Panellists take part in the session “Next-Gen Public Services: Anticipating and Fulfilling Citizen Needs”, during the GovTech Leaders 2024 conference in Vilnius, Lithuania, 24 September 2024.

Using AI to Preserve Lithuania’s Historic Buildings

Heading 1

Heading 2

Heading 3

Heading 4

Heading 5
Heading 6

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.

Owners of historic buildings in Lithuania submit photographs of the structure, which an AI-powered solution uses to detect and identify any damage. Based on the type of damage, the system provides the owner with tailored recommendations and actions to preserve the building. Granary of Pagryžuvys Manor. Kelmė, Lithuania. 3 March 2025.
Block quote

Ordered list

  1. Item 1
  2. Item 2
  3. Item 3

Unordered list

  • Item A
  • Item B
  • Item C

Text link

Bold text

Emphasis

Superscript

Subscript

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.

The sixth GovTech Challenge Series began in 2024 with an open call from GovTech Lab inviting public sector institutions in Lithuania to submit their most pressing challenges. Out of more than 70 unique submissions, a panel of experts selected the ten most promising problems to address. One standout entry was from the Centre for Cultural Infrastructure.

The Challenge

Owners of Lithuania’s historic buildings face the difficult task of identifying physical damage at an early stage and conducting preventive maintenance without compromising the cultural integrity of these sites. As part of the GovTech Challenge Series, the Centre for Cultural Infrastructure submitted a call for a digital solution to identify early damage in historic building façades from uploaded photographs. The solution was expected to achieve at least 65% accuracy in identifying the type of damage during the pilot phase and improve continuously as the database expands.

Owners of historic buildings in Lithuania submit photographs of the structure, which an AI-powered solution uses to detect and identify any damage. Based on the type of damage, the system provides the owner with tailored recommendations and actions to preserve the building, Granary of Pagryžuvys Manor, Kelme, Lithuania, 3 March 2025.

Idea Selection

The challenge was implemented through a public procurement process in the form of a design contest. Attractive cash prizes worth EUR 2,500–4,500 were awarded to the top three submissions. The first-place winner was granted a EUR 42,000 contract to develop a pilot version of their proposed solution.

During the contest, SMEs anonymously submitted demonstration versions of their solution and concept descriptions. A multidisciplinary jury comprising subject matter experts, information technology (IT) specialists, and service designers evaluated the proposals and selected the most promising concept.

Prototype Development and Impact

The winning proposal came from AAI Labs, a Lithuanian startup of more than 40 AI engineers who are specialists in machine learning, data science, and software engineering.

Over a three-month period, the Centre and AAI Labs collaborated to create a working prototype. The team developed an AI-powered system that analyses images of historic buildings to detect and classify structural damage. For each issue identified, the system provides a detailed description, the likely cause, and actionable repair recommendations. It also generates preventive maintenance plans with automated reminders to support the long-term care of heritage sites.

This innovative solution empowers site owners and managers to detect issues early, reduce maintenance costs, and extend the lifespan of culturally significant buildings. With further AI training and continued testing planned, it aims to improve the system’s accuracy and ensure it remains accessible and impactful for all users involved in the preservation of built cultural heritage.

Endnotes

  1. Item 1
  2. Item 2
  3. Item 3
Liucija Sabulytė

Liucija Sabulytė is the manager of GovTech Lab at Innovation Agency Lithuania. Previously, she worked as an innovation programme manager at GovTech Lab, coordinating the GovTech Challenge Series programme. Before joining GovTech Lab, Sabulytė served as a policy analyst with the design and behavioural insights team at Policy Lab, part of the Government Strategic Analysis Centre in Lithuania. In this role, she conducted research on public sector innovation and contributed to the preparation of the Lithuania Progress Strategy 2050.

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.