Inverting the Concentrations of Chlorophyll-a and Chemical Oxygen Demand in Urban River Networks Using Normalized Hyperspectral Data

Chlorophyll-a (Chl-a) and chemical oxygen demand (COD) are key indicators for water quality evaluation. In previous research on the inversion of Chl-a and COD concentrations using hyperspectral data, disparities in hyperspectral data types have constrained the universality of the inversion models. To solve this problem, in this study, synchronous in situ hyperspectral data and water samples were collected from 308 stations within the river networks of Zhongshan City. Four inversion models, support vector regression (SVR), random forest (RF), backpropagation neural network (BPNN), and one-dimensional convolutional neural network (1D-CNN), were established using the original reflectance (R), remote sensing reflectance (Rrs), and their normalized forms as inputs. To evaluate the robustness of the models, their performance was assessed via cross-reflectance type validation. For example, a model was trained using R data and then tested with Rrs data. The results show that using the normalized hyperspectral data for modeling not only improves the accuracy of the inversion results of Chl-a and COD concentrations, but also effectively unifies different types of hyperspectral data, thereby improving the versatility of the inversion model. This study provides a reference for constructing a general water quality inversion model based on hyperspectral data.