Use of Artificial Intelligence Toward Climate-Neutral Cultural Heritage

Abstract

Cultural heritage (CH) aims to create new strategies and policies for adapting to climate change. Additionally, the goals of sustainable development aim to protect, monitor, and preserve the world's CH and to take urgent action to combat climate change and its effects. Therefore, developing efficient and accurate techniques toward making CH climate neutral and more resilient is of vital importance. This study aims to provide a holistic solution to monitor and protect CH from climate change, natural hazards, and anthropogenic effects in a sustainable way. In our study, the efficiency of deep learning using low-cost unmanned aerial vehicles and camera images for the documentation and monitoring of CH is investigated. The dense extreme inception network for edge detection and richer convolutional feature architectures have been used for the first time in the literature to extract contours and cracks from CH structures. As a result of the study, F1 scores of 61.38% and 61.50% for both architectures, respectively, were obtained. The results show that the proposed solution can aid in monitoring the protection of CH from climate change, natural disasters, and anthropogenic effects.