Modeling the sea-surface pCO2 of the central Bay of Bengal region using machine learning algorithms

Abstract

The present study explores the capabilities of advanced machine learning algorithms in predicting the sea-surface pCO2 (partial pressure of carbon dioxide) in the open oceans of the Bay of Bengal (BoB). We collect the available observations (outside EEZ (Exclusive Economic Zone)) from the cruise tracks and the mooring stations. Due to the paucity of data in the BoB, we attempt to predict pCO2 based on the Sea Surface Temperature (SST) and the Sea Surface Salinity (SSS). Comparing the MLR, the ANN, and the XGBoost algorithm against a common dataset reveals that the XGBoost performs the best for predicting the sea-surface pCO2 in the BoB. Using the satellite-derived SST and SSS, we predict the sea-surface pCO2 using the XGBoost model and compare the same with the in-situ observations. The model performs satisfactorily, having a correlation of 0.75 and the RMSE of ±12.23μatm. Further using this model, we emulate the monthly variations in the sea-surface pCO2 for the central BoB between 2010–2019. Using the satellite data, we show that the central BoB is warming at a rate of 0.0175 °C per year, whereas the SSS decreases at a rate of -0.0088 PSU per year. The modeled pCO2 shows a declination at a rate of −0.4852 μatm per year. We perform sensitivity experiments to find that the variations in SST and SSS contribute ≈ 41% and ≈ 37% to the declining trends of the pCO2 for the last decade. Seasonal analysis shows that the pre-monsoon season has the highest rate of decrease of the sea-surface pCO2.