The match-mismatch hypothesis suggests that the fitness of organisms increases when key life cycle events occur within an optimal window, e.g. when food is abundant. Here we test the importance of match-mismatch between salmon arrival and the ocean relative to ecosystem phenology, and the influence of arrival timing matches and mismatches on the ocean survival rates of fall run Chinook salmon originating from California’s Central Valley. Specifically, we analyzed tag-recovery data for all releases of coded-wire tagged fish raised in hatcheries and released directly into the San Francisco Estuary. We calculated an offset for each release relative to the spring transition date at 39°N, defined as the first day in each calendar year that the cumulative coastal upwelling index for the year becomes positive. We used relative ocean fishery recovery rates as a proxy of relative survival for different releases within the same year, with models incorporating covariates including source hatchery, stage, disease, acclimation pens, and size of fish at release. We used linear models, GAMs, and AIC to identify the best-supported models for the effects of release timing and other covariates, as well as the offset between release timing and the spring transition date, on ocean recovery rates.
Results/Conclusions
Model results indicate that release time is important, above and beyond the partially collinear effects of size at release. The optimal timing occurs between mid-April and the end of May, and the optimal offset occurs between approximately 100 and 150 days after the spring transition date. This result is consistent with the timing of peak krill production off central California, however we note that the effects of timing were not always consistent across years, and that in practice release timing cannot be varied independently of other factors important to survival such as fish size and physiological state. In addition, modeled year effects were greater than the modeled effects of timing or release size, indicating the importance of factors operating at longer time scales than a single cohort’s ocean entry period.