It has been well established in the literature that surface contamination can adversely affect the aerodynamic performance of aerofoils and, hence, the efficiency with which turbines can convert wind energy to electrical power. Thus, for optimal power production, it is critical to ensure that turbine blades are kept contaminantfree to the greatest extent possible. In this thesis, LIBS was performed in both the Vacuum Ultraviolet and Ultraviolet Visible spectral ranges. Analysis of the spectra showed only slight variations in the constituent materials between clean and contaminated blade samples. Four methods were investigated to discriminate between clean and contaminated blades: Partial Least Squares Discriminant Analysis , Support Vector Machines , Competitive Learning, and Convolutional Neural Networks were evaluated. The spectral regions where machine learning algorithms were applied were determined via a volumetric ellipsoid overlap test based on Principal Component Analysis . LIBS, in this way, can be used for interim end-point detection; that is, the point at which the laser has adequately removed contaminants from the current Area of Irradiation before moving to the adjacent AoI must also be determined. In addition to LIBS analysis, this work presents a new laser ablation cleaning protocol validated by profilometry. Statistical tests, such as ANOVA and Tukey’s HSD tests, confirmed the significant improvement of surface smoothness after laser cleaning, proving the non-destructive nature of this technique over manual cleaning. Profilometry analysis showed that laser cleaning can selectively remove contaminants while preserving the integrity of the substrate. This thesis also presents novel advances in standoff detection systems. Telescopic imaging coupled with object detection models like YOLOv8 were utilised for remote monitoring of blade contamination and damage with high precision and recall.