Write a PREreview

Accurate Land Use and Land Cover (LULC) mapping in high-latitude mountain regions faces critical challenges from persistent cloud cover and complex topography, factors which limit the utility of passive optical sensors. To address the lack of operational guidelines for these data-scarce environments, this study establishes a transferable geospatial workflow based on 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. Using a Random Forest classifier, we implemented a progressive integration framework to compare a seasonal optical baseline model (A) against configurations incorporating intra-seasonal percentiles (A+P), topography (A+T), SAR (A+R), and their full integration (A+P+T+R). While the baseline model achieved an Overall Accuracy (OA) of 89.2% and a Macro-F1 of 80.5%, the fully integrated model reached an OA of 92.5% and a Macro-F1 of 86.0%. Notably, the inclusion of structural information from SAR and topography was decisive in improving the discrimination of complex vegetation classes, contributing to a net increase of +5.5 percentage points in the Macro-F1 score. Furthermore, the analysis revealed that annual SAR composites offer superior spatial consistency compared to seasonal aggregations, which introduce geometric artifacts despite high statistical metrics. These results demonstrate that the proposed structural–spectral integration framework resolves persistent ambiguities in transitional zones, providing a robust, replicable solution for ecosystem monitoring in complex high-latitude environments.