Archaeologists can now use advanced excavation techniques thanks to advances in technology, allowing for greater recovery of fragile artefacts. The latest digital project, which will involve researchers from across the University as well as the University of Otago and the Otago Museum, will use instrumentation, computational modelling, and machine learning to record and analyse large collections of cultural artefacts. The goal is to create digital repositories of our cultural heritage that are widely accessible to iwi and archaeologists worldwide.
The project has received $1 million in MBIE (Ministry of Business, Innovation and Employment) Endeavour – Smart Ideas funding. A professor from the Auckland Bioengineering Institute (ABI), whose research focuses on using mathematical modelling of complex biological systems to better understand and treat the disorders that can affect them, was excited at the expansive use. He feels it is an opportunity to take their research outside the bioengineering field and re-purpose it to record, analyse and popularise cultural heritage – much of which lies in large collections of repositories and museums.
The initiative will address the critical shortage of resources in archaeology and museums by developing tools that allow for the automatic identification, measurement, processing and interpretation of these artefacts. These have been discovered as a result of archaeological research or when archaeologists are called in to preserve valuable historical remains prior to housing or commercial development.
Professors of archaeology were acutely aware of a problem in the recording and analysis of our cultural heritage. The country has a large number of stone artefacts excavated from the past, but it lacks the resources and expertise to do anything about it – going through so many artefacts take a long time.
They were alerted to the other department in computational modelling and imaging techniques developed at the ABI, as well as the machine-learning research of another Professor and his team in the School of Computer Science, through serendipitous connections and “one degree of separation”. It occurred to them that they could collaborate to piece together the past using cutting-edge technologies and expertise that represent the future in many ways.
The project will involve the creation of a database that distinguishes, first and foremost, human-modified artefacts from those created by natural environmental forces. Next will entail ‘teaching’ a machine to distinguish one from the other and to identify the shape, size and characteristics of each object. Combining archaeological expertise, imaging capabilities and machine-learning capabilities, AI programmes will be able to quickly recognise what these objects are. This would improve the ability to manage and interpret heritage records, fragmented across museums, labs and storage facilities.
They are confident that this method could change the approach to heritage in New Zealand and around the world. As the professor notes, this is likely to be of immense value to archaeologists and heritage globally. “If we can succeed in this, we can use it nationally, but sell the technology internationally, including to Australia which has such vast areas and so many such valuable Indigenous objects to analyse.”