Key points
- Two peer-reviewed papers drawing on Interoceanmetal data were published in 2024.
- Tomczak et al. in Science of the Total Environment propose a convolutional neural network trained on seabed photographs to estimate nodule abundance automatically.
- Dolhanczuk-Srodka et al. in the Journal of Hazardous Materials assess natural radioactivity in polymetallic nodules and the health risk around processing facilities.
- Both articles are available in the Interoceanmetal publications section.
Automated estimation of offshore polymetallic nodule abundance based on seafloor imagery using deep learning (Tomczak et al., 2024) was published in the journal Science of the Total Environment. This paper advocates for the automation of polymetallic nodules detection and abundance estimation using deep learning algorithms applied to seabed photographs. Convolutional neural network framework was proposed, specifically trained to process the unique features of seabed imagery.
Assessment of natural radioactivity levels in polymetallic nodules and potential health risks from deep-sea mining (Dołhańczuk-Śródka et al., 2024) was published in the Journal of Hazardous Materials. The study aimed to estimate the threat posed by the radioactivity of the nodules to human health and the environment surrounding processing facilities.
The articles are available in our Publications section.
