Abstract This study investigates the potential of artificial intelligence (AI) to replace human experts in evaluating the conservation status of architectural heritage. Five mainstream AI models were employed to assess six architectural heritage sites in Kunming, Yunnan, China, using 18 evaluation indicators. The AI Evaluation Team (AET) and Expert Evaluation Team (EET) conducted comprehensive assessments, and the results were compared using the entropy weight method (EWM), independent sample t-tests, and kernel density estimations. The findings revealed no significant differences between the AET and EET outcomes, demonstrating that the AI’s assessment capability reached expert-level performance. Moreover, AI exhibits higher efficiency in information acquisition and work processes than human expertise. The objectivity of the AI-generated results was enhanced by the data-driven approach and the use of the EWM for indicator weighting. This study highlights the potential of AI in architectural heritage preservation, enabling the assessment of a larger number of heritage buildings within a shorter timeframe and overcoming the limitations of manual evaluation. The proposed method can be extended to assess various types of cultural heritage and predict future trends, providing a more efficient basis for heritage protection.
Wang et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: