A new study in *Frontiers in Materials* addresses eco-friendly detection of raveling, a common asphalt pavement disease. Raveling, which begins with the loss of fine aggregates and progresses to displacement of larger particles, is frequently observed in open-graded friction courses and airport pavements, where age-related distress results from severe erosion of the bituminous mastic. Contributing factors include material aging, insufficient binder content, improper compaction, freeze-thaw cycles, oxidation, and excessive traffic loads. The disease significantly impacts passenger comfort and pavement durability, and untreated raveling reduces skid resistance, accelerates moisture infiltration, increases road noise, and poses safety hazards. The research builds on prior work, including findings that traffic loads and asphalt mixture properties significantly influence pavement distress, and that machine learning methods can intelligently identify disease causes. The study focuses on using in-situ data and transfer learning for raveling detection, aiming to support scientific maintenance decision-making by improving the accurate classification of pavement diseases.