Bridging World Heritage Management with Climate Change Adaptation in the Netherlands using Artificial Intelligence

Abstract

UNESCO World Heritage (WH) properties are increasingly vulnerable to challenges caused by climate change, which requires them to balance the needs of heritage management with sustainable urban growth and climate change adaptation (CCA). CCA strategies are being developed by stakeholders at all levels. It is, however, not customary to generalise strategies developed in one property to another, since they are assumed to be highly localised. This paper takes the WH properties in the Netherlands as an example and showcases that topics relevant to CCA, such as climate change challenges and water management strategies, are being shared among properties in their heritage management plans, aiming to safeguard their Outstanding Universal Value. Sentence embeddings computed with cutting-edge Natural Language Processing models are used to retrieve similar topics among the properties and evaluate their associations. Common challenges (such as low groundwater level) and strategies (such as coastal dunes and dykes) are found to be mentioned in different properties. The methodological framework proposed in this paper, bridging CCA with WH management, can be repeated in other countries, and eventually at the global level, providing a generalisable integrated knowledge system beneficial and easily applicable in heritage properties from broad geographical and cultural contexts.