Accelerating the Adoption of Knowledge Graphs for Cross-Disciplinary Collaboration in Wind Energy

This study takes a comprehensive look at the adoption and use of Knowledge Graphs (KGs), a powerful technology for representing, structuring, and interoperating heterogeneous data, in wind energy. We systematically review sixteen implementations of KGs in wind energy, analysing their graph data models, construction strategies, technology stack, semantic formalisms and application areas. We find that current implementations predominantly use Labelled Property Graphs (LPGs) for isolated applications such as fault diagnosis and maintenance analytics, with limited adherence to semantic web standards (e.g., RDF, OWL) or FAIR (Findable, Accessible, Interoperable, Reusable) data principles. This means their potential as interoperable semantic backbones for intelligent decision support and cross-disciplinary collaboration remains under-exploited. Based on this finding, we identify key challenges hindering broader adoption and propose a set of targeted recommendations to accelerate the deployment of KGs in wind energy. These include the development of shared ontologies, greater alignment with semantic web standards and FAIR principles, and stronger data governance and capacity-building initiatives. This paper positions KGs as a foundational technology for the digital transformation of the wind energy sector.