Health assessment method of cave murals based on entropy-weighted AHP-cloud model

Cave murals are vital to cultural heritage, but they face an escalating risk of deterioration due to environmental and anthropogenic factors. Current assessments that rely on expert judgment lack objectivity and comprehensiveness. This study proposes an innovative health assessment framework that combines the analytic hierarchy process (AHP) with entropy weighting to objectively assign indicator weights, calculate hazard scores, and classify health levels. Combined with a common cloud model, it analyzes the dynamic sensitivity of murals to deterioration through digital features and cloud mapping. The method enables multidimensional quantitative analysis from historical, current, and prognostic perspectives, providing data-driven support for prioritizing preventive conservation. By minimizing subjective bias and combining assessment with predictive power, this approach improves the accuracy of degradation management and advances the digital preservation of mural heritage. This study aims to provide a mural health assessment system that prioritizes method validation over case-specific findings.