Transcriptome sequencing of seven deep marine invertebrates.

We present 4k video and whole transcriptome data for seven deep-sea invertebrate animals collected in the Eastern Pacific Ocean during a research expedition onboard the Schmidt Ocean Institute's R/V Falkor in August of 2021. The animals include one jellyfish (Atolla sp.), three siphonophores (Apolemia sp., Praya sp., and Halistemma sp.), one larvacean (Bathochordaeus mcnutti), one tunicate (Pyrosomatidae sp.), and one ctenophore (Lampocteis sp.). Four of the animals were sequenced with long-read RNA sequencing technology, such that the reads themselves define a reference assembly for those animals. The larvacean tissues were successfully preserved in situ and has paired long-read reference data and short read quantitative transcriptomic data for within-specimen analyses of gene expression. Additionally, for three animals we provide quantitative image data, and a 3D model for one siphonophore. The paired image and transcriptomic data can be used for species identification, species description, and reference genetic data for these deep-sea animals.

An in situ digital synthesis strategy for the discovery and description of ocean life.

Revolutionary advancements in underwater imaging, robotics, and genomic sequencing have reshaped marine exploration. We present and demonstrate an interdisciplinary approach that uses emerging quantitative imaging technologies, an innovative robotic encapsulation system with in situ RNA preservation and next-generation genomic sequencing to gain comprehensive biological, biophysical, and genomic data from deep-sea organisms. The synthesis of these data provides rich morphological and genetic information for species description, surpassing traditional passive observation methods and preserved specimens, particularly for gelatinous zooplankton. Our approach enhances our ability to study delicate mid-water animals, improving research in the world's oceans.

Machine learning techniques to characterize functional traits of plankton from image data.

Plankton imaging systems supported by automated classification and analysis have improved ecologists' ability to observe aquatic ecosystems. Today, we are on the cusp of reliably tracking plankton populations with a suite of lab-based and in situ tools, collecting imaging data at unprecedentedly fine spatial and temporal scales. But these data have potential well beyond examining the abundances of different taxa; the individual images themselves contain a wealth of information on functional traits. Here, we outline traits that could be measured from image data, suggest machine learning and computer vision approaches to extract functional trait information from the images, and discuss promising avenues for novel studies. The approaches we discuss are data agnostic and are broadly applicable to imagery of other aquatic or terrestrial organisms.

FathomNet: A global image database for enabling artificial intelligence in the ocean.

The ocean is experiencing unprecedented rapid change, and visually monitoring marine biota at the spatiotemporal scales needed for responsible stewardship is a formidable task. As baselines are sought by the research community, the volume and rate of this required data collection rapidly outpaces our abilities to process and analyze them. Recent advances in machine learning enables fast, sophisticated analysis of visual data, but have had limited success in the ocean due to lack of data standardization, insufficient formatting, and demand for large, labeled datasets. To address this need, we built FathomNet, an open-source image database that standardizes and aggregates expertly curated labeled data. FathomNet has been seeded with existing iconic and non-iconic imagery of marine animals, underwater equipment, debris, and other concepts, and allows for future contributions from distributed data sources. We demonstrate how FathomNet data can be used to train and deploy models on other institutional video to reduce annotation effort, and enable automated tracking of underwater concepts when integrated with robotic vehicles. As FathomNet continues to grow and incorporate more labeled data from the community, we can accelerate the processing of visual data to achieve a healthy and sustainable global ocean.

Plankton reconstruction through robust statistical optical tomography.

Plankton interact with the environment according to their size and three-dimensional (3D) structure. To study them outdoors, these translucent specimens are imaged in situ. Light projects through a specimen in each image. The specimen has a random scale, drawn from the population's size distribution and random unknown pose. The specimen appears only once before drifting away. We achieve 3D tomography using such a random ensemble to statistically estimate an average volumetric distribution of the plankton type and specimen size. To counter errors due to non-rigid deformations, we weight the data, drawing from advanced models developed for cryo-electron microscopy. The weights convey the confidence in the quality of each datum. This confidence relies on a statistical error model. We demonstrate the approach on live plankton using an underwater field microscope.