A CSIC team determines the acidification trend of the Balearic Sea through artificial intelligence

  • The study uses machine learning to describe the decrease in pH, a key factor in assessing the impact of climate change on marine biodiversity
  • The results reveal a pH decrease trend similar to the decrease rates observed in other basins of the global ocean



Field work for the retrieval of data collected at the Water:iOS monitoring station



Esporles, 9th september 2022. An interdisciplinary team from the Spanish National Research Council (CSIC) operating in the Balearic Islands has presented the first acidification rate of the coastal area of the Balearic Sea to shed light on the consequences of climate change in coastal areas of the archipelago. The study was aimed at reconstructing incomplete pH time series of relevance by means of artificial intelligence techniques



The results, which have been published in the journal Scientific Reports, indicate that these coastal areas exhibit a pH decrease trend (acidification) of 0.0020±0.00054 pH units per year. This trend is similar to those observed in other basins of the global ocean, and it is largely due to the incorporation of atmospheric carbon dioxide into seawater and the effect of rising temperatures.



‘The decrease in seawater pH is due to the increase of carbon dioxide present in the atmosphere, which ensues major alterations impacting marine ecosystems extensively. For example, ocean acidification leads to reduced carbonate mineral saturation levels, which in turn hinders shell formation in calcifying marine organisms such as plankton, molluscs, echinoderms and corals. Measuring how pH levels are shifting in these areas is therefore key in order to pinpoint this problem,’ says Iris E. Hendriks, principal investigator for the project and IMEDEA (CSIC-UIB) researcher.



‘Our work is a valuable contribution to understanding the role of coastal areas and the effects of climate change on the ecosystems present there,’ she says.



Artificial intelligence for data reconstruction


The study has entailed a major operational effort which first started in 2018 with the collection of pH data, alongside other variables (water temperature, salinity and dissolved oxygen levels) at the monitoring stations of the Balearic Ocean Acidification Time Series (BOATS) network in Palma Bay and the Cabrera Archipelago Maritime-Terrestrial National Park, within the framework of the Water:iOS Interdisciplinary Thematic Platform.



‘Maintaining this type of station is not without its difficulties - financial costs, meteorological hazards, deployment in areas of high shipping traffic, equipment malfunctions, and so on - which cause ‘gaps’ in the data, and the subsequent loss of quality when it comes to producing global studies,’ Hendriks points out.



In order to complete the data and estimate the pH series over a broad time interval prior to monitoring, the team applied deep learning techniques - an emerging area of machine learning that has recently produced significant advances in the field of Artificial Intelligence. More specifically, several recurrent neural network models were developed which, when trained, enabled researchers to link the pH series to the set of environmental variables obtained, thus predicting the pH value when it is not available.



The efforts to gather large amounts of data and the subsequent application of these techniques have made it possible to reconstruct the decadal acidification trend of the Balearic Sea, this being the most remarkable result of the work undertaken.



The IMEDEA-CSIC-UIB, the Institute of Marine Science of Andalusin (ICMAN-CSIC), the Institute of Marine Research (IIM-CSIC), the Institute for Cross-Disciplinary Physics and Complex Systems (IFISC-CSIC-UIB) and the Balearic Islands Coastal Observing and Forecasting System (ICTS SOCIB)  have taken part in the study. The management team of the Cabrera Archipelago Maritime-Terrestrial National Park and the Regional Department for Environment and Territory have collaborated in the project. It has been funded by the Ministry of Science and Innovation, the Government of the Balearic Islands and the BBVA Foundation.





More information: