A deep learning interpretable model for river dissolved oxygen multi-step and interval prediction based on multi-source data fusion

Water bodies experiencing excessively low dissolved oxygen (DO) concentrations cannot sustain aquatic life and disrupt ecosystem balance, whereas overly high concentrations induce eutrophication, deteriorating the water environment's health. DO monitoring and safeguarding have perennially been paramount for global environmental protection authorities. Precise DO prediction is vital for water resource protection. Due to the non-linearity, complexity, and periodicity of DO data sequence, this study introduces a predictive model integrating multi-source data fusion, mode decomposition, improved sparrow search algorithm (SSA), attention (AT) mechanism, and gated recurrent unit (GRU). Initially, the original sequence undergoes decomposition via variational mode decomposition (VMD), with the resultant decomposed sub-sequences being trained and predicted using the GRU. The final predictive outcomes are derived by summing the predictions of each sub-sequence. This study substantiates the proposed model's efficacy by contrasting single models, various decomposition strategies, and combined models utilizing diverse methods. For the testing sets of two datasets, the Nash-Sutcliffe efficiency (NSE) coefficient, and the proportion of acceptable predictive values of the proposed model are 0.980, 100% and 0.987, 100%, respectively, outperforming other benchmark models. Additionally, the Diebold Mariano (DM) test, valley, multi-step ahead, interval predictions, and interpretability are employed to compare and analyze the model results. DM test results reveal that at a 1% significance level, the predictions from the models proposed in this study surpass those of other benchmark models. Through various approaches and perspectives' comparison and analysis, it is further demonstrated that the model developed herein displays exceptional prediction accuracy and can be effectively deployed across diverse watersheds. © 2024 Elsevier B.V.