A New Data-Mining Method for the Digital Great Wall Exemplified by Statistical Evaluation and Analysis of the Ming Great Wall Archery Windows.

The authors reveal the functions of the Ming Great Wall's archery windows as well as the wisdom behind their construction. They developed a cross-regional, quantitative research method that identifies heritage values, beginning with data collection by drones, proceeding through data processing using artificial intelligence, and concluding with data analysis via landscape archaeology. The data collection method respects the morphology of the Great Wall and the rugged terrain around it. The authors improved an existing neural network by introducing automatic labeling and processing of image data. The method performs automatic statistical analyses of basic features such as the size, proportion, and morphology of archery windows along the Great Wall. The functions of the windows become apparent, as do the strategical importance to garrisons of watchtowers with windows and the principles of defensive zone planning that considers the surrounding terrain. The method breathes new life into heritage places and adds value to heritage interpretations. The images that the authors acquired and processed render heritage value analysis more efficient. Their method aids value mining and conservation of large cultural heritage sites. [ABSTRACT FROM AUTHOR]