This study analyzes the production of green hydrogen using dedicated offshore wind power in the Dutch North Sea region. The analysis is based on a detailed techno-economic model that simulates physical flows and estimates the levelized cost of hydrogen (LCOH). However, the model’s outputs depend on user-provided inputs and evaluating all possible inputs is computationally infeasible. To this end, “optimization with constraint learning” is employed, where surrogate machine learning models are trained on simulation data and embedded in mixed-integer optimization problems. The surrogate models are trained on 4096 simulation runs and achieve a mean absolute percentage error of ≤[jls-end-space/]3% for physical flow-related outputs, and an error of ≈[jls-end-space/]10% for the LCOH-related outputs. Once trained, these surrogates enable one to solve stakeholder–specific problem instances in sub-second solve times, supporting rapid scenario analysis and trade-off exploration.

A restructuring of the current mobility and transportation system seems to be inescapable, as a result of the increasing urbanization and challenges regarding global sustainability. The concept of Mobility-as-a-Service (MaaS) is regarded by policy-makers as an answer to the needed change. Generally speaking, MaaS is an online platform that enables users to plan, book and pay a trip out of a variety of transport modes, conventional and shared. However, in the literature, the potential impact of MaaS on mobility is still relatively unclear. This study, therefore, aims to provide insights into which factors influence the intention to use MaaS among private vehicle owners, who have until now been identified as relatively MaaS-averse travellers. Policy-makers are highly interested in this group to start using MaaS since their shift from private vehicles to other transport options might positively contribute to easing the congestion and environmental problems. In order to create some insights on possible travel behavioural shift and adoption of new systems, an empirical study has been conducted among (co–)owners of motorized vehicles (passenger car, electric passenger car, van, motorcycle; moped) that live in the Netherlands. The survey was based on a conceptual model that explains why people would use this new system (MaaS) and has asked respondents about their travel behaviour, socio-economic characteristics and attitudes towards MaaS. Using Latent Class Cluster Analysis (LCCA) five clusters in the sample population regarding the intention to use MaaS were identified. The cluster profiles show that private vehicle owners who often use public transport and active modes are most inclined to use MaaS, whereas the ‘conservative’ passenger car owners who use the car as their main mode of transport for all their trips (e.g. commuting, leisure) show a lower intention to use MaaS. As it can be expected that the societal benefits of MaaS will especially occur when these conservative car owners adopt MaaS, we conclude that, from a policy perspective, implementing MaaS could be less effective in reducing transport externalities (e.g. pollution and wasted time in congestion) as perhaps expected.