Journal of Ocean Technology - 2021 Machine Learning-Computer Coding Challenge

Your mission: Harness the power of cloud computing to identify and quantify organisms in benthic video transects. Start with pre-built artificial intelligence (AI) models or take it to the next level by building your own machine learning (aka coding) models.

With those words, the MATE ROV Competition challenged students around the globe to use the Microsoft Azure AI Platform to create computer programs capable of evaluating marine organisms in benthic video transects. This was the second time the MATE ROV Competition and Microsoft partnered on a project designed to expose students to machine learning and encourage them to understand and apply AI to solving real-world, ocean-related problems.

In 2019, the challenge was more free-form, tasking students to innovate on decisions that might be made from remotely operated vehicle (ROV) information and the machine learning process (data acquisition, transformation, classification, visualization, etc.). Students could use data acquired from their ROV, simulated data for a scenario, or public datasets to, for example, classify aquatic species or analyze fault lines to predict natural disasters.

The 2021 challenge was more specific and involved in-depth learning and applications...

Finish reading the TRADE WINDS column here.

You can also download or read the article as a .pdf here

Attachments: 

V16N3_Spindrift_Trade_Winds_MATE_ROV_HR.pdf