Klaus Böhm

As road users and means of transport in Germany become more diverse, we must better understand the causes and influencing factors of serious crashes. The aim of this work is to develop an AI-supported analysis approach that identifies and clearly visualizes the causes of crashes and their impact on crash severity in the urban area of the city of Mainz. The machine learning models predict crash severity and use Shapley values as explainability methods to make the underlying patterns understandable for urban planners, safety personnel, and other stakeholders. A particular challenge lies in presenting these complex relationships in a user-friendly way through visualizations and interactive maps.

Understanding spatiotemporal relationships is essential for effective urban decision-making. In this context, interactive geovisualizations offer the promising potential to support precise, rational-analytical decision processes. This paper examines a refined version of our GeoVisual Analytics tool called GC-Analyzer for analyzing spatiotemporal relationships in urban environments. We report the results of a case study where the tool was utilized in planning parking garages in a city and discuss the benefits of an interactive, geovisual analysis approach. We compare the GC-Analyzer approach with a conventional tabular representation of spatiotemporal correlations in a controlled usability study with expert users, evaluating two real-world analysis scenarios. Findings reveal that the GC-Analyzer provides substantial added value in spatiotemporal analysis, particularly enhancing users’ comprehension of complex correlations. Notably, decision-making with the GC-Analyzer was more analytical and objective, fostering a deeper understanding of spatiotemporal relationships than the tabular representations typically used for correlation results.

As road users and means of transport in Germany become more diverse, we must better understand the causes and influencing factors of serious accidents. The aim of this work is to develop an AI-supported analysis approach that identifies and clearly visualizes the causes of accidents and their impact on accident severity in the urban area of the city of Mainz. The machine learning models predict accident severity and use Shapley values as explainability methods to make the underlying patterns understandable for urban planners, safety personnel, and other stakeholders. A particular challenge lies in presenting these complex relationships in a user-friendly way through visualizations and interactive maps.

Geospatial use cases involve data with a geospatial and a temporal dimension. Machine learning is applied to such use cases for tasks such as prediction and classification. However, machine learning models are often perceived as opaque and incomprehensible. Explainable artificial intelligence can be used for either global explanations that provide an overview of the model behavior, or local explanations that explain individual predictions in detail. These approaches may be either too general or too detailed for analysis in geospatial contexts. This study introduces a novel concept ‘Geo-Glocal Explainable Artificial Intelligence’ that combines the strengths of global and local explanations to provide a more balanced explanatory power. The concept uses the geospatial and temporal dimension in the data to aggregate local explanations into geo-glocal slots, to focus on the geospatial context. These slots are scalable and can be applied according to the different dimensions in the data. The concept is applied to a real-world use case-predicting car park occupancy. The results of the application are evaluated against the traditional global and local explanations. The study shows that bridging the gap between local detail and global overview can be of great benefit to geospatial machine learning, improving understandability of the model’s behavior in a geospatial context.

Walking is a sustainable, safe, and active mode of transportation. The benefits that the elderly in particular gain from outdoor walking are manifold, be it free andindependent access to stores and services of all kinds or the opportunity to socialize, enjoy parks, et cetera. This article depicts one particular factor that affects outdoor walkability,namely the gradient of walking paths. Steep slopes can be a serious obstacle to walkability, primarily for older people. The evaluation of available geospatial data sources formedthe basis for a geospatial analysis of walkability in the larger city of Kaiserslautern, located in southwest Germany. The concept of Walk Score was used to quantify the resultsobtained. The results demonstrate that the Walk Score can be refined to better address the mobility needs of older adults. The methodology was implemented for the German cityof Kaiserslautern by integrating volunteered geographic information with high-quality official datasets.

Explainable Artificial Intelligence (XAI) has the potential to open up black-box machine learning models. XAI can be used to optimize machine learning models, to search for scientific findings, or to improve the understandability of the AI system for the end users. Geospatial XAI refers to AI systems that apply XAI techniques to geospatial data. Geospatial data are associated with geographical locations or areas and can be displayed on maps. This paper provides an overview of the state-of-the-art in the field of geospatial XAI. A structured literature review is used to present and discuss the findings on the main objectives, the implemented machine learning models, and the used XAI techniques. The results show that research has focused either on using XAI in geospatial use cases to improve model quality or on scientific discovery. Geospatial XAI has been used less for improving understandability for end users. The used techniques to communicate the AI analysis results or AI findings to users show that there is still a gap between the used XAI technique and the appropriate visualization method in the case of geospatial data.

Geospatial factors, because of their spatio-temporal correlations with demand-driven limited service, offer to improve urban planning decisions and expand the knowledge base in cities. Spatio-temporal analyses require an efficient and comprehensible visualization and explanation in order to analyze and understand geospatial relationships in urban areas. The aim of our research is to support domain experts in these analyses with user-oriented geovisualization. In this article, we propose concepts towards a semantic comparison visualization, which combines a visual analysis view and a visual explanation view. The visual analysis view is a knowledge-oriented view that focuses on analyzing resulting spatio-temporal correlations. The visual explanation view is an understanding-oriented view that focuses on explaining the underlying complex analysis process of geospatial factors and spatio-temporal correlations. We define general requirements for this aim and validate and evaluate our concepts related to these requirements. The results show the benefit of our concepts, but, at the same time, they also point to limitations and potential for optimization in further work.

This paper uses various machine learning methods which explore the combination of multiple sensors for quality improvement. It is known that a reliable occupancy estimation can help in many different cases and applications. For the containment of the SARS-CoV-2 virus, in particular, room occupancy is a major factor. The estimation can benefit visitor management systems in real time, but can also be predictive of room reservation strategies. By using different terminal and non-terminal sensors in different premises of varying sizes, this paper aims to estimate room occupancy. In the process, the proposed models are trained with different combinations of rooms in training and testing datasets to examine distinctions in the infrastructure of the considered building. The results indicate that the estimation benefits from a combination of different sensors. Additionally, it is found that a model should be trained with data from every room in a building and cannot be transferred to other rooms.

In this publication we introduce a linked data powered application which assists users to find so-called Stolpersteine, stones commemorating Jewish victims of the second world war. We show the feasibility of a dedicated location based service as an app using linked data resources and evaluate this approach against local data sources gathered by communities to find out if the current linked data environment can equally and/or sufficiently support an application in this knowledge domain.