Dynamic Bayesian-Network-Based Approach to Enhance the Performance of Monthly Streamflow Prediction Considering Nonstationarity

Abstract

In recognizing the pervasive nonstationarity of hydrometeorological variables, a paradigm shift towards alternative analytical methodologies is imperative for refining hydroclimatic data modeling and prediction. We introduce a novel approach leveraging nonstationary Graphical Modeling and Bayesian Networks (NGM-BNs) tailored for hydrometeorological applications. Demonstrated through monthly streamflow forecasting in the Kashgar River Basin of China, our method illuminates the temporal evolution of network relationships, underscoring the dynamism inherent in both input variables and modeling parameters. The key to our approach is identifying the most suitable time horizon (MST) for model updates, which is intricately problem-specific and crucial for peak performance. This methodology not only unveils changing predictor significance across varying flow conditions but also elucidates the fluctuating temporal links between variables, especially under the lens of climate change, for instance, the growing impact of snowmelt on the Kashgar Basin’s streamflow. Compared to stationary counterparts, our nonstationary Bayesian framework excels in capturing extreme events by adeptly accommodating temporal shifts, outperforming traditional models including both stationary and nonstationary variants of Support Vector Regression (SVR) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS).