ABSTRACT: The aquaculture industry can be impacted by mortality events triggered by marine heatwaves, pathogens, and other environmental factors. Aquaculture managers would benefit from advanced warning of mortality events so they can make decisions to maximise production and profitability. To help monitor fish health and performance, finfish farms are often equipped with an array of cameras and environmental sensors. However, analysing and interpreting all this information can be difficult. Decision support systems (DSSs) can help by simplifying multiple data sources into a single output for quick interpretation and action. Here, we present a DSS capable of providing salmon farmers with 4 wk warning of an impending mortality event. This DSS was trained on a suite of data routinely collected by New Zealand salmon farmers and provides an alert if weekly mortality is predicted to exceed 0.5%. In the final model, present mortality, water temperature, and standardised feeding rate were all found to be significantly correlated with the probability of a future mortality event. The model performed well when tested on data not included in the model-building process, suggesting that the DSS could be useful to farm managers. This study shows that even limited information can be used to construct a DSS capable of providing some advanced warning of elevated mortality risk. Given the ease with which DSSs can be adapted to ingest and predict other parameters, we see strong potential for future development and adoption of these tools by the aquaculture industry and other sectors.