A New Predictive Model for Evaluating Chlorophyll-a Concentration in Tanes Reservoir by Using a Gaussian Process Regress
- PDF / 1,988,376 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 30 Downloads / 134 Views
A New Predictive Model for Evaluating Chlorophyll-a Concentration in Tanes Reservoir by Using a Gaussian Process Regression Paulino José García-Nieto 1 & Esperanza García-Gonzalo 1 & José Ramón Alonso Fernández 2 & Cristina Díaz Muñiz 2 Received: 5 June 2020 / Accepted: 22 October 2020/ # Springer Nature B.V. 2020
Abstract
Chlorophyll-a (hereafter referred to as Chl-a) is a recognized indicator for phytoplankton abundance and biomass –hence, an effective estimation of the trophic condition– of water bodies as lakes, reservoirs and oceans. Indeed, Chl-a is the primary molecule responsible for photosynthesis. A strong and robust Bayesian nonparametric technique, termed Gaussian process regression (GPR) approach, for foretelling the dependent variable Chl-a concentration in Tanes reservoir from a dataset concerning to 268 samples is shown in this paper. Ten years (2006–2015) of monitoring water quality variables (biological and physico-chemical independent variables) in the Tanes reservoir were used to build this mathematical GPR-relied model. As an optimizer, the method known as Limited-memory Broyden-Fletcher-Goldfarb-Shanno (LBFGSB) iterative algorithm was used; this allows the selection of kernel optimal parameters during the GPR training phase, which greatly determines the regression precision. The results of the current investigation can be summarized in two. Firstly, the relevance of each input variable on Chl-a concentration in Tanes reservoir is determined. Secondly, the Chl-a can be successfully predicted using this hybrid LBFGSB/GPR–relied model (R2 and r values were 0.8597 and 0.9306, respectively). The concordance between observed data and the model clearly proves the high efficiency of this innovative approach. Keywords Chlorophyll-a . Gaussian process regression (GPR) . Bayesian statistics . Regression analysis . Reservoir water quality
* Paulino José García-Nieto [email protected] * José Ramón Alonso Fernández [email protected]; [email protected]
1
Department of Mathematics, Faculty of Sciences, University of Oviedo, 33007 Oviedo, Spain
2
Cantabrian Basin Authority, Spanish Ministry for the Ecological Transition and Demographic Challenge, 33071 Oviedo, Spain
Nieto P.J.G. et al.
1 Introduction Reservoirs and lakes are large bodies of standing water and multipurpose use (drinking water storage, hydropower, irrigation or simply leisure). Chl-a is an extensively applied environmental indicator of the algae or phytoplankton biomass growth –since it is found in every single photosynthesizing organism– and of the eutrophication process in reservoirs, lakes and oceans (Latif et al. 2003). Chlorophylls are a family of green pigments (forms a, b, c, d, e and f) found in cyanobacteria and in all those organisms that contain chloroplasts or tylocoidal membranes in their cells, which includes plants and various algae (Wetzel 2001; Schinck et al. 2020). Chla is the primary molecule (found in every single photosynthesizing organism) responsible for photosynthesis, a process that enables p
Data Loading...
