Dissolved oxygen prediction in the Dianchi River basin with explainable artificial intelligence based on physical prior knowledge

Junhao Wu, Xi Chen, Jinghan Dong, Nen Tan, Xiaoping Liu, Antonis Chatzipavlis, Philip L. H. Yu, Adonis Velegrakis, Yining Wang, Yonggui Huang, Heqin Cheng, Diankai Wang

Abstract: Highlights•Physical prior knowledge significantly enhances DO prediction accuracy.•DO decreases with an increase in electric conductivity and turbidity.•PKBiLSTM outperforms the traditional models on 10 datasets.•The primary factors affecting DO exhibit seasonal differences.