Comparing quantile regression spline analyses and supervised machine learning for environmental quality assessment at coastal marine aquaculture installations

Organic enrichment associated with marine finfish aquaculture is a local stressor of marine coastal ecosystems. To maintain ecosystem services, the implementation of biomonitoring programs focusing on benthic diversity is required. Traditionally, impact-indices are determined by extracting and identifying benthic macroinvertebrates from samples. However, this is a time-consuming and expensive method with low upscaling potential. A more rapid, inexpensive, and robust method to infer the environmental quality of marine environments is eDNA metabarcoding of bacterial communities. To infer the environmental quality of coastal habitats from metabarcoding data, two taxonomy-free approaches have been successfully applied for different geographical regions and monitoring goals, namely quantile regression splines (QRS) and supervised machine learning (SML). However, their comparative performance remains untested for monitoring the impact of organic enrichment introduced by aquaculture on marine coastal environments. We compared the performance of QRS and SML using bacterial metabarcoding data to infer the environmental quality of 230 aquaculture samples collected from seven farms in Norway and seven farms in Scotland along an organic enrichment gradient. As a measure of environmental quality, we used the Infaunal Quality Index (IQI) calculated from benthic macrofauna data (reference index). The QRS analysis plotted the abundance of amplicon sequence variants (ASVs) as a function to the IQI from which the ASVs with a defined abundance peak were assigned to eco-groups and a molecular IQI was subsequently calculated. In contrast, the SML approach built a random forest model to directly predict the macrofauna-based IQI. Our results show that both QRS and SML perform well in inferring the environmental quality with 89% and 90% accuracy, respectively. For both geographic regions, there was high correspondence between the reference IQI and both the inferred molecular IQIs (p < 0.001), with the SML model showing a higher coefficient of determination compared to QRS. Among the 20 most important ASVs identified by the SML approach, 15 were congruent with the good quality spline ASV indicators identified via QRS for both Norwegian and Scottish salmon farms. More research on the response of the ASVs to organic enrichment and the co-influence of other environmental parameters is necessary to eventually select the most powerful stressor-specific indicators. Even though both approaches are promising to infer environmental quality based on metabarcoding data, SML showed to be more powerful in handling the natural variability. For the improvement of the SML model, addition of new samples is still required, as background noise introduced by high spatio-temporal variability can be reduced. Overall, we recommend the development of a powerful SML approach that will be onwards applied for monitoring the impact of aquaculture on marine ecosystems based on eDNA metabarcoding data.

Estimating sea lice infestation pressure on salmon farms: Comparing different methods using multivariate state-space models

Sea lice are ectoparasites of salmonids, and are considered to be one of the main threats to Atlantic salmon farming. Sea lice infestation on a farm is usually initiated by attachment of the free-living copepodid stage derived from the surrounding water, frequently originating from adult lice on the same farm or from neighboring salmonid farms, referred to as internal and external sources, respectively. Various approaches have been proposed to quantify sea lice infestation pressure on farms to improve the management of this pest. Here, we review and compare five of these methods based on sea lice data from 20 farms located near Grand Manan island in the Bay of Fundy, New Brunswick, Canada. Internal and external infestation pressures (IIP and EIP, respectively) were estimated using different approaches, and their effects were modeled either by a unique parameter for all production cycles or by different parameters for each production cycle, using a multivariate state-space model. Predictive variables, such as water temperature and sea lice treatments, were included in the model, and their effects across production cycles were estimated along with those of other model parameters. Results showed that models with only EIP explained the variation in the data better than models with only IIP, and that models with unique IIP and unique EIP for all cycles were generally associated with the best model fit. The simplest, fixed lag method for calculating infestation pressure had the best predictive performance in our models among the methods studied.