Optimizing Chlorophyll-a Concentration Inversion in Coastal Waters Using SVD and Deep Learning Approach

Remote sensing of chlorophyll-a (Chl-a) concentrations in coastal waters is of great importance for the assessment of the marine ecological conditions. However, due to the complex water body optical properties, accurate selection of optimal feature bands is limited, which poses a great challenge for high-precision retrieval. The purpose of this research is to address the problem of high-precision retrieval of the Chl-a concentration in small coastal waters. In this article, a singular value decomposition and deep neural network (SVD-DNN) Chl-a inversion model for Hong Kong coastal waters were constructed. Other machine learning methods, such as random forest (RF) and the support vector machine (SVM) are also used to establish the inversion models for the comparison. At the same time, a comparative analysis was performed with Chl-a retrieval models created using a feature selection method based on the correlation of band combinations. These models are validated using the Landsat 8 OLI and synchronously measured Chl-a dataset (N = 149 samples). Results show that the developed SVD-DNN model has the best retrieval accuracy [mean R = 0.90, root mean square error (RMSE) = 1.21, mean absolute error (MAE) = 1.05], outperforming the SVD-RF and SVD-SVM models. The SVD-DNN model shows superior retrieval performance when the Chl-a concentration is below 6 micrograms per liter (RMSE = 0.66, MAE = 0.67). The proposed model also shows better temporal generalization ability in 2013, 2014, and 2016 compared to the other models. This study demonstrates that the developed and validated SVD-DNN model has excellent robustness and generalization ability and can be used in combination with Landsat data for long-term retrieval of Chl-a across different time series.