 The paper examined the use of the random forest algorithm for the non-invasive assessment of excessively damp and salty historic brick walls. The algorithm was found to be highly accurate, with correlation coefficients of 0.801 and 0.803 for two different buildings. Additionally, the algorithm had low median absolute error and relative error rates of 1.79% and 13.75% respectively. These results suggest that the random forest algorithm can be used as a reliable tool for non-destructive assessments of historic brick walls. This article was authored by Anna Ola.