An Artificial Neural Network Algorithm to Retrieve Chlorophyll a for Northwest European Shelf Seas from Top of Atmosphere Ocean Colour Reflectance

TL;DR

This paper presents a neural network-based method for retrieving chlorophyll-a from satellite data in turbid coastal waters, overcoming atmospheric correction challenges and providing uncertainty estimates.

Contribution

The study introduces a neural network approach operating on top-of-atmosphere reflectance data that outperforms existing algorithms and includes pixel-specific uncertainty quantification.

Findings

Neural networks improved chlorophyll retrieval accuracy in turbid coastal waters.

TOA reflectance-based neural network outperformed BOA and RC versions.

Uncertainty estimates are generated for each pixel, enhancing data reliability.

Abstract

Chlorophyll-a (Chl) retrieval from ocean colour remote sensing is problematic for relatively turbid coastal waters due to the impact of non-algal materials on atmospheric correction and standard Chl algorithm performance. Artificial neural networks (NNs) provide an alternative approach for retrieval of Chl from space and results in northwest European shelf seas over the 2002-2020 period are shown. The NNs operate on 15 MODIS-Aqua visible and infrared bands and are tested using bottom of atmosphere (BOA), top of atmosphere (TOA) and Rayleigh corrected TOA reflectances (RC). In each case, a NN architecture consisting of 3 layers of 15 neurons improved performances and data availability compared to current state-of-the-art algorithms used in the region. The NN operating on TOA reflectance outperformed BOA and RC versions. By operating on TOA reflectance data, the NN approach overcomes the common but difficult problem of atmospheric correction in coastal waters. Moreover, the NN provides data for regions which other algorithms often mask out for turbid water or low zenith angle flags. A distinguishing feature of the NN approach is generation of associated product uncertainties based on multiple resampling of the training data set to produce a distribution of values for each pixel, and an example is shown for a coastal time series in the North Sea. The final output of the NN approach consists of a best-estimate image based on medians for each pixel and a second image representing uncertainty based on standard deviation for each pixel, providing pixel-specific estimates of uncertainty in the final product.