Evaluation of Machine Learning predictions of a highly resolved time series of Chlorophyll-a concentration

Abstract

Pelagic Chlorophyll-a concentrations are key for evaluation of the environmental status and productivity of marine systems. In this study, chlorophyll-a concentrations for the Helgoland Roads Time Series were modeled using a number of measured water and environmental parameters. We chose three common Machine Learning algorithms from the literature: Support Vector Machine Regressor, Neural Networks Multi-layer Perceptron Regressor and Random Forest Regressor. Results showed that Support Vector Machine Regressor slightly outperformed other models. The evaluation with a test dataset and verification with an independent validation dataset for chlorophyll-a concentrations showed a good generalization capacity, evaluated by the root mean squared errors of less than 1 µg L-1. Feature selection and engineering are important and improved the models significantly, as measured in performance, improving by a minimum of 48% the adjusted R2. We tested SARIMA in comparison and found that the univariate nature of SARIMA does not allow for better results than the Machine Learning models. Additionally, the computer processing time needed was much higher (prohibitive) for SARIMA.

Climate Change Induced Trends and Uncertainties in Phytoplankton Spring Bloom Dynamics

“…While long-term data driven chlorophyll-a concentration prediction for climate impact assessment is not widespread, there have been few studies conducted on both inland water systems (Cho et al, 2018;Keller et al, 2018;Liu et al, 2019;Luo et al, 2019) and marine systems (Irwin and Finkel, 2008;Blauw et al, 2018;Krasnopolsky et al, 2018;de Amorim et al, 2021) that performed short term predictions. Blauw et al (2018) predicted chlorophyll-a in the North Sea at different sites applying Generalized Additive Models (GAMs) with accuracies (R 2 values) ranging from 0.25 to 0.51 for hourly time scale, 0.15-0.22 for daily time scale, and 0.27-0.63 for bi-weekly time scale.…”

“…Changing climatic conditions directly affect the photosynthetic metabolism of phytoplankton, but also indirectly impact them by modifying their physical environment (D'Alelio et al, 2020). Climate change impacts on phytoplankton are manifested as shifts in seasonal dynamics, species composition, and population size structure .…”