On an Artificial Neural Network Approach for Predicting Photosynthetically Active Radiation in the Water Column

Kumm, Martin; Nolle, Lars; Stahl, Frederic; Jemai, Ahlem

doi:10.1007/978-3-031-21441-7_8

Cited by 1 publication

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pioneering work by [26] showed that global 3D reconstruction of the b bp could be performed thanks to the development of the first SOCA model. More recently, subsets of irradiance data (ED380, ED412, and ED490) acquired by BGC-Argo floats have been used to predict PAR either through statistical approaches [59] or the use of neural networks [60].…”

Section: Discussionmentioning

confidence: 99%

Vertically Resolved Global Ocean Light Models Using Machine Learning

Renosh,

Zhang,

Sauzède

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The vertical distribution of light and its spectral composition are critical factors influencing numerous physical, chemical, and biological processes within the oceanic water column. In this study, we present vertically resolved models of downwelling irradiance (ED) at three different wavelengths and photosynthetically available radiation (PAR) on a global scale. These models rely on the SOCA (Satellite Ocean Color merged with Argo data to infer bio-optical properties to depth) methodology, which is based on an artificial neural network (ANN). The new light models are trained with light profiles (ED/PAR) acquired from BioGeoChemical-Argo (BGC-Argo) floats. The model inputs consist of surface ocean color radiometry data (i.e., Rrs, PAR, and kd(490)) derived by satellite and extracted from the GlobColour database, temperature and salinity profiles originating from BGC-Argo, as well as temporal components (day of the year and local time in cyclic transformation). The model outputs correspond to ED profiles at the three wavelengths of the BGC-Argo measurements (i.e., 380, 412, and 490 nm) and PAR profiles. We assessed the retrieval of light profiles by these light models using three different datasets: BGC-Argo profiles that were not used for the training (i.e., 20% of the initial database); data from four independent BGC-Argo floats that were used neither for the training nor for the 20% validation dataset; and the SeaBASS database (in situ data collected from various oceanic cruises). The light models show satisfactory predictions when thus compared with real measurements. From the 20% validation database, the light models retrieve light variables with high accuracies (root mean squared error (RMSE)) of 76.42 μmol quanta m−2 s−1 for PAR and 0.04, 0.08, and 0.09 W m−2 nm−1 for ED380, ED412, and ED490, respectively. This corresponds to a median absolute percent error (MAPE) that ranges from 37% for ED490 and PAR to 39% for ED380 and ED412. The estimated accuracy metrics across these three validation datasets are consistent and demonstrate the robustness and suitability of these light models for diverse global ocean applications.

show abstract

Section: Discussionmentioning

confidence: 99%