Using AI to automatically detect archaeology from Earth Observation data

ArchAI automates the assessment of archaeological sites required by environmental impact assessments (EIAs) during the planning permission application process for construction projects within Europe. Its pre-trained AI models can assess thousands of images instantly, providing rapid, accurate feedback to developers and project planners.

As a space sector company reliant on satellite data, ArchAI uses AI to rapidly and automatically detect buried archaeological remains using Earth Observation (EO) data. This facilitates the identification of potential issues within the Environmental Impact Assessment (EIA) as part of the consents stage of a planning application. 

Currently, the analysis of EO data is not integrated at the start of the planning process, and is often only requested alongside geophysics and trial trenches at later stages. ArchAI’s automated assessments of EO data offer higher accuracy at an earlier stage, offering significant savings on construction projects.

Space archaeology supports construction industry

In December 2020, the government redefined the meaning of ‘treasure’ to increase the protection for archaeological finds to ensure more significant artefacts are saved for the public. For the first time, the official definition of treasure would not be based solely on the material qualities of an artefact. The changes have made the treasure finds process more transparent and efficient for museums and the public.

To respond to these new changes, ArchAI planned to use space archaeology and EO data to help the construction industry by spotting likely sites with archaeology, saving people and businesses money when acquiring planning permission by significantly lowering the risk of construction inadvertently beginning on a burial site.

Space archaeology uses satellites or high-flying aircraft to take pictures remotely of the Earth’s surface to find hints of ancient features buried under the ground. Things may show up visually or near-infrared light may show small differences in vegetation, with growth on top of buried stone likely to be less healthy.

This particular project was funded by the UK Space Agency, via the national SPRINT business support programme.

Lowering cost of construction and preserving historical sites

For the SPRINT project, ArchAI collaborated with experts at the University of Southampton, based on the University’s capabilities in archaeology and as it is a leading centre for remote sensing, geophysics, geomatics and the application of advanced computing for heritage purposes.

Knowing where archaeology is located at the earliest planning stages of large construction projects will allow accurate estimates of time and cost involved with acquiring planning permission and significantly reduces the risk of discovering unexpected archaeology during construction. This means that ArchAI will be able to lower the cost of construction and ensure that vital historical sites are preserved.

ArchAI’s automated analysis will be integrated into a web application to provide customers with instant insights into this crucial project risk. Access to ArchAI’s technology will lower the cost of construction and ensure that vital historical sites are preserved for future generations.

Benefits achieved through the SPRINT support included:

• Proof of the scalability of Iris Kramer’s PhD research which clearly demonstrated the potential of AI. This is helping with establishing partnerships with key stakeholders in the sector who will help to generate wide support and adoption of the technology

• Established new collaborations and joint ventures including the National Trust, where a first commercial project has been completed, and the Forestry Commission

• Using the outcomes of the project to apply for other grants including a successful application to ESA Business Incubation Centre Harwell and also from NESTA, the UK’s innovation agency for social good

• Hired two consultants on the project, kept one of them on a full-time basis after the project and the other is still brought in for projects

Improving solution to scale globally

Iris Kramer, CEO of ArchAI, said:

---

“This project, in collaboration with the University of Southampton, has helped us to increase the training data and new datasets of known archaeological sites, and validate our AI across the country to detect unknown sites.

---

“That has already helped us to use the SPRINT model as a platform to develop other commercial opportunities. We’re also now able to improve our solution on satellite imagery which will help us scale globally.”

Critical to understanding of the past and future development

Dr Fraser Sturt, Professor of Archaeology at the University of Southampton, added: “Aerial photography transformed archaeology in the early 20th century, revealing sites in a way that few people could have conceived of in the past. Advances in Earth Observation EO and machine learning offer another leap forward, helping us to identify and monitor sites across space and time. This information is critical not only for our understanding of the past, but how we manage the built environment and its development in the future.

---

“We are proud that we were able to bring our expertise to ArchAI’s SPRINT project and that the results of this work have generated further commercial successes for the company in the space archaeology area.”

---