Juvenile salmon usage of the Skeena River estuary

Abstract

Migratory salmon transit estuary habitats on their way out to the ocean but this phase of their life cycle is more poorly understood than other phases. The estuaries of large river systems in particular may support many populations and several species of salmon that originate from throughout the upstream river. The Skeena River of British Columbia, Canada, is a large river system with high salmon population- and species-level diversity. The estuary of the Skeena River is under pressure from industrial development, with two gas liquefaction terminals and a potash loading facility in various stages of environmental review processes, providing motivation for understanding the usage of the estuary by juvenile salmon. We conducted a juvenile salmonid sampling program throughout the Skeena River estuary in 2007 and 2013 to investigate the spatial and temporal distribution of different species and populations of salmon. We captured six species of juvenile anadromous salmonids throughout the estuary in both years, and found that areas proposed for development support some of the highest abundances of some species of salmon. Specifically, the highest abundances of sockeye (both years), Chinook in 2007, and coho salmon in 2013 were captured in areas proposed for development. For example, juvenile sockeye salmon were 2-8 times more abundant in the proposed development areas. Genetic stock assignment demonstrated that the Chinook salmon and most of the sockeye salmon that were captured originated from throughout the Skeena watershed, while some sockeye salmon came from the Nass, Stikine, Southeast Alaska, and coastal systems on the northern and central coasts of British Columbia. These fish support extensive commercial, recreational, and First Nations fisheries throughout the Skeena River and beyond. Our results demonstrate that estuary habitats integrate species and population diversity of salmon, and that if proposed development negatively affects the salmon populations that use the estuary, then numerous fisheries would also be negatively affected.

Fig 1. The Skeena River estuary, proposed development, and distribution of juvenile salmon sampling.

During the period of highest flow, the zone of freshwater influence extends from the mouth of the Skeena south to Ogden and Grenville Channels, and northwest through Chatham Sound, which also receives freshwater from the Nass River. The study area is shown divided into our analysis regions indicated by the letters IN for inside North, ON for outside north, MID for middle, IS for inside south, and OS for outside south. The IN region contains the focal industrial developments. Note that the ON region includes two polygons.

Fig 2. Beach seine sampling stations within the IN region indicated in Fig. 1.

Existing developments are shown in dark grey, while proposed development areas are diagonally shaded. Beach seine sampling stations are indicated by triangles. Beach seine sub-regions are indicated with open circles, except at Kinahan Islands where there was only one site.

Fig 3. GAM estimates of abundance showing temporal trend for sockeye (a, b), coho (c, d) and Chinook (e, f) salmon abundance during juvenile outmigration season in 2007 and 2013.

Points indicate normalized trawl catch per 20 min set, note different scales for each species. The smoothed line and shaded region indicate the temporal trend and confidence region for the GAM models.

Fig 4. Average beach seine catches of juvenile pink (a), chum (b), coho (c), and Chinook (d) salmon by sub-region, pooled across all sampling dates.

No sockeye salmon were captured by beach seine. Pink salmon catches greater than 100 per location are indicated by black dots above bars. Catches greater than 100 or 1000 individuals were calculated as 100 or 1000. Note different scales of y‐axes. Locations are as follows: KIN = Kinahan Islands, LEL = Lelu Island, RID = Ridley Island, TTS = Tsum Tsadai Inlet. LEL and RID sites are within footprints of proposed development.

Fig 5. Average normalized trawl catch of all species of juvenile sockeye (a), coho (b), pink (c), Chinook (d) and chum (e) salmon, pooled across all locations and sampling dates and normalized for 20 min sets.

Dark grey bars indicate 2007 and light grey bars indicate 2013. Note different scales for y‐axes for different species. Region boundaries and abbreviations are same as for Fig. 1.

Fig 6. GAM coefficients for parametric region covariates for sockeye (a), coho (b) and Chinook (c) salmon.

Coefficients are related to the (log) mean normalized catch per trawl set for each region in 2007 (black) and 2013 (grey ). Thus, a value of 0 indicates a mean normalized trawl catch of 1. Error bars indicate ± 2 standard errors.

Fig 7. Map of the north coast of British Columbia and the Skeena watershed showing locations of origin for genetically identified sockeye and Chinook salmon smolts captured in the Skeena estuary in 2007 and 2013.

Red and pink dots indicate the most likely location of origin for sockeye salmon, with locations that scored above (red) and below (pink) a 90% probability threshold for at least one specimen. Blue dots indicate the highest probability location of origin above (dark blue) and below (light blue) the 90% probability threshold for Chinook salmon. The sampling areas in the estuary of the Skeena River, where all fish were captured, are shown in black.

Fig 8. Picture of a pink salmon and a coho salmon smolt caught in the Skeena River estuary, in the area that is proposed to be dredged to accommodate tankers at a proposed terminal for natural gas.

A drilling rig is in the background. Photo by J.W. Moore.