The first five years (2019-2024) of operations of The Ocean Cleanup's Automated Debris Imaging System (ADIS) has been reviewed and findings published in Environmental Research Communications . In addition to reviewing the performance of the technology, it covers the initial 14,500 km2 of global ocean surface it scanned for plastic debris, and the more than 20,000 large floating objects it has helped identify.
Why ADIS matters
ADIS is part of a larger strategy aimed at identifying plastic hotspots and tracking their movements to help The Ocean Cleanup's efforts to remove plastic from the world's ocean gyres. Satellite-based methods have proven challenging for the open ocean, where floating marine debris is too dispersed. Specifically, large floating macroplastics (>50 cm) constitute a significant part of the ocean plastic mass, but are poorly quantifiable even by classical methods, such as surface trawls and visual observations, creating a need to develop a method capable of covering large areas of ocean and consistently detecting large plastics and doing so at a low cost.
The first generation of ADIS consisted of a GoPro mounted on the sides of a vessel set to photo-timelapse mode with images backed up on hard drives daily. This data was then brought back to Rotterdam to be processed. Between 2019 and 2024, over 165TB of ocean scans worldwide were collected – 27 million photos in total, gathered from ships crossing the North and South Pacific, North and South Atlantic, and Indian Oceans. These images were fed to an AI model, which recognized and extracted images with objects from the dataset which were then validated manually. From these images, over 20,000 macroplastic items were identified.
The individual plastic detection data from all ADIS cameras is collated into a global dataset and map . This shows how much plastic is found in different areas of the oceans – measured in pieces per square kilometer. An open-access resource, it enables The Ocean Cleanup to better understand the GPGP and also allows other researchers to study the same dataset and map other garbage patches as well.
Testing and Calibrations
In 2022, a ground-truthing expedition to the Great Pacific Garbage Patch (GPGP) was carried out to put ADIS' detection rate to the test and was compared to UAV aerial imagery and physical trawl samples (manta and mega trawls). During this campaign, ADIS was found to undercount debris 5-6 times less than physical samples, due mostly to color and material bias. However, the consistent nature of the undercount meant it could be used as a correction factor, and data showed that ADIS and physical trawls agreed on where plastic was concentrated, with both methods recording the same peaks and dips in debris density as the research vessel moved through the GPGP. These findings helped guide the development of the next generation of ADIS cameras.
ADIS2.0
While the current paper publication deals with all data collected by the first generation of ADIS, the second generation of ADIS has been collecting data worldwide since 2024. ADIS2.0 autonomously recognizes floating debris and takes detailed pictures of the debris along with GPS coordinates. It automates the processing and offloading of data and is suitable for long-term deployments without relying on experts to maintain it.
As a result, ADIS2.0 has quietly been collecting even more data than ADIS1 – which can be visualized on an online data collection map . If we keep running and expanding ADIS2.0 long enough, it will allow us to create not only a static but a periodic map of plastic around the world, making it possible to compare between years and investigate trends over time. In the past two years we've already mapped an extra 39,431 km2, bringing it up to almost 54,000km2 overall.
