: how will geo-foundation models reshape spatial data science and GeoAI?
- Open Access
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Technology and Society
- Vol. 6 (2) , 129-154
Locational Data and the Public Interest
This article presents a paper developed by the AAG Organizing Committee on Locational Information and the Public Interest through a summit held in Santa Barbara, California in June 2022. The summit resulted in goals and ideas for addressing the issues that arise from the present environment for geodata, whereby public, private, and third-sector entities can tap into publicly available locational information with relatively little regulation on its access or use. The Committee articulates four goals: (1) develop a research agenda extending across disciplines, (2) outline educational resources and strategies to guide ethical practice, (3) devise a pathway to increase public understanding, and (4) create a path to increased dialogue with non-traditional and indirect stakeholders in GIS, as well as increased collaboration between academic, public, and private sectors on the use of locational information. These goals were developed to highlight the host of ethical issues that may arise in the use of locational data, whether for research, commercial application, public administration, communities or any other purpose. Some of the ethical issues are specific to this type of data and will not arise over the use of data that are not locational. Others are common to data sampling, in general, regardless of whether location is collected or not. For this project, the focus is on those issues that arise only when the data are locational. GeoEthics is the term used by this Committee that incorporates geoprivacy among other concepts.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Technology and Society
- Vol. 6 (2) , 129-154
Open AccessLocational Data and the Public Interest
This article presents a paper developed by the AAG Organizing Committee on Locational Information and the Public Interest through a summit held in Santa Barbara, California in June 2022. The summit resulted in goals and ideas for addressing the issues that arise from the present environment for geodata, whereby public, private, and third-sector entities can tap into publicly available locational information with relatively little regulation on its access or use. The Committee articulates four goals: (1) develop a research agenda extending across disciplines, (2) outline educational resources and strategies to guide ethical practice, (3) devise a pathway to increase public understanding, and (4) create a path to increased dialogue with non-traditional and indirect stakeholders in GIS, as well as increased collaboration between academic, public, and private sectors on the use of locational information. These goals were developed to highlight the host of ethical issues that may arise in the use of locational data, whether for research, commercial application, public administration, communities or any other purpose. Some of the ethical issues are specific to this type of data and will not arise over the use of data that are not locational. Others are common to data sampling, in general, regardless of whether location is collected or not. For this project, the focus is on those issues that arise only when the data are locational. GeoEthics is the term used by this Committee that incorporates geoprivacy among other concepts.
- Open Access
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 99-105
Spatial Task-Explicity Matters in Prompting Large Multimodal Models for Spatial Planning
The advance in large multimodal models (LMMs) gives rise to autonomous bots that perform complex tasks using human-like reasoning on their own. The ability of large models to understand spatial relations and perform spatial operations, however, is known to be limited. This gap hinders the development of autonomous GIS analysts, travel planning assistants, and other possibilities of spatial bots. In this paper, we explore the impact of modality on the performance of LMMs in spatial planning tasks - specifically, retrieving a target brick by first removing all other bricks on top of it. Experiments demonstrate that what matters is not only the modality of the prompts (text or image), but also how informative the spatial descriptions are for the LMMs to complete the task. We propose novel concepts of task-implicit and task-explicit spatial descriptions to qualitatively quantify the task-specific informativity of prompts. Furthermore, we develop simple techniques to increase the spatial task-explicity of image prompts, and the accuracy of spatial planning increases from 26% to 100% accordingly.
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 99-105
Open AccessSpatial Task-Explicity Matters in Prompting Large Multimodal Models for Spatial Planning
The advance in large multimodal models (LMMs) gives rise to autonomous bots that perform complex tasks using human-like reasoning on their own. The ability of large models to understand spatial relations and perform spatial operations, however, is known to be limited. This gap hinders the development of autonomous GIS analysts, travel planning assistants, and other possibilities of spatial bots. In this paper, we explore the impact of modality on the performance of LMMs in spatial planning tasks - specifically, retrieving a target brick by first removing all other bricks on top of it. Experiments demonstrate that what matters is not only the modality of the prompts (text or image), but also how informative the spatial descriptions are for the LMMs to complete the task. We propose novel concepts of task-implicit and task-explicit spatial descriptions to qualitatively quantify the task-specific informativity of prompts. Furthermore, we develop simple techniques to increase the spatial task-explicity of image prompts, and the accuracy of spatial planning increases from 26% to 100% accordingly.
- 8 December 2023
- Published by Taylor & Francis
- p. 411-426
Fast Forward from Data to Insight: (Geographic) Knowledge Graphs and Their Applications
In this chapter, we explain what knowledge graphs are, how they relate to GeoAI research such as knowledge engineering and representation learning, discuss their value proposition for geography and the broader geosciences, outline application areas for knowledge graphs across domains, and introduce the KnowWhereGraph as an example of a geospatially centered, highly heterogeneous graph consisting of billions of graph statements extracted from 30 different data layers at the intersection between humans and the environment.
- 8 December 2023
- Published by Taylor & Francis
- p. 411-426
Fast Forward from Data to Insight: (Geographic) Knowledge Graphs and Their Applications
In this chapter, we explain what knowledge graphs are, how they relate to GeoAI research such as knowledge engineering and representation learning, discuss their value proposition for geography and the broader geosciences, outline application areas for knowledge graphs across domains, and introduce the KnowWhereGraph as an example of a geospatially centered, highly heterogeneous graph consisting of billions of graph statements extracted from 30 different data layers at the intersection between humans and the environment.