Artificial Intelligence Meets Marine Ecotoxicology: Applying Deep Learning to Bio-Optical Data from Marine Diatoms Exposed to Legacy and Emerging Contaminants

Abstract

Over recent decades, the world has experienced the adverse consequences of uncontrolled development of multiple human activities. In recent years, the total production of chemicals has been composed of environmentally harmful compounds, the majority of which have significant environmental impacts. These emerging contaminants (ECs) include a wide range of man-made chemicals (such as pesticides, cosmetics, personal and household care products, pharmaceuticals), which are of worldwide use. Among these, several ECs raised concerns regarding their ecotoxicological effects and how to assess them efficiently. This is of particular interest if marine diatoms are considered as potential target species, due to their widespread distribution, being the most abundant phytoplankton group in the oceans, and also being responsible for key ecological roles. Bio-optical ecotoxicity methods appear as reliable, fast, and high-throughput screening (HTS) techniques, providing large datasets with biological relevance on the mode of action of these ECs in phototrophic organisms, such as diatoms. However, from the large datasets produced, only a small amount of data are normally extracted for physiological evaluation, leaving out a large amount of information on the ECs exposure. In the present paper, we use all the available information and evaluate the application of several machine learning and deep learning algorithms to predict the exposure of model organisms to different ECs under different doses, using a model marine diatom (Phaeodactylum tricornutum) as a test organism. The results show that 2D convolutional neural networks are the best method to predict the type of EC to which the cultures were exposed, achieving a median accuracy of 97.65%, while Rocket is the best at predicting which concentration the cultures were subjected to, achieving a median accuracy of 100%.

Potential of Asparagopsis armata as a Biopesticide for Weed Control under an Invasive Seaweed Circular-Economy Framework

“…These multivariate profile effects are more perceivable and also produce more reliable and efficient biomarkers. Non-invasive bio-optical tools that evaluate plant photochemistry preciously have been highlighted as among the most efficient tools to address plant stress [ 37 , 62 , 63 ]. In the present study, regardless of the high discrimination accuracy of the chlorophyll a fluorescence-derived biomarkers (78.9% correct classification accuracy), these were not the most efficient in depicting the A. armata exposure in the test plants.…”

A UAS and Machine Learning Classification Approach to Suitability Prediction of Expanding Natural Habitats for Endangered Flora Species

“…Remote Sens. 2022, 14, x FOR PEER REVIEW 3 of 20 machine learning classification algorithms have recently been established as state-of-theart methods for suitability prediction in various disciplines, such as agriculture [9], forestry [23], nature and environment conservation [24], including land and marine contamination studies [25,26]. While these methods have been successfully utilized in previous studies [27,28], habitat suitability prediction methods according to environmental criteria have been relatively unexplored, especially for the purpose of extending the habitat of endangered flora species [29].…”

“…To provide an efficient multispectral imaging solution with high spatial resolution in restricted locations, unmanned aerial systems (UASs) have been successfully implemented in various nature conservation studies, specifically ensuring non-invasive data collection in sensitive study areas [22]. Various machine learning classification algorithms have recently been established as state-of-the-art methods for suitability prediction in various disciplines, such as agriculture [9], forestry [23], nature and environment conservation [24], including land and marine contamination studies [25,26]. While these methods have been success-fully utilized in previous studies [27,28], habitat suitability prediction methods according to environmental criteria have been relatively unexplored, especially for the purpose of extending the habitat of endangered flora species [29].…”

Effects on Biomarkers in Stress Ecology Studies. Well, So What? What Now?

“…Additionally, in microalgae (marine diatom Phaeodactylum tricornutum ), Nuno Rodrigues et al [ 6 ] used a deep learning artificial intelligence approach to tackle bio-optical data in diatoms exposed to legacy and emerging contaminants, including pesticides, cosmetics, personal and household care products, and pharmaceuticals. By merging an ecotoxicological approach with the most advanced optical high-throughput phenotyping grounded in deep learning artificial intelligence methods, it was possible to assess not only the type of contaminant to which the diatoms were exposed, but also the dose that was applied in each experimental unit.…”

“…This decision task often requires one to opt for either a few options that may provide an incomplete overview of effects, or a more complete set that will often send the researcher into a myriad of misleading interpretations or dead ends, which today are less of a burden due to bioinformatic tools and artificial intelligence, helping to simplify and interconnect the data. Moreover, every day, more complete and comprehensive statistical tools allow for the simplification and communication of these data in multifactorial analyses, enabling a practical visualization of the results of integrating effects: Crespo et al [ 2 ], Damasceno et al [ 3 ], Procopio et al [ 5 ], and Rodrigues et al [ 6 ].…”