A Deep Learning-Assisted Algorithm to Improve Inherent Optical Properties Estimations Over Inland and Nearshore Coastal Waters

Abstract

Inherent optical properties (IOPs) are crucial parameters for assessing water quality, with widely applied estimation methods established for open oceans. The estimation of IOPs for inland and coastal waters, however, remains a longstanding challenge due to their complex optical properties. In order to address this, we developed a deep learning-assisted quasi-analytical algorithm (QAA-DL) for estimating IOPs in inland and coastal waters. This method enhances traditional QAA procedures by using a neural network to reparameterize the algorithm for extremely turbid waters. Additionally, we introduced a soft-wired classification scheme to ensure smooth retrieval of IOPs in slightly turbid waters. Validation analyses showed that the IOPs retrievals using QAA-DL agreed well with the worldwide in situ measurements. Compared to other standard IOPs algorithms, QAA-DL provided more than double the valid data coverage in turbid waters. Additionally, when applied to moderate resolution imaging spectroradiometer (MODIS) imagery, the QAA-DL algorithm demonstrates consistent spatial patterns in IOPs retrievals. The QAA-DL algorithm can be adopted in different ocean color missions to produce high-quality IOPs retrievals for global inland and coastal waters.