Spectral Complexity of Hyperspectral Images: A New Approach for Mangrove Classification

Hyperspectral remote sensing across multiple spatio-temporal scales allows for mapping and monitoring mangrove habitats to support urgent conservation efforts. The use of hyperspectral imagery assessing mangroves is less common than terrestrial forest ecosystems. In this study, two well-known measures in statistical physics, Mean Information Gain (MIG) Marginal Entropy (ME), have been adapted high spatial resolution (2.5 m) full range (Visible-Shortwave-Infrared) airborne imagery. These spectral complexity metrics describe the heterogeneity aspatial reflectance. we compare MIG ME with surface reflectance extent species composition Sierpe Costa Rica. highest accuracy separating from was achieved visible-near infrared (VNIR) (98.8% overall accuracy), following by shortwave (SWIR) (98%). Our results also show that can discriminate dominant higher alone (e.g., MIG–VNIR = 93.6% vs. VNIR Reflectance 89.7%).