The study was particularly beneficial for coastal protection, and it has been published in the journal Nature Scientific Reports.

Over the past few decades, every ocean basin has undergone considerable warming and sea-level rise induced by climate change. But there are significant regional variations, leading to various processes on different time scales, like those related to temperature changes as a result of natural causes.

For a better understanding of the observations of sea-level changes on coastal regions at a local level, the research team of Verónica Nieves, Distinguished Researcher of the GenT Program at the Image Processing Laboratory (IPL) of the University of Valencia, has designed a machine learning method that leverages sea temperature calculations to model coastal sea-level variability and related uncertainty throughout a variety of timescales varying from months to several years.

The study published in the Nature Scientific Reports journal also demonstrates that the physical relationships present between temperature variables in the upper layers of open sea regions and predictions of sea level anomalies on the coastal sites of such regions can be utilized together with machine learning techniques to make fairly precise, brief forecasts of the sea-level tendency (from one to many years).

The team concluded that so far, short-term regional coastal sea-level changes are still hugely impacted by natural processes in wider open ocean regions, like the open ocean temperature changes down the water column to 700 m, which are more associated with internal natural climate variability.

Such processes are superimposed on the impact of other effects, such as storms or high tides, besides others.

Climate is a highly complex and dynamical system that can change naturally in unexpected ways; and, in this sense, machine learning methods can provide useful insight to better interpret data that exhibits complex nonlinear patterns and identify near-future regional sea level changes.

Verónica Nieves, Study First Author and Head of AI4OCEANS Group, Image Processing Laboratory, University of Valencia

This line of study is being pursued at IPL.

“Our models perform particularly well in the coastal areas most influenced by internal climate variability, but they are widely applicable to evaluate the rising and falling sea level patterns across many places around the globe”, noted Cristina Radín, a member of the group to which professor Gustau Camps-Valls is associated.

This is the first ever research to make use of the Artificial Intelligence methods in the oceans to make this kind of forecasts. In the years to come, modeling and predicting sea-level variations are vital for near future decision-making and strategic planning regarding coastal protection efforts.

The researchers have developed an interactive map as a support tool that will enable the investigation of separate regions where the machine learning model forecast was performed.

Journal Reference:

Nieves, V., et al. (2021) Predicting regional coastal sea level changes with machine learning. Scientific Reports. doi.org/10.1038/s41598-021-87460-z.

This article appeared on the Azo Cleantech website at https://www.azocleantech.com/news.aspx?newsID=29207