Research Article: Predictive performance of regression models to estimate Chlorophyll-a concentration based on Landsat imagery

Date Published: October 12, 2018

Publisher: Public Library of Science

Author(s): Miguel Ángel Matus-Hernández, Norma Yolanda Hernández-Saavedra, Raúl Octavio Martínez-Rincón, Zhihua Zhang.


Chlorophyll-a (Chl-a) concentration is a key parameter to describe water quality in marine and freshwater environments. Nowadays, several products with Chl-a have derived from satellite imagery, but they are not available or reliable sometimes for coastal and/or small water bodies. Thus, in the last decade several methods have been described to estimate Chl-a with high-resolution (30 m) satellite imagery, such as Landsat, but a standardized method to estimate Chl-a from Landsat imagery has not been accepted yet. Therefore, this study evaluated the predictive performance of regression models (Simple Linear Regression [SLR], Multiple Linear Regression [MLR] and Generalized Additive Models [GAMs]) to estimate Chl-a based on Landsat imagery, using in situ Chl-a data collected (synchronized with the overpass of Landsat 8 satellite) and spectral reflectance in the visible light portion (bands 1–4) and near infrared (band 5). These bands were selected because of Chl-a absorbance/reflectance properties in these wavelengths. According to goodness of fit, GAM outperformed SLR and MLR. However, the model validation showed that MLR performed better in predicting log-transformed Chl-a. Thus, MLR, constructed by using four spectral bands (1, 2, 3, and 5), was considered the best method to predict Chl-a. The coefficients of this model suggested that log-transformed Chl-a concentration had a positive linear relationship with bands 1 (coastal/aerosol), 3 (green), and 5 (NIR). On the other hand, band 2 (blue) suggested a negative relationship, which implied high coherence with Chl-a absorbance/reflectance properties measured in the laboratory, indicating that Landsat 8 images could be applied effectively to estimate Chl-a concentrations in coastal environments.

Partial Text

Coastal environments are highly productive and complex marine ecosystems because they show the interaction of various natural and anthropogenic phenomena that provide an important source of nutrients for phytoplankton and aquatic organisms, as well as for various human activities. Nevertheless, during the last decades, studies have demonstrated that these water bodies have been under significant stress due to anthropogenic alterations and climate variations that are increasingly frequent events, such as algal blooms [1,2]. In these environments, Chl-a has been considered as one of the most important parameters for measuring water quality, so it can be used as an indicator of ecosystem health [3,4].

This study evaluated the use of Landsat 8 for estimating Chl-a concentration in the coastal water body located in northwestern Mexico by field data collection, simple linear regression, multiple linear regression and generalized additive models, using as response variable log-transformed Chl-a and reflectance values as spectral predictive variables of the visible part of light and NIR. The results obtained suggested that the use of spectral bands 1 (coastal/aerosol), 2 (blue), 3 (green), and 5 (NIR), from the MLR model, allowed us to reliably estimate the concentrations of Chl-a in a coastal environment.

This study has evaluated the performance of simple and multiple linear regression and generalized additive models to estimate Chl-a concentration, using the first five bands of Landsat 8 images in the Bahía de La Paz, Baja California Sur, Mexico. The obtained results indicated that this method provided a reliable estimation of Chl-a in small coastal water bodies because of the high coherence found in model coefficients with the absorption/reflection properties of Chl-a evaluated in the laboratory under controlled conditions. Therefore, remote sensing has shown to represent an ideal opportunity to develop regional scale research on various parameters in environments estimated in small coastal water bodies to allow a constant monitoring at low cost and high-quality spatial scale.




0 0 vote
Article Rating
Notify of
Inline Feedbacks
View all comments