TU Dortmund University

More and more people move to cities, urban areas become denser, space more scarce. As a consequence, house prices increase, leading to gentrification and displacement in city centres. At the same time, there is untapped potential for densification in suburban areas. Such suburban densification bears the potential of alleviating the negative consequences of housing shortage. In addition, densification is considered critical by urban planning to tackle climate change mitigation and adaptation by reducing net land uptake. But suburban densification is tricky as it meets plural rationalities of space, actors, and policies. Plural rationalities of space entail that suburban areas are socially constructed - conceived - by its landowners not by one logic, but multiple conceptions of space - space as territory, as economic asset, as social status, etc - coexist. In addition, there is often strong resistance to change in suburban areas, impeding the implementation of densification. Such resistance stems from different interpretations of densification by actors - i.e. landowners and local stakeholders. Furthermore, suburban densification policy by national or urban planning meets locationally specific politics of space. Public policy interventions in land – land policy – that does not take into account these plural rationalities of policy are deemed to fail. This project seeks to better understand the polyrationalities of space, actors and policies on suburban densification. It will explore how diverse strategies of land policy interact with landowners’ and local stakeholders’ interest and agency to shape suburban densification and their impact on suburbia across different planning systems. There are methodological and theoretical challenges with this aim of the project. Densification processes are analyzed in-depth in case studies. To explore polyrationalities, data science and spatial analysis is combined in this project with socio-anthropological approaches (Cultural Theory) and spatial planning across different institutional contexts. Such an endeavour implies to combine knowledge, methodologies and theories from different disciplines, able to reveal polyrationalities of each element alone - space, actors, and policies - and in combination. Ultimately, SUBDENSE combines geospatial and socio-demographic data to analyse and inform on polyrationalities. This entails to assess and enhance the fitness of data for comparative analysis of understanding densification phenomena on the ground as well as for communication and decision-making in a densification dashboard.

The Affordable AI (AffAI) proposal aims to address three bottlenecks preventing industrial end users from tapping into the potential of AI technologies: * a considerable know-how is required to build data-driven intelligent systems. The exploration of the processing pipelines (pre-processing and learning algorithms, and their hyper-parameters), referred to as AutoML, is increasingly acknowledged as non sustainable due to its huge computational cost. * black-box models learned from data are not satisfactory for reliability, fairness, and accountability reasons. * in many industrial sectors one can only gather small data (contrasting with the wealth of data behind the AI breakthroughs). One must thus find a way to leverage the knowledge of the domain experts to palliate the lack of data. AffAI builds up a consortium involving 2 international level Universities, renowned for their leadership in AI: Univ. Paris-Saclay and TU Dortmund University, and 2 AI SMEs, RapidMiner and MyData Models. This consortium is able to: i) actually understand the main needs of industrial end users; ii) design accurate solutions by leveraging and adapting the best state of the art; iii) implement these solutions in a professional and efficient way; iv) enforce their fast dissemination thanks to an active network of corporate customers and a large size user community. The above three bottlenecks will be addressed by, building upon the complementary expertises of the consortium: 1. AutoML will be extended to accommodate the fact that end users are actually interested in several performance indicators (including the overall computational cost), making the search for a good pipeline a multi-criteria optimization problem. A most innovative aspect is to address Embeddable AutoML, where the training of the intelligent systems is done on-board, subject to specific resource constraints. 2. Two functionalities will be provided to open the black-box of the learned intelligent systems: a sensitivity analysis, showing how the current decision proposed by the system depends on the case and its context; a causal model, characterizing how the features of the case depend on each other. This causal model will support the exploration of *interventions*, aimed to modify the features when possible in order to bring desired effects. 3. The shortage of data, and possibly the partially incomplete specifications of the sought intelligent systems will be addressed by leveraging the expertise of the domain expert, through interaction. On the one hand, the shortage of data will be palliated by active learning (asking the domain expert to label a few dozens most informative cases). On the other hand, the models compliant with the evidence will iteratively be demonstrated to the domain expert, who will be able to provide a simple feedback about which model is more appropriate than the other. This interactive dialog will support the gradual learning of the expert's preferences and expectations, and will be used to shape the behavior of the eventual intelligent system. The validation and transfer of the proposed functionalities will be achieved along an original 2-tier mechanism: * The two SMEs will provide 2 representative use cases, respectively related to predictive maintenance and process optimization, on which they can gather and share data. * The proposed functionalities will be first validated on these use cases. * In a third phase, these functionalities will be applied on similar but confidential industrial applications. The SMEs will thus be able to assess and enforce the robustness and generality of these functionalities, interacting back and forth with the Labs and with their end-users. Ultimately, AffAI is relevant to Green AI, as it expects to significantly decrease the computational cost of building intelligent systems, and to the Democratisation of AI, through enabling industrial end users (and others) to build and trust intelligent systems.

The overall goal of AQUACLEW is to use innovative research techniques and integrated co-development with users to advance the quality, and usability of climate services that provide climate change information to water related sectors. Data and information in present climate services reflect high uncertainties and low resolution, which is difficult to use in practical climate adaptation work. AQUACLEW will therefore work to improve confidence and site specific information by better tailoring climate data and adaptation knowledge. In AQUACLEW, we not only co-develop the climate service with users, we also co-develop the research requirements, the service interfaces and the guidance tools. By integrating users and researchers throughout the climate service production chain, the quality, usability and user uptake of climate services for water will be improved. Data providers and researchers will more fully understand user needs and users will be updated on the latest scientific knowledge; better understand potentials or limitations of the data, and can influence (choose between) assumptions made in each step when producing the service output. In AQUACLEW we aim to produce research that will be transferable to improve climate services everywhere. During the project we will develop regional, national and pan-European climate services together with some 30 users to be evaluated in 7 real-world climate adaptation case studies across Europe. These cover a diverse array of water affected sectors, i.e. (i) flash flood risks in pre-alpine regions, (ii) flash flood risks in urban areas (iii) drought and water resource allocation for industry, tourism, agriculture and energy, (iv) hydropower production, (v) biodiversity decline, (vi) agricultural production and (vii) sediment transport and coastal erosion. Project results will be quantified by comparing climate service usability and economic cost of adaptation studies for these case studies before and after the project.