River Freeze-Up and Breakup Prediction Using Multi-Station Adaptive Echo-State Temperature Forecasting and Reach-Specific Criteria

Freeze-up and breakup dates in cold-region rivers strongly influence winter navigation closure, spring navigation resumption, and navigation safety during ice runs. However, river-ice transitions are reach-specific and cannot be reliably determined from instantaneous air-temperature thresholds alone, while recursive multi-step forecasting is vulnerable to error accumulation. To address these challenges, this study develops the SAG-AL-ESN-HRCLRC framework for multi-station air-temperature forecasting and reach-specific freeze-up and breakup date determination in the Harbin, Heihe, and Raohe reaches. The framework extracts inter-station dependence from lagged correlations of temperature increments and combines correlation-based spatial weighting with annual, semiannual, and diurnal periodic encodings. It further employs an echo state network with an adaptive leaking rate and introduces horizon- and regime-conditioned closed-loop residual correction to reduce recursive error accumulation in both target- and auxiliary-station forecasts. Across the three scenarios, the 10-run evaluation yields an average MAE of 1.980 ± 0.193 °C, an RMSE of 2.544 ± 0.218 °C, and an R2 of 0.9761 ± 0.0030. The corresponding Step-1 and Step-56 MAEs are 1.195 ± 0.167 °C and 2.040 ± 0.230 °C, respectively. The corresponding freeze-up and breakup date prediction errors across the three ice seasons from 2023–2024 to 2025–2026 are 1.33 and 1.22 days, respectively. These results indicate that, under the data conditions and reach-specific criteria considered in this study, the proposed framework can provide useful temperature-based information for river-ice monitoring, navigation management, and ice-season safety decisions.