Accurate Land Use and Land Cover (LULC) mapping in high-latitude mountain regions faces critical challenges from persistent cloud cover and complex topography, which limit the utility of passive optical sensors. To address the absence of evidence-based guidelines for these data-scarce environments, this study employs a systematic ablation design to quantify the marginal and synergistic contributions of optical data (Sentinel-2), Synthetic Aperture Radar (Sentinel-1 SAR), topography, and intra-seasonal phenological metrics within the Aysén River basin, Chilean Patagonia, developing a geospatial workflow with high transferability potential. Using a Random Forest classifier, five progressive configurations were compared: a seasonal optical baseline (A), and configurations incorporating intra-seasonal percentiles (A + P), topography (A + T), SAR (A + R), and their full integration (A + P + T + R). The baseline model achieved an Overall Accuracy (OA) of 89.2% and a Macro-F1 of 80.5%; the fully integrated model reached OA = 92.5% and Macro-F1 = 86.0%. Macro-F1 was adopted as the primary metric because it assigns equal weight to all 11 classes regardless of spatial prevalence, capturing gains in minority but ecologically critical classes that OA would mask. SAR and topographic variables were the largest contributors, generating non-redundant improvements in structurally complex and relief-conditioned classes, respectively. Furthermore, annual SAR composites demonstrated superior cartographic spatial consistency over seasonal aggregations, which introduced purely cartographic geometric artifacts at class ecotones despite achieving marginally higher point-based statistical metrics, a divergence explained by the spatial blindness of confusion-matrix validation to boundary-zone classification errors.
Escalona et al. (Thu,) studied this question.