 This paper proposes a new method for predicting algal blooms using a Bayesian scale mixture of skew normal, Bayesian SMSN, model. The model uses readily available water quality parameters such as dissolved oxygen, pH, temperature, and turbidity to predict the distribution of algae biomass. The model was tested on two different datasets, one from a river and one from a lake, and it was found to be highly accurate at predicting the distribution of algae biomass. Additionally, the model was able to produce a probabilistic assessment of algal blooms, which is more accurate than traditional methods. This article was authored by Mu Enlu, Jing Hu, Yu Zhou Huang, and others.