Researchers to recover Europe’s lost smells

Scientists are using artificial intelligence (AI) to research past and present smells of Europe to identify and trace their link to language, places, cultural practices and emotions.

The international research project, Odeuropa, has received 2.8m (2.5m) of funding from the EU Horizon 2020 programme. It is the first European initiative to use AI to investigate the importance of scents and smelling, and to discover how scents have moulded our communities and traditions.

The information gathered will be stored in a database called the European Olfactory Knowledge Graph, with academics from the UCL Institute for Sustainable Heritage leading the work on olfactory heritage science, involving historic scent preservation and communication.

The goal of the project is to show that critically engaging our sense of smell and our scent heritage is an important and viable means of connecting and promoting Europe’s tangible and intangible cultural heritage.

Dr Cecilia Bembibre Jacobo (UCL Institute for Sustainable Heritage) said: "We are delighted to have this opportunity to advance smell preservation using heritage science techniques, and to better understand how we can access historic smells to enrich our experience of heritage today.

"Our role in Odeuropa is to lead the scientific analysis and preservation of the key scents of Europe from both the past and present."

The ISH team’s expertise in engaging with the heritage sector will be used to share the key scents of Europe in museums between 2021 and 2023, allowing everyone to experience the past through scents.

"Smells shape our experience of the world, yet we have very little sensory information about the past", explained project lead Professor Inger Leemans (VU University and the Royal Netherlands Academy of Arts & Sciences Humanities Cluster). "Odeuropa will dive into digital heritage collections to discover the key scents of Europe and the stories they carry, then bring them back to our noses today."

Odeuropa will find references to smells such as disease-fighting perfumes, tobacco or the stench of industrialisation in historic literature and paintings using AI techniques, aiming to teach the computer to see a smell.

Computer linguistics expert Sara Tonelli (Fondazione Bruno-Kessler, Italy) explained: "Our goal is to develop a ’computer nose’ able to trace scents and olfactory experiences in digital texts over four centuries and seven languages."


  • Welcome to Odeuropa