Microbes as marine habitat formers and ecosystem engineers
Despite their small individual size, marine prokaryotic and eukaryotic microbes can form
large 3D structures and complex habitats. These habitats contribute to seafloor …
large 3D structures and complex habitats. These habitats contribute to seafloor …
Is one annotation enough?-a data-centric image classification benchmark for noisy and ambiguous label estimation
High-quality data is necessary for modern machine learning. However, the acquisition of
such data is difficult due to noisy and ambiguous annotations of humans. The aggregation of …
such data is difficult due to noisy and ambiguous annotations of humans. The aggregation of …
[HTML][HTML] Assessing plume impacts caused by polymetallic nodule mining vehicles
Deep-sea mining may be just a few years away and yet society is struggling to assess the
positive aspects, such as increasing the supply of metals for battery production to fuel the …
positive aspects, such as increasing the supply of metals for battery production to fuel the …
Url: A representation learning benchmark for transferable uncertainty estimates
Abstract Representation learning has significantly driven the field to develop pretrained
models that can act as a valuable starting point when transferring to new datasets. With the …
models that can act as a valuable starting point when transferring to new datasets. With the …
A review of megafauna diversity and abundance in an exploration area for polymetallic nodules in the eastern part of the Clarion Clipperton Fracture Zone (North East …
K Uhlenkott, K Meyn, A Vink, P Martínez Arbizu - Marine Biodiversity, 2023 - Springer
Abstract The Clarion Clipperton Fracture Zone (CCZ) is an abyssal region in the north-east
Pacific that is currently being explored for metal-rich polymetallic nodules, but also harbors a …
Pacific that is currently being explored for metal-rich polymetallic nodules, but also harbors a …
Making marine image data FAIR
Underwater images are used to explore and monitor ocean habitats, generating huge
datasets with unusual data characteristics that preclude traditional data management …
datasets with unusual data characteristics that preclude traditional data management …
[HTML][HTML] Improving coral monitoring by reducing variability and bias in cover estimates from seabed images
Seabed cover of organisms is an established metric for assessing the status of many
vulnerable marine ecosystems. When deriving cover estimates from seafloor imagery, a …
vulnerable marine ecosystems. When deriving cover estimates from seafloor imagery, a …
Deepdive: Leveraging Pre-trained Deep Learning for Deep-Sea ROV Biota Identification in the Great Barrier Reef
Understanding and preserving the deep sea ecosystems is paramount for marine
conservation efforts. Automated object (deep-sea biota) classification can enable the …
conservation efforts. Automated object (deep-sea biota) classification can enable the …
Deep learning based deep-sea automatic image enhancement and animal species classification
V Lopez-Vazquez, JM Lopez-Guede… - Journal of Big Data, 2023 - Springer
The automatic classification of marine species based on images is a challenging task for
which multiple solutions have been increasingly provided in the past two decades. Oceans …
which multiple solutions have been increasingly provided in the past two decades. Oceans …
Gear-induced concept drift in marine images and its effect on deep learning classification
D Langenkämper, R Van Kevelaer, A Purser… - Frontiers in Marine …, 2020 - frontiersin.org
In marine research, image data sets from the same area but collected at different times allow
seafloor fauna communities to be monitored over time. However, ongoing technological …
seafloor fauna communities to be monitored over time. However, ongoing technological …