Search

Machine learning covers a large set of algorithms that can be trained to identify patterns in data. Thanks to the increase in the amount of data and computing power available, it has become pervasive across scientific disciplines. We first highlight why machine learning is needed in marine ecology. Then we provide a quick primer on machine learning techniques and vocabulary. We built a database of & SIM;1000 publications that implement such techniques to analyse marine ecology data. For various data types (images, optical spectra, acoustics, omics, geolocations, biogeochemical profiles, and satellite imagery), we present a historical perspective on applications that proved influential, can serve as templates for new work, or represent the diversity of approaches. Then, we illustrate how machine learning can be used to better understand ecological systems, by combining various sources of marine data. Through this coverage of the literature, we demonstrate an increase in the proportion of marine ecology studies that use machine learning, the pervasiveness of images as a data source, the dominance of machine learning for classification-type problems, and a shift towards deep learning for all data types. This overview is meant to guide researchers who wish to apply machine learning methods to their marine datasets.

Fuller’s earth is an adsorbent material used in the electric industry for dielectric oil regeneration. The high amount of polyaromatic hydrocarbons removed from oil and adsorbed in the Fuller’s earth makes this material a hazardous waste. It is necessary to implement a toxicity test and apply a suitable treatment to safely dispose of this waste in a landfill or repurpose it for reuse. In this paper, the toxicity of Fuller’s earth contaminated with dielectric oil is assessed before and after treatment. The toxic potential of the Fuller’s earth and the dielectric oil extracted through decontamination processes was evaluated in two types of soil with different carbon contents, analyzing the effects on the test organisms, Eisenia Foetida earthworms. These tests showed that decontaminated Fuller’s earth is non-toxic, and that the toxicity of the contaminated Fuller’s earth, or its extracts after treatment, represented by the median lethal concentration (LC50) depends significantly on the type of soil used., La tierra de Fuller es un material adsorbente utilizado en la industria eléctrica para la regeneración de aceite dieléctrico. La gran cantidad de hidrocarburos poliaromáticos eliminados del petróleo y adsorbidos en la tierra de Fuller hace que este material sea un desecho peligroso. Es necesario implementar una prueba de toxicidad y aplicar un tratamiento adecuado para desechar de manera segura estos desechos en un vertedero o reciclar para su reutilización. En este documento, la toxicidad de la tierra de Fuller contaminada con aceite dieléctrico se evalúa antes y después del tratamiento. El potencial tóxico de la tierra de Fuller y el aceite dieléctrico extraído mediante procesos de descontaminación se evaluó en dos tipos de suelo con diferentes contenidos de carbono, analizando los efectos en los organismos de prueba, las lombrices de tierra Eisenia Foetida. Estas pruebas mostraron que la tierra de Fuller descontaminada no es tóxica, y que la toxicidad de la tierra de Fuller contaminada, o sus extractos después del tratamiento, representada por la concentración letal media (CL50) depende significativamente del tipo de suelo utilizado.