| Summary: | Quantifying the spatial and temporal footprint of multiple environmental stressors on marine fisheries is imperative to understanding the effects of changing ocean conditions on living marine resources. Pacific Cod (Gadus macrocephalus), an important marine species in the Gulf of Alaska ecosystem, has declined dramatically in recent years, likely in response to extreme environmental variability in the Gulf of Alaska related to anomalous marine heatwave conditions in 2014–2016 and 2019. Here, we evaluate the effects of two potential environmental stressors, temperature variability and ocean acidification, on the growth of juvenile Pacific Cod in the Gulf of Alaska using a novel machine-learning framework called “stress-scapes,” which applies the fundamentals of dynamic seascape classification to both environmental and biological data. Stress-scapes apply a probabilistic self-organizing map (prSOM) machine learning algorithm and Hierarchical Agglomerative Clustering (HAC) analysis to produce distinct, dynamic patches of the ocean that share similar environmental variability and Pacific Cod growth characteristics, preserve the topology of the underlying data, and are robust to non-linear biological patterns. We then compare stress-scape output classes to Pacific Cod growth rates in the field using otolith increment analysis. Our work successfully resolved five dynamic stress-scapes in the coastal Gulf of Alaska ecosystem from 2010 to 2016. We utilized stress-scapes to compare conditions during the 2014–2016 marine heatwave to cooler years immediately prior and found that the stress-scapes captured distinct heatwave and non-heatwave classes, which highlighted high juvenile Pacific Cod growth and anomalous environmental conditions during heatwave conditions. Dominant stress-scapes underestimated juvenile Pacific Cod growth across all study years when compared to otolith-derived field growth rates, highlighting the potential for selective mortality or biological parameters currently missing in the stress-scape model as well as differences in potential growth predicted by the stress-scape and realized growth observed in the field. A sensitivity analysis of the stress-scape classification result shows that including growth rate data in stress-scape classification adjusts the training of the prSOM, enabling it to distinguish between regions where elevated sea surface temperature is negatively impacting growth rates. Classifications that rely solely on environmental data fail to distinguish these regions. With their incorporation of environmental and non-linear physiological variables across a wide spatio-temporal scale, stress-scapes show promise as an emerging methodology for evaluating the response of marine fisheries to changing ocean conditions in any dynamic marine system where sufficient data are available.
|
|---|