top of page




ATMOSMARINE has great expertise in the calibration of atmospheric and ocean dynamic models and developed a new approach for the forecasting of environmental parameters through the combination of dynamic models calibrated in with statistical models. This hybrid approach (numerical-statistical) manages to use the knowledge of present-time physics, through the source terms of the models, to isolate the error of the numerical model (residue) and characterize these residues on simulations using Neural Networks (RNs).


This system was named SOPHIA (Hybrid Forecasting Operational System with Artificial Intelligence) and the results obtained can be applied in the prediction of extreme events or specialty products. This methodology has been proved and published in a few international scientific journals.

Wave Buoy Data Process

ATMOSMARINE has the most knowledgeable wave experts in the world. We offer detailed observed wave data analysis from buoys and satellite data. Our real-time online wave data processing software can be integrated with any wave buoy and it contains comprehensive statistical analysis, time-series analysis and different types of graphs.


ATMOSMARINE also developed its own mini wave buoy called PinkDot®, which allows the monitoring of waves and sea temperature in real time. It is a small and practical buoy with low cost sensors and plates perfect for certain applications where centimeter accuracy is enough. This buoy connects with our online software to provide very detailed wave information.


Proprietary forecasting models

ATMOSMARINE applies the latest regional and global numerical models available to our proprietary implementations and improvements to provide better calibrations with observed data from several sources and deliver more accurate forecast and hindcast results.

  • Base atmospheric models used: WRF and BRAMS

  • Base wave Models used: WWIII and SWAN

  • Base ocean circulation models used: ROMS and DELFT 3D

bottom of page