Sound exposure data are central for any intervention study. In the case of utilitarian mobility, where studies cannot be conducted in controlled environments, exposure data are commonly self‐reported. For short‐term intervention studies, wearable devices with location sensors are increasingly employed. We aimed to combine self‐reported and technically sensed mobility data, in order to provide more accurate and reliable exposure data for GISMO, a long‐term intervention study. Through spatio‐temporal data matching procedures, we are able to determine the amount of mobility for all modes at the best possible accuracy level. Self‐reported data deviate ±10% from the corrected reference. Derived modal split statistics prove high compliance to the respective recommendations for the control group (CG) and the two intervention groups (IG‐PT, IG‐C). About 73.7% of total mileage was travelled by car in CG. This share was 10.3% (IG‐PT) and 9.7% (IG‐C), respectively, in the intervention groups. Commuting distances were comparable in CG and IG, but annual mean travel times differ between x¯  = 8,458 min (σ = 6,427 min) for IG‐PT, x¯  = 8,444 min (σ = 5,961 min) for IG‐C, and x¯  = 5,223 min (σ = 5,463 min) for CG. Seasonal variabilities of modal split statistics were observable. However, in IG‐PT and IG‐C no shift toward the car occurred during winter months. Although no perfect single‐method solution for acquiring exposure data in mobility‐related, naturalistic intervention studies exists, we achieved substantially improved results by combining two data sources, based on spatio‐temporal matching procedures.

Natural language processing systems like ChatGPT have recently attracted enormous attention in the field of higher education. We aim to contribute to this discussion by scrutinizing the suitability of current testing methods and potentially necessary shifts in learning objectives in GIScience. This paper presents an anecdotal approach to the impact of ChatGPT on teaching and learning based on a real-world use case. It focuses on the results of a fictional student who used ChatGPT for the completion of applicationdevelopment assignments, including coding. The solutions were submitted to the instructor, who assessed the results in a single-blind experiment. The instructor's feedback and grading as well as the AI-plagiarism results were part of our evaluation of the testing methods applied. This triggered a discussion on the adequacy of current learning objectives in the development of GIS applications and the integration of AI into the learning process.

With the advent of wearable GNSS devices and activity trackers, new opportunities for automatic travel-mode detection arise. Although physiological measures such as heart rates carry a high potential for travel-mode detection, little research has been done that exploits this data. This paper presents a rule-based method for the detection of the travel modes walk, bike, bus, train and car, based on the combination of GNSS and heart-rate data from off-the-shelf fitness watches. The aim of this research is to minimize the input variables and reference data for mode detection. In the case study, the proposed workflow performed very well and substantially reduced the confusion between active and motorized travel modes compared to a workflow that did not take heart rate into consideration, although the differentiation among motorized travel modes could be further enhanced with additional data. Combining GNSS data with physiological variables such as heart rate allows a clear reduction in the amount of reference data and processing effort required for mode detection.

Abstract. Mobility data of cyclists and pedestrians are fundamental for design and planning strategies of sustainable smart cities. However, adequate data is commonly scarce, expensive to acquire, or hardly accessible. For overcoming this shortcoming and providing support in planning processes, we propose an agent-based model that simulates bicycle and pedestrian traffic flows at a regional scale over one day. The bottom-up approach allows to set individual behaviour that generates system-level patterns. The uncertainty analysis of model results shows moderate and strong correlations with the observational data in terms of spatial and temporal distribution of traffic volumes. The model produces traffic flows at a high spatial (road segment) and temporal (minute) resolution. The model can be used as a scenario-based solution for simulating traffic in different conditions of a physical environment and travel behaviour.

Natural language processing systems like ChatGPT recently gained enormous attention in the field of higher education. We aim to contribute to this discussion by scrutinising the suitability of current testing methods and potentially necessary shifts in learning objectives in GIScience. This paper presents an anecdotal approach of the impact of ChatGPT on teaching and learning based on a real world use case. It focuses on the results of a fictional student who used ChatGPT for the completion of application development assignments, including coding. The solutions were submitted to the instructor, who assessed the results in a blind experiment. The instructor’s feedback and positive grading as well as the AI-plagiarism results were part of our evaluation of the applied testing methods. This triggered a discussion on the adequacy of current learning objectives in geo-application development and the integration of AI into the learning process.