In the Barents Sea and adjacent water, fishing grounds are closed for shrimp fishing by the Norwegian Directorate of Fisheries Monitoring and Surveillance Service (MSS) if the expected number of juvenile fish caught are predicted to exceed a certain limit per kilogram shrimp (Pandalus borealis). Today, a simple ratio estimator, which does not fully utilize all data available, is in use. In this paper, we construct a Bayesian hierarchical spatiotemporal model for improved prediction of the bycatch ratio in the Barents Sea shrimp fishery. More predictable bycatch will be an advantage for the MSS because of more correct decisions and better resource allocation and also for the fishermen because of more predictable fishing grounds. The model assumes that the occurrence of shrimp and juvenile Atlantic cod (Gadus morhua) can be modeled by linked regression models containing several covariates (including 0-group abundance estimates) and random effects modeled as Gaussian fields. Integrated nested Laplace approximations is applied for fast calculation. The method is applied to prediction of the bycatch ratio for Atlantic cod.