Using Artificial Intelligence and Autonomous Robotics for Rapid Exploration of Deep-Sea Ecosystems

Latest expedition headed by Dr Blair Thornton, holding Associate Professorships at both the University of Southampton and the Institute of Industrial Science, the University of Tokyo, showed the way the application of artificial intelligence and autonomous robotics at sea can drastically speed up the exploration and study of hard-to-reach deep-sea ecosystems, such as intermittently active methane seeps.

The quick, high-throughput data analysis at sea enabled the identification of biological hotspots at the Hydrate Ridge Region off the coast of Oregon, at an adequately rapid pace to survey and sample them within days after the Autonomous Underwater Vehicles (AUV) imaging survey. The team on-board the Falkor research vessel used a type of artificial intelligence known as unsupervised clustering for the analysis of AUV-obtained seafloor images and for identifying target areas for more detailed photogrammetric AUV surveys and focused interactive hotspot sampling with ROV SuBastian.

This study showed the way modern data science can considerably increase the efficiency of traditional research at sea, and enhance the productivity of interactive seafloor exploration with the very well-known “stumbling in the dark” mode. “Developing totally new operational workflows is risky, however, it is very relevant for applications such as seafloor monitoring, ecosystem survey and planning the installation and decommissioning of seafloor infrastructure,” stated Thornton.

The concept behind this Adaptive Robotics mission was not to transform the structure of the way things are performed at sea, but simply to eliminate bottlenecks in the flow of information and data-processing with the help of computational techniques and artificial intelligence. The applied algorithms have the ability to quickly produce straightforward summaries of observations, and create subsequent deployment plans. Thus, researchers can respond to dynamic variations in the environment and target areas that will result in the biggest scientific, operational, or environmental management gains.

Over 1.3 million seafloor images were gathered and algorithmically investigated to discover biological hotspots and exactly target them for interactive sampling and observations. The initial broad-area seafloor imagery was obtained using an underwater vehicle “Ae2000f” with the help of high-altitude 3D visual mapping cameras at underwater sites between 680 and 780 m depth. The international team of researchers deployed a number of AUVs, built by the University of Tokyo, which were provided with 3D visual mapping technology collaboratively developed by the University of Sydney, University of Southampton, and the University of Tokyo and the Kyushu Institute of Technology as part of an international collaboration.

The transformation of the initial broad-area survey imagery into 3D seafloor maps and habitat-type summaries aboard Falkor enabled the scientists to plan the subsequent robotic deployments to carry out higher resolution visual imaging, chemical and environmental surveying, as well as physical sampling in areas of higher interest, specifically at the ephemeral hotspots of biological activity that are intermittently formed around transitory methane seeps. In total, 15 ROV dives and 19 AUV deployments were performed at the time of the expedition, which included a number of multi-vehicle operations.

The rapid data processing enabled completion of a photogrammetric map of one of the best-investigated gas hydrate deposits. This is considered to be the largest 3D color reconstruction of the seafloor (by area) across the globe, measuring over 118,000 m2 or 11.8 hectares, and covering a region of roughly 500 x 350 m. Although the average resolution of the maps acquired is 6 mm, the areas of the highest interest were mapped with a resolution an order of magnitude higher, which would have been impossible without the potential to intelligently target the intended sites with high-resolution imaging surveys and process the large volumes of acquired data within hours of their acquisition at sea.

Usually, maps such as this would need several months of time to process and only following the completion of an expedition, at which point the research team will no longer be at the site, and the habitats may have already expired or evolved. Rather, the research team was in a position to compose the 3D maps aboard Falkor within a few days of obtaining the images. The composite map was used to plan operations at the time of the expedition, including the recovery of seafloor instruments, and was highly vital for revisiting particular sites, such as active bubble plumes, rendering the whole operation highly efficient.

It is quite amazing to see such large areas of the seafloor mapped visually, especially only days after the raw data was collected. It is not just the size of the map, but also the way we were able to use it to inform our decisions while still on site. This makes a real difference as the technology makes it possible to visualize wide areas at very high resolution, and also easily identify and target areas where we should collect data. This has not previously been possible.

Dr Blair Thornton

Source: https://schmidtocean.org/

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit
Azthena logo

AZoM.com powered by Azthena AI

Your AI Assistant finding answers from trusted AZoM content

Your AI Powered Scientific Assistant

Hi, I'm Azthena, you can trust me to find commercial scientific answers from AZoNetwork.com.

A few things you need to know before we start. Please read and accept to continue.

  • Use of “Azthena” is subject to the terms and conditions of use as set out by OpenAI.
  • Content provided on any AZoNetwork sites are subject to the site Terms & Conditions and Privacy Policy.
  • Large Language Models can make mistakes. Consider checking important information.

Great. Ask your question.

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.