An artificial neural network model reveals water level changes alter bioavailable PCB concentrations in the Detroit River.

Temporal trends of bioavailable PCB water concentrations from a long running mussel biomonitoring program (1998-2023) in the Detroit River, Ontario, Canada. Bioavailable sum PCB10 concentrations exhibited long term declines at two biomonitoring locations but such declines were influenced by changes in water levels and showed different responses among individual congeners. Temporal declines in PCBs were highest rising water levels, PCBs reverted to an increasing trend for all congeners at the upstream biomonitoring location. At the midstream location, only PCBs 28 + 31 and 52 changed their temporal trajectories, while other PCBs slowed their decline relative to the constant water level regime. A deep neural network (DNN) model was trained to the data. The parsimony optimized model identified sediment PCB concentrations, chemical KOW, mean annual water level and year as the most important predictors of PCB water concentrations and explained more than double the variation compared to a multiple regression model. Overall, both empirical and modeled results show that hydrological fluctuations significantly affected bioavailable PCB concentrations and their temporal trends in this system. As water levels continue to decline in the Detroit River, PCBs are expected to resume their previous decreasing trend in the coming years.