Robert Keller’s research while affiliated with Kempten University of Applied Sciences and other places

In light of global warming, hotels account for one of the highest energy demands within the building sector, offering great decarbonization potential. As electrification increases, so does the demand for electric vehicles (EVs) charging stations at hotels and the proportion of Vehicle-to-Building-capable EVs. Therefore, the study explores the potential of guest-centric energy management. To accomplish this, we develop an optimization model for an energy management system that focuses on either cost-efficiency or carbon dioxide equivalents (CO2)-efficiency, grounded in a real-world case study. Through scenario analyses considering seasons as well as different guest mobility behaviors, this study discusses the expenses associated with CO2 savings using digital solutions. It emphasizes the currently perceived conflict between cost reduction and decarbonization goals to achieve a sustainable design of information systems. Thereby, this study highlights the critical importance of individual mobility behavior in enabling sustainable energy management for hotels.

Ecosystems have the promising potential to respond to economic but also environmental and social challenges, such as by enabling circular thinking, establishing fair supply chains, responsible collaborations, and ensuring resilience. In this report, we summarize findings from multiple data sources in the context of the NaWerSys workshop series which was held together with the INFORMATIK conference. The results are informed by experiences collected from full-day paper sessions in 2021, 2022, and 2023, and a world café-based discussion with 15 participants from different backgrounds, including sustainability, engineering, platform governance, product service systems, and artificial intelligence. We structured the results along with four main fields of action concerning the core, the value, the design, and the management of sustainable ecosystems. By jointly elaborating on the status quo and possible research directions, the findings aim to advance our understanding and boost the concept of sustainable ecosystems.

After the temporary shock of the Covid-19 pandemic, the rapid recovery and resumed growth of the tourism sectors accelerates unsustainable tourism, resulting in local (over-)crowding, environmental damage, increased emissions, and diminished tourism acceptance. Addressing these challenges requires an active visitor management system at points of interest (POI), which requires local and timely POI-specific occupancy predictions to predict and mitigate crowding. Therefore, we present a new approach to measure visitor movement at an open-spaced, and freely accessible POI and evaluate the prediction performance of multiple occupancy and visitor count machine learning prediction models. We analyze multiple case combinations regarding spatial granularity, time granularity, and prediction time horizons. With an analysis of the SHAP values we determine the influence of the most important features on the prediction and extract transferable knowledge for similar regions lacking visitor movement data. The results underline that POI-specific prediction is achievable with a moderate relation for occupancy prediction and a strong relation for visitor count prediction. Across all cases, XGBoost and Random Forest outperform other models, with prediction accuracy increasing as the prediction time horizon shortens. For effective active visitor management, combining multiple models with different spatial aggregations and prediction time horizons provides the best information basis to identify appropriate steering measures. This innovative application of digital technologies facilitates information exchange between destination management organizations and tourists, promoting sustainable destination development and enhancing tourism experience.

Artificial intelligence (AI) promises various new opportunities to create and appropriate business value. However, many organizations-especially those in more traditional industries-struggle to seize these opportunities. To unpack the underlying reasons, we investigate how more traditional industries implement predictive maintenance, a promising application of AI in manufacturing organizations. For our analysis, we employ a multiple-case design and adopt a critical realist perspective to identify generative mechanisms of AI implementation. Overall, we find five interdependent mechanisms: experimentation; knowledge building and integration; data; anxiety; and inspiration. Using causal loop diagramming, we flesh out the socio-technical dynamics of these mechanisms and explore the organizational requirements of implementing AI. The resulting topology of generative mechanisms contributes to the research on AI management by offering rich insights into the cause-effect relationships that shape the implementation process. Moreover, it demonstrates how causal loop diagraming can improve the modeling and analysis of generative mechanisms.

The design of sustainable urban environments is one of the most pressing endeavors. Particularly the emergence of digital technologies has triggered a range of technocentric movements for urban development, such as smart cities or districts. City stakeholders, including city or district planners, public administrators, or governance stakeholders, expect technological innovations to enhance life in the city. However, citizens are under-represented in discussions about respective technical designs. Against this backdrop, we measure 2930 German citizens' preferences for smart energy technologies and services of future smart districts as a small sub-area of the city and starting point for larger change. Using Best-Worst scaling, we find that citizens prefer local energy storage, photovoltaic, and district and local heating systems. Further, a cluster analysis reveals three distinct clusters of citizens with different preferences. We describe the clusters in terms of socio-demographics, living situation, attitude to sustainability, and affinity for technology. Results provide insight by revealing cit-izens' preferences for smart energy technologies and services that can inform the design of future citizen-centered smart districts.

Tourism is an important economic driver for numerous regions, attracting more than one billion visitors annually. While economically significant, excessive numbers of visitors lead to local overcrowding, which negatively impacts visitors’ experience and safety, and causes environmental harm. This paper proposes a practical approach to empowering destination management organizations (DMOs) to manage tourist flows. We advocate for a rule-based approach that models visitor occupancy based on easily understandable influence factors like weather and date. As a central component, an ontology-guided knowledge graph ensures compatibility with diverse touristic data models and allows seamless integration into existing infrastructures. By digitizing DMOs’ experiential knowledge, we facilitate the implementation of lean and cost-effective visitor guidance. We demonstrate our approach by implementing two applications for two different use cases. The results of our qualitative evaluation reveal the compelling potential for rule-based occupancy modeling approaches serving as a baseline for future visitor management systems.

Cities worldwide are seeking to enhance their sustainable mobility by reducing individual motorized transportation. While intermodal mobility-combining multiple transportation modes in one journey-is a key solution, individuals encounter challenges initiating intermodal journeys owing to the proliferation of mobility services. Providing accurate information at the right time is crucial amidst this complexity. While research has examined information needs for each mobility mode independently, the relationships between modes, phases, and information needs have barely been empirically investigated. Through a sequential mixed-method approach involving a literature review and a survey of >500 participants, this study identifies and validates the concept of phase-and mode chain-sensitive information needs. The findings provide initial insights, emphasizing phase relationships, mode chain relationships, and the interplays between phases and mode chains-a holistic understanding. This research can guide the design of more effective traveler information systems, aiding the shift toward sustainable urban mobility.

Carsharing is an integral part of the transformation toward flexible and sustainable mobility. New carsharing programs are entering the market to challenge large operators by offering innovative services. This study investigates the use of generative machine learning models for creating synthetic data to support carsharing decision-making when data access is limited. To this end, it explores the evaluation, selection, and implementation of leading-edge methods, such as gener-ative adversarial networks (GANs) and variational autoencoders (VAEs), to generate synthetic tabular transaction data of carsharing trips. The study analyzes usage data of an emerging car-sharing program that is expanding its services to include free-floating electric vehicles (EVs). The results show that augmenting real training data with synthetic samples improves predictive modeling of upcoming trips by up to 4.63%. These results support carsharing researchers and practitioners in generating and leveraging synthetic mobility data to develop solutions to real-world decision support problems in carsharing.