Urban ecology is a rapidly growing research field that has to keep pace with the pressing need to tackle the sustainability crisis. As an inherently multi-disciplinary field with close ties to practitioners and administrators, research synthesis and knowledge transfer between those different stakeholders is crucial. Knowledge maps can enhance knowledge transfer and provide orientation to researchers as well as practitioners. A promising option for developing such knowledge maps is to create hypothesis networks, which structure existing hypotheses and aggregate them according to topics and research aims. Combining expert knowledge with information from the literature, we here identify 62 research hypotheses used in urban ecology and link them in such a network. Our network clusters hypotheses into four distinct themes: (i) Urban species traits & evolution, (ii) Urban biotic communities, (iii) Urban habitats and (iv) Urban ecosystems. We discuss the potentials and limitations of this approach. All information is openly provided as part of an extendable Wikidata project, and we invite researchers, practitioners and others interested in urban ecology to contribute additional hypotheses, as well as comment and add to the existing ones. The hypothesis network and Wikidata project form a first step towards a knowledge base for urban ecology, which can be expanded and curated to benefit both practitioners and researchers.

BACKGROUND: Combining different sources of knowledge to build improved structure activity relationship models is not easy owing to the variety of knowledge formats and the absence of a common framework to interoperate between learning techniques. Most of the current approaches address this problem by using consensus models that operate at the prediction level. We explore the possibility to directly combine these sources at the knowledge level, with the aim to harvest potentially increased synergy at an earlier stage. Our goal is to design a general methodology to facilitate knowledge discovery and produce accurate and interpretable models.
RESULTS: To combine models at the knowledge level, we propose to decouple the learning phase from the knowledge application phase using a pivot representation (lingua franca) based on the concept of hypothesis. A hypothesis is a simple and interpretable knowledge unit. Regardless of its origin, knowledge is broken down into a collection of hypotheses. These hypotheses are subsequently organised into hierarchical network. This unification permits to combine different sources of knowledge into a common formalised framework. The approach allows us to create a synergistic system between different forms of knowledge and new algorithms can be applied to leverage this unified model. This first article focuses on the general principle of the Self Organising Hypothesis Network (SOHN) approach in the context of binary classification problems along with an illustrative application to the prediction of mutagenicity.
CONCLUSIONS: It is possible to represent knowledge in the unified form of a hypothesis network allowing interpretable predictions with performances comparable to mainstream machine learning techniques. This new approach offers the potential to combine knowledge from different sources into a common framework in which high level reasoning and meta-learning can be applied; these latter perspectives will be explored in future work.