Multi-task Convolution Neural Network for Season-Insensitive Chlorophyll-A Estimation in Inland Water

Abstract

Chlorophyll-a (Chl-a) concentration, a crucial indicator of phytoplankton biomass, is sensitive to seasonality. The variations in trophic states regarding seasonality and the changes of spectral properties of water bodies pose uncertainties to the accuracy of remote sensing semiempirical models. In particular, lakes in subtropical regions generally experience different trophic states in dry and wet seasons. In this study, a season-insensitive Chl-a retrieval model using multitask convolution neural network with multiple output layers (MCNN) is proposed. A layer-sharing network combined with data augmentation is adopted to alleviate the issue of insufficient quantity of <italic>in situ</italic> samples. In addition, a hyperparameter optimization is performed to automatically refine the MCNN architecture. To evaluate the accuracy of proposed method, Laguna Lake, one of the largest lakes in Southeast Asia, is selected as the validation target. The lake is characterized by oligotrophic and mesotrophic states in wet season, whereas the states change to mesotrophic and low-level eutrophic states in dry season. A collection of Sentinel-3 Ocean and Land Colour Instrument Level-2 images and 409 <italic>in situ</italic> samples with the Chl-a concentration range 1.24–22.30 mg<inline-formula><tex-math notation= LaTeX >$\\cdot$</tex-math></inline-formula>m<inline-formula><tex-math notation= LaTeX >$^{-3}$</tex-math></inline-formula> were used for model calibration and evaluation. Experimental results showed that MCNN with the performance of average <inline-formula><tex-math notation= LaTeX >$\\boldsymbol{R^{2}}$</tex-math></inline-formula> = 0.74, RMSE = 2.06 mg<inline-formula><tex-math notation= LaTeX >$\\cdot$</tex-math></inline-formula>m<inline-formula><tex-math notation= LaTeX >$^{-3}$</tex-math></inline-formula>, Pearson s <inline-formula><tex-math notation= LaTeX >$\\boldsymbol {r}$</tex-math></inline-formula> = 0.86 outperforms related semiempirical models, including normalized difference chlorophyll index, two-band and three-band models, and WaterNet. The Chl-a prediction accuracy was improved by 7.19–14.6%, in terms of RMSE, compared with WaterNet.