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

Southeast Asia's environmental challenges: emergence of new contaminants and advancements in testing methods

Emerging contaminants, including pharmaceuticals, personal care products, microplastics, and per- and poly-fluoroalkyl substances, pose a major threat to both ecosystems and human health in Southeast Asia. As this region undergoes rapid industrialization and urbanization, the increasing presence of unconventional pollutants in water bodies, soil, and various organisms has become an alarming concern. This review comprehensively examines the environmental challenges posed by emerging contaminants in Southeast Asia and recent progress in toxicity testing methods. We discuss the diverse range of emerging contaminants found in Southeast Asia, shedding light on their causes and effects on ecosystems, and emphasize the need for robust toxicological testing methods. This review is a valuable resource for researchers, policymakers, and environmental practitioners working to mitigate the impacts of emerging contaminants and secure a sustainable future for Southeast Asia.

Deep learning in water protection of resources, environment, and ecology: achievement and challenges

The breathtaking economic development put a heavy toll on ecology, especially on water pollution. Efficient water resource management has a long-term influence on the sustainable development of the economy and society. Economic development and ecology preservation are tangled together, and the growth of one is not possible without the other. Deep learning (DL) is ubiquitous in autonomous driving, medical imaging, speech recognition, etc. The spectacular success of deep learning comes from its power of richer representation of data. In view of the bright prospects of DL, this review comprehensively focuses on the development of DL applications in water resources management, water environment protection, and water ecology. First, the concept and modeling steps of DL are briefly introduced, including data preparation, algorithm selection, and model evaluation. Finally, the advantages and disadvantages of commonly used algorithms are analyzed according to their structures and mechanisms, and recommendations on the selection of DL algorithms for different studies, as well as prospects for the application and development of DL in water science are proposed. This review provides references for solving a wider range of water-related problems and brings further insights into the intelligent development of water science.

Application of supervised learning classification modeling for predicting benthic sediment toxicity in the southern California bight: A test of concept

Benthic sediment toxicity is linked to harmful effects in marine organisms and humans, and an understanding of the link would require, in part, a comprehensive and exhaustive analysis of sediment toxicity data already in hand. One tool which could aid in the process is machine learning (ML), a supervised classification modeling technique that has transformed how actionable insight are acquired from large datasets. The current study is a test of concept in which an ML classifier is sought that can accurately extrapolate the characteristics of a 5437 California-wide coastal training dataset (assembled from 1635 samples) to predict sediment toxicity in southern California bight (SCB). Twelve classifiers were trained to recognize sediment toxicity using 70 % of the dataset and among them, a Gradient Boosting Classifier (GBC) model using latitude, longitude, and water depth was found to be the most accurate at predicting toxicity (83 %). Among the variables, latitude was found to be the most significant driver of prediction by GBC in this test ecosystem. The performance of the model was verified with the remaining 30 % of the dataset and found to be 83 % accurate. Presented with 884 unfamiliar data points assembled from 854 measurements at 346 stations across SCB, GBC was 87 % accurate post-training, thus demonstrating a role supervised learning can play in the southern California environmental analytics.

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

Effects assessed at higher levels of biological organization (populations and communities) are the consequence of the sum of effects on individuals, which usually result from impacts at cellular and molecular levels. Given this rationale, these lower levels of biological organization are more responsive at an early stage, making them potential resources that can be used as early warning endpoints to address environmental stress. In this way, the information concerning effects at the molecular level of biological organization (e.g., transcripts, proteins, or metabolites) allows for an early assessment of future ecosystem problems, which may eventually enable a timely intervention before the impacts become visible and irreversible. However, despite providing an early warning and a better understanding of the toxicity mechanisms, enabling the protection of biological integrity, the most significant setback is that these endpoints may fail to foresee later impacts on the environment due to the ecosystem resilience or a weak link to the effects in the following level of biological organization, making these tools simply too conservative for stakeholders' interests. Hence, an approach targeting lower levels of biological organization will greatly benefit from addressing potential effects at higher levels. This can be achieved by establishing a link in biological organization, where the effects assessed at the lower end of biological organization are linked with the high probability of causing an effect at the other end, inducing changes in populations and communities, and eventually altering ecosystems in the future.

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

In this study, we propose integrating unmanned aerial systems (UASs) and machine learning classification for suitability prediction of expanding habitats for endangered flora species to prevent further extinction. Remote sensing imaging of the protected steppe-like grassland in Bilje using the DJI P4 Multispectral UAS ensured non-invasive data collection. A total of 129 individual flora units of five endangered flora species, including small pasque flower (Pulsatilla pratensis (L.) Miller ssp. nigricans (Störck) Zämelis), green-winged orchid (Orchis morio (L.)), Hungarian false leopardbane (Doronicum hungaricum Rchb.f.), bloody cranesbill (Geranium sanguineum (L.)) and Hungarian iris (Iris variegate (L.)) were detected and georeferenced. Habitat suitability in the projected area, designated for the expansion of the current area of steppe-like grassland in Bilje, was predicted using the binomial machine learning classification algorithm based on three groups of environmental abiotic criteria: vegetation, soil, and topography. Four machine learning classification methods were evaluated: random forest, XGBoost, neural network, and generalized linear model. The random forest method outperformed the other classification methods for all five flora species and achieved the highest receiver operating characteristic (ROC) values, ranging from 0.809 to 0.999. Soil compaction was the least favorable criterion for the habitat suitability of all five flora species, indicating the need to perform soil tillage operations to potentially enable the expansion of their coverage in the projected area. However, potential habitat suitability was detected for the critically endangered flora species of Hungarian false leopardbane, indicating its habitat-related potential for expanding and preventing further extinction. In addition to the current methods of predicting current coverage and population count of endangered species using UASs, the proposed method could serve as a basis for decision making in nature conservation and land management.

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

Simple Summary

The invasive seaweed Asparagopsis armata has the potential to be used as a biopesticide. The application of its exudate shows severe impacts on energetic and carotenoid metabolism and induces significant oxidative stress in a model weed. This points to the potential use of this macroalga as a resource for a biopesticide cocktail, for sustainable and eco-friendly weed control and as a substitute for the chemical pesticides widely used nowadays.

Abstract

Marine macroalgae have been increasingly targeted as a source of bioactive compounds to be used in several areas, such as biopesticides. When harvesting invasive species, such as Asparagopsis armata, for this purpose, there is a two-folded opportunity: acquiring these biomolecules from a low-cost resource and controlling its spreading and impacts. The secondary metabolites in this seaweed’s exudate have been shown to significantly impact the physiology of species in the ecosystems where it invades, indicating a possible biocidal potential. Considering this in the present work, an A. armata exudate cocktail was applied in the model weed Thellungiella halophila to evaluate its physiological impact and mode of action, addressing its potential use as a natural biocide. A. armata greatly affected the test plants’ physiology, namely, their photochemical energy transduction pathway (impairing light-harvesting and chemical energy production throughout the chloroplast electron transport chain), carotenoid metabolism and oxidative stress. These mechanisms of action are similar to the ones triggered when using the common chemical pesticides, highlighting the potential of the A. armata exudate cocktail as an eco-friendly biopesticide.