Current operational snow mapping products struggle to accurately map patchy, late-season snow cover in challenging environments like Scotland, hindering hydrological and ecological model validation. We hypothesise that machine learning (ML) could better handle these variable conditions, including dirty and metamorphosed snow, cloud and atmospheric disturbance, varying illumination levels and shading.</p> <p>To address this, we generated a novel Snow Cover Fraction (SCF) reference dataset for Sentinel-2 (10 m resolution) by aggregating manual and semi-automated <em>"pseudo-labels"</em> derived from 25 cm aerial surveys of Scotland. Using this dataset, we developed a Snow Patch U-Net (SPUN) by adapting a U-Net architecture with a regression head to predict SCF, utilising a combined Dice and L1 loss function. On our Scottish test set, SPUN successfully mapped challenging snow patches &ndash; even through cloud gaps and in topographic shadow &ndash; outperforming the operational Theia Let-It-Snow (LIS) product with a snow segmentation F1 score of 0.737, a Mean Absolute Error (MAE) of 28.49 %, and an RMSE of 42.16 %.</p> <p>Furthermore, by integrating pre-trained weights from satellite foundation models, our model demonstrated strong generalisation when applied to an independent global dataset, achieving a macro averages F1 Score of 0.9313 across the three classes (snow, cloud, background) and a snow-only F1 score of 0.8923.</p> <p>This study demonstrates that ML has the potential to tackle persistent challenges in optical snow retrieval. We suggest that a broader, community-driven effort to create a global, high-resolution training dataset could significantly advance snow mapping capabilities across optical satellite sensors.