July 6, 2026•2 min read•from Frontiers in Marine Science | New and Recent Articles

Modelling forage fish species distribution in the Canadian Salish Sea

Our take

Understanding forage fish distribution is critical for effective marine ecosystem management. A new study utilizes a predictive geospatial model to map "hotspots" for six forage fish species within the Canadian Salish Sea, leveraging over two decades of Fisheries and Oceans Canada data. Employing a stacked ensemble approach, the model achieved high accuracy in identifying key environmental drivers, including surface currents and nutrient levels. Resulting hotspot maps highlight areas around the Fraser River delta and Gulf Islands, emphasizing the importance of inlets.

The recent study modelling forage fish species distribution in the Canadian Salish Sea represents a significant advancement in our understanding of these crucial components of the marine ecosystem. Forage fish, often overlooked despite their pivotal role as a link between primary producers and higher trophic levels, are experiencing increasing pressures from climate change, habitat degradation, and fisheries. This research directly addresses a critical knowledge gap, moving beyond anecdotal observations to provide a spatially explicit predictive model. It builds upon the foundational work examining animal migration patterns, such as the recent findings on sea turtle navigation Geomagnetic Migration, highlighting the increasing sophistication of our ability to understand and predict animal movements based on environmental factors. Furthermore, the approach undertaken—integrating extensive observational data with expert knowledge—echoes the kind of interdisciplinary solutions being explored for broader marine research platforms, as detailed in discussions around combining cetacean observations with ocean conditions How could a platform combining cetacean observations, ocean conditions and human impacts be useful for marine biology research or education.

The utilization of a stacked ensemble approach, combining Neural Network, Generalized Linear Mixed Effects, and XGBoost models, is particularly noteworthy. This demonstrates a commitment to rigorous methodology, leveraging the strengths of each model type to enhance predictive accuracy. The reported performance metrics—an AUC of 0.73, 98% precision, and 72% recall—are robust indicators of the model's ability to reliably identify forage fish hotspots. The identification of wind-driven surface currents, dissolved organic nitrogen, and mesozooplankton biomass as key predictor variables offers valuable insights into the ecological drivers of forage fish distribution. This empirical validation strengthens the model’s utility for both research and management applications, allowing for more targeted conservation efforts and spatially informed fisheries management strategies. The longitudinal data set, spanning 2000-2023, provides a degree of temporal context that is crucial for assessing the impact of long-term environmental changes on these populations.

The spatial resolution of the resulting map, highlighting areas of concentrated forage fish presence around the Fraser River delta, along the southern coast of Vancouver Island, and throughout the Gulf Islands, provides actionable intelligence for resource managers. Identifying these hotspots allows for prioritization of monitoring programs, habitat protection initiatives, and potentially, the mitigation of anthropogenic impacts. The observed association between higher probabilities and inlets, like Desolation Sound, further refines our understanding of habitat preferences and underscores the importance of these specific geomorphological features for forage fish survival and reproduction. This aligns with broader concerns regarding the impact of human activity and underscores the need for continued research into the effects of environmental changes on marine ecosystems, particularly as college students increasingly seek opportunities to engage in this field How can I get more experience as an uprising college freshman.

Looking ahead, a critical question arises: how can this model be integrated with real-time oceanographic data streams to provide adaptive management tools? The capacity to update the model with near real-time information on climate indicators, prey availability, and other relevant variables could transform it from a static map of hotspots into a dynamic forecasting tool. This would enable proactive responses to changing environmental conditions, enhancing the resilience of forage fish populations and safeguarding the broader ecosystem services they provide. Moreover, further refinement of the model to incorporate species-specific life history stages and their associated habitat requirements would significantly increase its predictive power and conservation value.

Forage fish are small, schooling fish that play a vital role in marine ecosystems, serving as a primary food source for seabirds, marine mammals, and commercially important species such as salmon. Despite their ecological importance, forage fish distributions remain understudied in the Canadian Salish Sea. Improved knowledge of their habitat uses and population dynamics is essential for effective conservation and management. In this study, a predictive geospatial model was developed to identify and map forage fish species “hot-spots” in the Canadian Salish sea. The model was constructed using 2,629 observations of six common forage fish species taken from Fisheries and Oceans Canada’s juvenile Pacific salmon survey, spanning 2000-2023. Discussions with a panel of local experts were then conducted to identify 18 environmental variables that were likely to influence the distributions of the forage species. Forage fish occurrence probabilities were estimated using a stacked ensemble approach which combined Neural Network, Generalized Linear Mixed Effects, and XGBoost models. The stacked ensemble achieved an average AUC of 0.73 across a 3-fold cross-validation, indicating strong overall ability to distinguish between presence and absence. Predicted presences were accurate 98% of the time (precision), and the model successfully detected 72% of all true presences (recall). Wind-driven surface current speeds, dissolved organic nitrogen (DON), and mesozooplankton biomass were found to be the most important predictor variables. A predictive map of forage fish hotspots was generated and reviewed, providing insight into the spatial distribution of the six species. Hotspots were identified around the Fraser River delta, along the southern coast of Vancouver Island, and throughout the Gulf Islands. Generally, higher probabilities were associated with inlets, such as Desolation Sound. The lowest probabilities of occurrence were associated with deep waters in the central Strait of Georgia.

Read on the original site

Open the publisher's page for the full experience

View original article →