Spectral Feature Selection Optimization for Water Quality Estimation

Abstract

The spatial heterogeneity and nonlinearity exhibited by bio-optical relationships in turbid inland waters complicate the retrieval of chlorophyll-a (Chl-a) concentration from multispectral satellite images. Most studies achieved satisfactory Chl-a estimation and focused solely on the spectral regions from near-infrared (NIR) to red spectral bands. However, the optical complexity of turbid waters may vary with locations and seasons, which renders the selection of spectral bands challenging. Accordingly, this study proposes an optimization process utilizing available spectral models to achieve optimal Chl-a retrieval. The method begins with the generation of a set of feature candidates, followed by candidate selection and optimization. Each candidate links to a Chl-a estimation model, including two-band, three-band, and normalized different chlorophyll index models. Moreover, a set of selected candidates using available spectral bands implies an optimal composition of estimation models, which results in an optimal Chl-a estimation. Remote sensing images and in situ Chl-a measurements in Lake Kasumigaura, Japan, are analyzed quantitatively and qualitatively to evaluate the proposed method. Results indicate that the model outperforms related Chl-a estimation models. The root-mean-squared errors of the Chl-a concentration obtained by the resulting model (OptiM-3) improve from 11.95 mg · m − 3 to 6.37 mg · m − 3 , and the Pearson’s correlation coefficients between the predicted and in situ Chl- a improve from 0.56 to 0.89.

Multi-Reservoir Water Quality Mapping from Remote Sensing Using Spatial Regression

“…In addition, the best global model is the green-red band in a high Chla concentration of water. The result matches the previous studies [5,28,29]. Most algorithms for Chla estimation in waters have been based on the principles of water absorption that a high content of Chla leads to an increase in water absorption of 443 nm and near 675 nm [5,30].…”

“…Most algorithms for Chla estimation in waters have been based on the principles of water absorption that a high content of Chla leads to an increase in water absorption of 443 nm and near 675 nm [5,30]. Chla mapping in clear waters is commonly used at the blue and green spectral bands because the optical properties in clear waters are controlled by phytoplankton, whereas Chla mapping in turbid waters shifts from the blue and green to the red and NIR spectral bands or the green-to-red band to avoid high absorption of non-algal particles [5,29,31]. With the low Chla and turbid concentration water environment (area 1), the turbid becomes relatively high impacts in the study area.…”

UAV-Borne Hyperspectral Imaging Remote Sensing System Based on Acousto-Optic Tunable Filter for Water Quality Monitoring

“…Water quality parameter band selection finds the most relevant band by analyzing the correlation between the in situ measurement results of the water quality parameters of the sampling points and the spectral reflectance of the sampling points to obtain the sensitive band selection of a certain water quality parameter. The sensitive band can be a single band, double band, or multi-band [72][73][74]. Due to the small number of samples collected from the ground in this study, the water quality parameter bands of the traditional algorithm were selected to find the best band combination.…”

WaterNet: A Convolutional Neural Network for Chlorophyll-a Concentration Retrieval

“…Since then, numerous satellite images and methods have been proposed to link the spectral information of remote sensing images and the water quality parameters, especially Chl-a concentrations which is a measure of phytoplankton biomass and frequently used to indicate algal blooms [4]. For example, Ha et al [5], Kown et al [6], and Van Nguyen et al [7] used Landsat-8 OLI sensor which provides a moderate spatial resolution, which is 30 m × 30 m for a pixel. However, in addition to that designed for land, the Landsat-8 image has only five spectral bands available for the purpose of water bodies.…”

“…Researchers converted and simplified a three-band model into a two-band model, in which the blue spectral band at 443 nm was removed [29,30]. With respect to the appreciable information in the spectral domain, Barnes et al [31] utilized all available bands of the MERIS sensor in band combinations to develop a Chl-a retrieval model, and several methods [7,10,[32][33][34] determine important features which are sensitive to Chl-a concentration from a pool of band combination. Take Sentinel-3 satellite images and a two-band combination as an example.…”