Water quality time series datasets for multi-step dissolved oxygen forecasting at two tributary monitoring stations in the Yangtze River Basin

This dataset supports the manuscript entitled “Multi-step dissolved oxygen prediction based on seasonal-trend decomposition and dual-branch global temporal modelling”. The dataset contains water quality time series from two automatic water quality monitoring stations in the middle and lower reaches of the Yangtze River Basin, China. Dataset A was collected from the Hannan Village site on the Han River, and Dataset B was obtained from the Liangtian Village site on the Jin River. The records cover the period from January 2021 to April 2024 at 4-hour intervals. The monitored variables include water temperature (WT), pH, dissolved oxygen (DO), chemical oxygen demand (COD), ammonia nitrogen (NH4+-N), total phosphorus (TP), total nitrogen (TN), electrical conductivity (EC), and turbidity (NTU). These datasets were used to evaluate multi-step dissolved oxygen forecasting under distinct water quality dynamics.