Remote quantification of phycocyanin in potable water sources through an adaptive model

摘要

Cyanobacterial blooms in water supply sources in both central Indiana USA (CIN) and South Australia (SA) are a cause of great concerns for toxin production and water quality deterioration. Remote sensing provides an effective approach for quick assessment of cyanobacteria through quantification of phycocyanin (PC) concentration. In total, 363 samples spanning a large variation of optically active constituents (OACs) in CIN and SA waters were collected during 24 field surveys. Concurrently, remote sensing reflectance spectra (R_(rs)) were measured. A partial least squares-artificial neural network (PLS-ANN) model, artificial neural network (ANN) and three-band model (TBM) were developed or tuned by relating the R_(rs) with PC concentration. Our results indicate that the PLS-ANN model outperformed the ANN and TBM with both the original spectra and simulated ESA/Sentinel-3/Ocean and Land Color Instrument (OLCI) and EO-1/ Hyperion spectra. The PLS-ANN model resulted in a high coefficient of determination (R~2) for CIN dataset (R~2 = 0.92, R: 0.3-220.7 μg/L) and SA (R~2 = 0.98, R: 0.2-13.2 μg/L). In comparison, the TBM model yielded an R~2 = 0.77 and 0.94 for the CIN and SA datasets, respectively; while the ANN obtained an intermediate modeling accuracy (CIN: R~2 = 0.86; SA: R~2 = 0.95). Applying the simulated OLCI and Hyperion aggregated datasets, the PLS-ANN model still achieved good performance (OLCI: R~2 = 0.84; Hyperion: R~2 = 0.90); the TBM also presented acceptable performance for PC estimations (OLCI: R~2 = 0.65, Hyperion: R~2 = 0.70). Based on the results, the PLS-ANN is an effective modeling approach for the quantification of PC in productive water supplies based on its effectiveness in solving the non-linearity of PC with other OACs. Furthermore, our investigation indicates that the ratio of inorganic suspended matter (ISM) to PC concentration has close relationship to modeling relative errors (CIN: R~2 = 0.81; SA: R~2 = 0.92), indicating that ISM concentration exert significant impact on PC estimation accuracy.