Cross-City Transferability of Urban Green View Index Estimation from Satellite Imagery within Selected European Contexts

Traditional green view index (GVI) estimation depends on street-view imagery, which is geographically uneven, costly, and infrequently updated. This paper proposes SatGreenCNN, a convolutional neural network (CNN) that estimates GVI directly from freely available Sentinel-2A Level-2A imagery using eight interpretable ground indices. We validated the approach on 19 European cities partitioned via principal component analysis and K-means clustering into a training cluster (Group Seen, 8 cities) and a held-out cluster (Group Unseen, 11 cities). The resulting evidence is interpreted as cross-city transferability within selected European contexts. SatGreenCNN reached an R 2 = 0 . 66 on the Group Seen set and a mean R 2 = 0 . 59 (range 0.53–0.65) on the Group Unseen set. A complementary ordinal-grade evaluation classifies unseen-city greenery into low/medium/high categories with an accuracy of 0.83, outperforming random forest, XGBoost, LightGBM, and three alternative variants, on average, while using roughly three orders of magnitude fewer parameters than a ResNet18 baseline.