Hi,

I am trying to see how the number of items found on the beach at 14 different sites (within 3 different states) across the Australian coast is affected by different factors (E.g., winds, currents, population). The offset is the effort of sampling (volunteers, hours, length of the beach, and the interval between sampling). All the parameters I am including in the model are already equally scaled.

I am a noob with bayesian and stan/brms models. But previous models were not working for me, the poisson was overdispersed. Therefore, I have tried poisson, negbinomial and zeroinflatedpoisson with brms.

And I having a great number of errors when running a brms model (whatever the family is, although zeroinflated looks to have the best results). See below the warning messages. I have tried to increase the interactions and chains but the errors persist. I attached the script and a subset of the data. Briefly, the errors occur when I introduce the random effects. Without them, the model runs really well.

Since I am a noob I am not to sure how to choose the priors and if this would help. I tried the standard, and few other combinations after using (get_prior) but the warnings persisted.

Let me know if more information is needed to understand the warning messages.

Any help will be much appreciated.

```
bm1 <- brm(TotalNumberItems ~ scaled_SOI_Index + scaled_Nearest_port_km + LandUse +
WeatherRegions +scaled_PC1winds+
scaled_PC1currents+ (1 | State) +(1| Site) +
offset(log(EffortDayC)),data = dat1,
family = zero_inflated_poisson("log"))
```

```
pp_check(bm1)
```

Warning messages:

1: There were 248 divergent transitions after warmup.

2: There were 3751 transitions after warmup that exceeded the maximum treedepth. Increase max_treedepth above 10.

3: There were 1 chains where the estimated Bayesian Fraction of Missing Information was low.

4: Examine the pairs() plot to diagnose sampling problems

5: The largest R-hat is 3.87, indicating chains have not mixed.

Running the chains for more iterations may help.

6: Bulk Effective Samples Size (ESS) is too low, indicating posterior means and medians may be unreliable.

Running the chains for more iterations may help.

7: Tail Effective Samples Size (ESS) is too low, indicating posterior variances and tail quantiles may be unreliable.

Running the chains for more iterations may help.