Comments on Retrieving monthly and interannual pHT on the East China Sea shelf using an artificial neural network: ANN-pHT-v1

Abstract. While our understanding of pH dynamics has strongly progressed for open ocean regions, for marginal seas such as the East China Sea (ECS) progress has been constrained by limited observations and complex interactions between biological, physical, and chemical processes. Seawater pH is a very valuable oceanographic variable but not always measured using high quality instrumentation and according to standard practices. In order to predict water column total scale pH (pHT) and enhance our understanding of the seasonal variability of pHT on the ECS shelf, an artificial neural network (ANN) model was developed using 11 cruise datasets from 2013 to 2017 with coincident observations of pHT, temperature (T), salinity (S), dissolved oxygen (DO), nitrate (N), phosphate (P) and silicate (Si) together with sampling position and time. The reliability of the ANN model was evaluated using independent observations from 3 cruises in 2018, and showed a root mean square error accuracy of 0.04. A weight analysis of the ANN model variables suggested that DO, S, T were the most important predictor variables. Monthly water column pHT for the period 2000-2016 was retrieved using T, S, DO, N, P, and Si from the Changjiang Biology Finite-Volume Coastal Ocean Model (FVCOM).

Download Full-text

Retrieving monthly and interannual total-scale pH (pHT) on the East China Sea shelf using an artificial neural network: ANN-pHT-v1

Geoscientific Model Development ◽

10.5194/gmd-13-5103-2020 ◽

2020 ◽

Vol 13 (10) ◽

pp. 5103-5117

Author(s):

Xiaoshuang Li ◽

Richard Garth James Bellerby ◽

Jianzhong Ge ◽

Philip Wallhead ◽

Jing Liu ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

East China Sea ◽

Ocean Model ◽

East China ◽

Ann Model ◽

The East China Sea ◽

China Sea ◽

Artificial Neural ◽

Artificial Neural Network Ann

Abstract. While our understanding of pH dynamics has strongly progressed for open-ocean regions, for marginal seas such as the East China Sea (ECS) shelf progress has been constrained by limited observations and complex interactions between biological, physical and chemical processes. Seawater pH is a very valuable oceanographic variable but not always measured using high-quality instrumentation and according to standard practices. In order to predict total-scale pH (pHT) and enhance our understanding of the seasonal variability of pHT on the ECS shelf, an artificial neural network (ANN) model was developed using 11 cruise datasets from 2013 to 2017 with coincident observations of pHT, temperature (T), salinity (S), dissolved oxygen (DO), nitrate (N), phosphate (P) and silicate (Si) together with sampling position and time. The reliability of the ANN model was evaluated using independent observations from three cruises in 2018, and it showed a root mean square error accuracy of 0.04. The ANN model responded to T and DO errors in a positive way and S errors in a negative way, and the ANN model was most sensitive to S errors, followed by DO and T errors. Monthly water column pHT for the period 2000–2016 was retrieved using T, S, DO, N, P and Si from the Changjiang biology Finite-Volume Coastal Ocean Model (FVCOM). The agreement is good here in winter, while the reduced performance in summer can be attributed in large part to limitations of the Changjiang biology FVCOM in simulating summertime input variables.

Download Full-text