Real-time Analytics
LoVe Ocean needed a faster way to sift through massive volumes of ocean-sensor data so researchers could better understand marine ecosystems and climate-related change.
Reported impact
The project gave LoVe Ocean a selected AI approach for faster data processing, highlighted previously overlooked marine signals, and created a practical route toward broader real-time access to ocean insights.
LoVe Ocean used Capgemini's Global Data Science Challenge to turn a decade of subsea sensor data into a concrete machine-learning workflow for marine research. The observatory streams real-time measurements from fiber-optic subsea cables and sensor nodes to the National Marine Data Center, but manual review could not keep pace with more than 100 terabytes of data. Capgemini and AWS structured the challenge so teams built and tested AI approaches with Amazon S3, Amazon SageMaker, and Amazon ECR against the observatory's time-series and acoustic data. The winning concept focused on automatically extracting indicators such as whale vocalization patterns, oceanographic and tidal features, and weather effects from raw measurements, creating a practical path from bulk sensor ingestion to model-driven analysis and future real-time researcher access.
Fiber-optic subsea cables and sensor nodes stream marine observations into the National Marine Data Center, where challenge teams organize the data in Amazon S3, build and test models in Amazon SageMaker, and package supporting workflows with Amazon ECR. The resulting AI pipeline surfaces patterns such as whale vocalizations and oceanographic changes so researchers can analyze the marine environment faster.
"For example, whale vocalization, oceanographic and tidal features we hadn't yet recognized, and the strong influence of weather on the environment."
"The winning team's proposal included a set of solutions focused on using AI and machine learning to automatically extract data pertaining to a wide variety of unique elements of the marine ecosystem."
"Throughout a ten-year period, LoVe Ocean has gathered over 100 terabytes of data"
"teams comprising nearly 1200 total participants competed to develop a concept for an AI-based solution leveraging AWS Technology such as Amazon S3, Amazon SageMaker, and Amazon ECR."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample Oct 9, 2026 California Department of Transportation (Caltrans) Caltrans needed to inspect and monitor roughly 1,200 active transportation projects more frequently and safely, but manual site visits were slow, inconsistent, and risky for staff working around traffic, bridges, and… Remote operations up to 100 miles Esri ArcGIS · NVIDIA CUDA · NVIDIA Jetson Orin 
OpenAI Sample Modified · Oct 7, 2026 SensoRy AI SensoRy AI needed to convert complex wildfire sensor readings into clear, immediate guidance for responders because detecting a fire is only useful if firefighters and officials can understand the situation quickly… answers in seconds ChatGPT · ChatGPT Voice 
Microsoft Sample Sep 28, 2026 NASA NASA had decades of scientific and operational data spread across open repositories, academic sources, engineering reviews, safety analyses, and mission systems, making it difficult for scientists, planners, and flight… More than 500 employees signed up Earth Copilot · Hydrology Copilot · Microsoft Copilot 
