| Optimal Band Selection for Airborne Hyperspectral Imagery to Retrieve a Wide Range of Cyanobacterial Pigment Concentration Using a Data-Driven Approach |
|---|
|
학술지명 Remote Sensing
저자 신재기
발표일 2022-04-06
|
|
Understanding the concentration and distribution of cyanobacteria blooms is an importantaspect of managing water quality problems and protecting aquatic ecosystems. Airborne hyperspectralimagery (HSI)?which has high temporal, spatial, and spectral resolutions?is widely usedto remotely sense cyanobacteria bloom, and it provides the distribution of the bloom over a widearea. In this study, we determined the input spectral bands that were relevant in effectively estimatingthe main two pigments (PC, Phycocyanin; Chl-a, Chlorophyll-a) of cyanobacteria by applyingdata-driven algorithms to HSI and then evaluating the change in the spatio-temporal distribution ofcyanobacteria. The input variables for the algorithms consisted of reflectance band ratios associatedwith the optical properties of PC and Chl-a, which were calculated by the selected hyperspectralbands using a feature selection method. The selected input variable was composed of six reflectancebands (465.7?589.6, 603.6?631.8, 641.2?655.35, 664.8?679.0, 698.0?712.3, and 731.4?784.1 nm). Theartificial neural network showed the best results for the estimation of the two pigments with averagecoefficients of determination 0.80 and 0.74. This study proposes relevant input spectral informationand an algorithm that can effectively detect the occurrence of cyanobacteria in the weir pool alongthe Geum river, South Korea. The algorithm is expected to help establish a preemptive response tothe formation of cyanobacterial blooms, and to contribute to the preparation of suitable water qualitymanagement plans for freshwater environments. |