{"id":3871,"date":"2025-01-27T16:43:32","date_gmt":"2025-01-27T16:43:32","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2025\/01\/27\/amphitrite-rides-ai-wave-to-boost-maritime-shipping-ocean-cleanup-with-real-time-weather-prediction-and-simulation\/"},"modified":"2025-01-27T16:43:32","modified_gmt":"2025-01-27T16:43:32","slug":"amphitrite-rides-ai-wave-to-boost-maritime-shipping-ocean-cleanup-with-real-time-weather-prediction-and-simulation","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2025\/01\/27\/amphitrite-rides-ai-wave-to-boost-maritime-shipping-ocean-cleanup-with-real-time-weather-prediction-and-simulation\/","title":{"rendered":"Amphitrite Rides AI Wave to Boost Maritime Shipping, Ocean Cleanup With Real-Time Weather Prediction and Simulation"},"content":{"rendered":"
\n\t\t<\/span> <\/span> <\/span><\/span><\/p>\n

Named after Greek mythology\u2019s goddess of the sea, France-based startup Amphitrite<\/a> is fusing satellite data and AI to simulate and predict oceanic currents and weather.<\/p>\n

It\u2019s work that\u2019s making waves in maritime-shipping and oceanic litter-collection operations.<\/p>\n

Amphitrite\u2019s AI models \u2014 powered by the NVIDIA AI<\/a> and Earth-2<\/a> platforms \u2014 provide insights on positioning vessels to best harness the power of ocean currents, helping ships know when best to travel, as well as the optimal course. This helps users reduce travel times, fuel consumption and, ultimately, carbon emissions.<\/p>\n

\u201cWe\u2019re at a turning point on the modernization of oceanic atmospheric forecasting,\u201d said Alexandre Stegner, cofounder and CEO of Amphitrite. \u201cThere\u2019s a wide portfolio of applications that can use these domain-specific oceanographic AI models \u2014 first and foremost, we\u2019re using them to help foster the energy transition and alleviate environmental issues.\u201d<\/p>\n

Optimizing Routes Based on Currents and Weather<\/b><\/h2>\n

Founded by expert oceanographers, Amphitrite \u2014 a member of the NVIDIA Inception<\/a> program for cutting-edge startups \u2014 distinguishes itself from other weather modeling companies with its domain-specific expertise.<\/p>\n

Amphitrite\u2019s fine-tuned, three-kilometer-scale AI models focus on analyzing one parameter at a time, making them more accurate than global numerical modeling methods for the variable of interest. Read more in this paper<\/a> showcasing the AI method, dubbed ORCAst, trained on NVIDIA GPUs.<\/p>\n

Depending on the user\u2019s needs, such variables include the current of the ocean within the first 10 meters of the surface \u2014 critical in helping ships optimize their travel and minimize fuel consumption \u2014 as well as the impacts of extreme waves and wind.<\/p>\n

\u201cIt\u2019s only with NVIDIA accelerated computing that we can achieve optimal performance and parallelization when analyzing data on the whole ocean,\u201d said Evangelos Moschos, cofounder and chief technology officer of Amphitrite.<\/p>\n

Using the latest NVIDIA AI technologies to predict ocean currents and weather in detail, ships can ride or avoid waves, optimize routes and enhance safety while saving energy and fuel.<\/p>\n

\u201cThe amount of public satellite data that\u2019s available is still much larger than the number of ways people are using this information,\u201d Moschos said. \u201cFusing AI and satellite imagery, Amphitrite can improve the accuracy of global ocean current analyses by up to 2x compared with traditional methods.\u201d<\/p>\n

Fine-Tuned to Handle Oceans of Data<\/b><\/h2>\n

The startup\u2019s AI models, tuned to handle seas of data on the ocean, are based on public data from NASA and the European Space Agency \u2014 including its Sentinel-3 satellite.<\/p>\n

Plus, Amphitrite offers the world\u2019s first forecast model incorporating data from the Surface Water and Ocean Topography (SWOT) mission \u2014 a satellite jointly developed and operated by NASA and French space agency CNES, in collaboration with the Canadian Space Agency and UK Space Agency.<\/p>\n

\u201cSWOT provides an unprecedented resolution of the ocean surface,\u201d Moschos said.<\/p>\n

While weather forecasting technologies have traditionally relied on numerical modeling and computational fluid dynamics, these approaches are harder to apply to the ocean, Moschos explained. This is because oceanic currents often deal with nonlinear physics. There\u2019s also simply less observational data available on the ocean than on atmospheric weather.<\/p>\n

Computer vision and AI, working with real-time satellite data, offer higher reliability for oceanic current and weather modeling than traditional methods.<\/p>\n

Amphitrite trains and runs its AI models using NVIDIA H100 GPUs<\/a> on premises and in the cloud \u2014 and is building on the FourCastNet<\/a> model, part of Earth-2, to develop its computer vision models for wave prediction.<\/p>\n

According to a case study along the Mediterranean Sea, the NVIDIA-powered Amphitrite fine-scale routing solution helped reduce one shipping line\u2019s carbon emissions by 10%.<\/p>\n

Through NVIDIA Inception, Amphitrite gained technical support when building its on-premises infrastructure, free cloud credits for NVIDIA GPU instances on Amazon Web Services, as well as opportunities to collaborate with NVIDIA experts on using the latest simulation technologies, like Earth-2 and FourCastNet.<\/p>\n

Customers Set Sail With Amphitrite\u2019s Models<\/b><\/h2>\n

Enterprises and organizations across the globe are using Amphitrite\u2019s AI models to optimize their operations and make them more sustainable.<\/p>\n

CMA-CGM, Genavir, Louis Dreyfus Armateurs and Orange Marine are among the shipping and oceanographic companies analyzing currents using the startup\u2019s solutions.<\/p>\n

In addition, Amphitrite is working with a nongovernmental organization to help track and remove pollution in the Pacific Ocean. The initiative uses Amphitrite\u2019s models to analyze currents and follow plastics that drift from a garbage patch off the coast of California.<\/p>\n

\"\"<\/p>\n

Moschos noted that another way the startup sets itself apart is by having an AI team \u2014 led by computer vision scientist Hannah Bull \u2014 that comprises majority women, some of whom are featured in the image above.<\/p>\n

\u201cThis is still rare in the industry, but it\u2019s something we\u2019re really proud of on the technical front, especially since we founded the company in honor of Amphitrite, a powerful but often overlooked female figure in history,\u201d Moschos said.<\/p>\n

Learn more about <\/i>NVIDIA Earth-2<\/i><\/a>.<\/i><\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

https:\/\/blogs.nvidia.com\/blog\/amphitrite-ocean-simulation-prediction\/<\/p>\n","protected":false},"author":0,"featured_media":3872,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/3871"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=3871"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/3871\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/3872"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=3871"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=3871"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=3871"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}