Damage Assessment of Earthen Sites of the Ming Great Wall in Qinghai Province

Support Vector Machine (SVM) emerges as a superior model for assessing damage to earthen sites of the Ming Great Wall in Qinghai Province, outperforming traditional back-propagation Neural Networks. This study demonstrates that SVM can accurately predict damage levels, providing a robust tool for conservation efforts. Researchers trained and tested two machine learning algorithms using data from 18 earthen sites, with SVM showing significantly better predictive performance. Validated through the case study of Liutun Great Wall, this approach offers a practical solution for preserving these historically significant structures, which have endured environmental threats for centuries.

Du, Y., Chen, W., Cui, K., Zhang, J., Chen, Z., & Zhang, Q. (2020). Damage Assessment of Earthen Sites of the Ming Great Wall in Qinghai Province. Journal on Computing and Cultural Heritage, 13(2), 1–18. https://doi.org/10.1145/3376120