Optimal Band Selection for Airborne Hyperspectral Imagery to Retrieve a Wide Range of Cyanobacterial Pigment Concentration Using a Data-Driven Approach

Understanding the concentration and distribution of cyanobacteria blooms is an important aspect managing water quality problems protecting aquatic ecosystems. Airborne hyperspectral imagery (HSI)—which has high temporal, spatial, spectral resolutions—is widely used to remotely sense bloom, it provides bloom over a wide area. In this study, we determined input bands that were relevant in effectively estimating main two pigments (PC, Phycocyanin; Chl-a, Chlorophyll-a) by applying data-driven algorithms HSI then evaluating change spatio-temporal cyanobacteria. The variables for consisted reflectance band ratios associated with optical properties PC which calculated selected using feature selection method. variable was composed six (465.7–589.6, 603.6–631.8, 641.2–655.35, 664.8–679.0, 698.0–712.3, 731.4–784.1 nm). artificial neural network showed best results estimation average coefficients determination 0.80 0.74. This study proposes information algorithm can detect occurrence weir pool along Geum river, South Korea. expected help establish preemptive response formation cyanobacterial blooms, contribute preparation suitable management plans freshwater environments.