To address the limitations of traditional runoff prediction methods—namely, the oversimplification of meteorological factor selection, ambiguous interactions among core variables, and the disruptive influence of redundant inputs—this study focuses on the Zijiang River Basin as a representative case. A suite of machine learning models, including Long Short-Term Memory Neural Network (LSTM), Convolutional Neural Network (CNN)-LSTM, Temporal Convolutional Network (TCN), and Gradient Boosting Regression Tree (GBRT), was constructed and trained using 13 distinct combinations of meteorological variables. These configurations were systematically evaluated to assess their compatibility with each model in simulating daily runoff patterns. Additionally, the Shapley Additive Explanations (SHAP) algorithm was employed to quantitatively assess the contribution of each factor to predictive accuracy. Among the models tested, the TCN model consistently demonstrated superior performance, particularly in mitigating the effects of irrelevant or redundant features. The GBRT model showed distinctive strengths in accurately predicting peak flow timings. Of all input configurations, the combination of “runoff + precipitation + evaporation + temperature” emerged as the most effective. Findings indicate that the predictive value of individual meteorological variables hinges primarily on their direct correlation with runoff, while the effectiveness of multi-factor schemes depends on the degree of functional integration—specifically, the coupling of hydrological recharge, consumption, and regulatory processes. The presence of redundant variables was found to impair model performance unless they contributed to a meaningful synergistic relationship with core inputs. The SHAP analysis further reinforced these insights: precipitation-related variables proved to be the most critical to prediction accuracy, whereas temperature and evaporation served more complementary roles. Notably, the inclusion of relative humidity tended to suppress runoff responses and increased deviation in peak timing estimates. These findings shed light on the nuanced interplay between meteorological input design and model selection, offering a robust foundation for optimizing data-driven runoff prediction frameworks.

High-resolution satellite precipitation products are key inputs for basin-scale rainfall estimation, but they still exhibit substantial biases in complex terrain and during heavy rainfall. Recent multi-source fusion studies have shown that simply stacking multiple same-type microwave satellite products yields only limited additional gains for high-quality precipitation estimates and may even introduce local degradation, suggesting that targeted correction of a single, widely validated high-quality microwave product (such as IMERG) is a more rational strategy. Focusing on the mountainous, gauge-sparse Lüshui River basin with pronounced relief and frequent heavy rainfall, we use GPM IMERG V07 as the primary microwave product and incorporate CHIRPS, ERA5 evaporation, and a digital elevation model as auxiliary inputs to build a daily attention-enhanced CNN–LSTM (A-CNN–LSTM) bias-correction framework. Under a unified IMERG-based setting, we compare three network architectures—LSTM, CNN–LSTM, and A-CNN–LSTM—and test three input configurations (single-source IMERG, single-source CHIRPS, and combined IMERG + CHIRPS) to jointly evaluate impacts on corrected precipitation and SWAT runoff simulations. The IMERG-driven A-CNN–LSTM markedly reduces daily root-mean-square error and improves the intensity and timing of 10–50 mm·d⁻¹ rainfall events; the single-source IMERG configuration also outperforms CHIRPS-including multi-source setups in terms of correlation, RMSE, and performance across rainfall-intensity classes. When the corrected IMERG product is used to force SWAT, daily Nash-Sutcliffe Efficiency increases from about 0.71/0.70 to 0.85/0.79 in the calibration/validation periods, and RMSE decreases from 87.92 to 60.98 m³ s⁻¹, while flood peaks and timing closely match simulations driven by gauge-interpolated precipitation. Overall, the results demonstrate that, in gauge-sparse mountainous basins, correcting a single high-quality, widely validated microwave product with a small set of heterogeneous covariates is more effective for improving precipitation inputs and their hydrological utility than simply aggregating multiple same-type satellite products.

Near-real-time quantitative precipitation estimation (QPE) is crucial for flood modeling and disaster early warning. This study proposes a three-stage machine learning framework (TSMLF) for near-real-time QPE using Himawari-8 satellite data and rain gauge observations. The framework introduces a deep imbalance regression (DIR) algorithm to handle the imbalance in precipitation data. Building upon the existing two-stage “classification–estimation” QPE framework, a rainfall intensity classification model is incorporated. Furthermore, 27 combined QPE schemes are designed based on the TSMLF. This novel method is applied in the Xiangjiang River Basin, southern China. The performance of the different QPE schemes is evaluated. Results show that the DIR algorithm is effective for handling precipitation data imbalance, achieving a lower false alarm rate and a higher critical success index compared to the synthetic minority oversampling technique algorithm. Among the QPE schemes designed based on TSMLF, the S1-C41 scheme [i.e., using a rainfall intensity threshold of 4.1 mm/h (90th percentile)] achieves the best performance, with a correlation coefficient (CC) of 0.77 and a mean absolute error of 0.14 mm/h. In the evaluation of a representative rainstorm event, the S1-C41 scheme achieves a CSI of 0.767 and a CC of 0.779, demonstrating superior performance in capturing spatiotemporal precipitation features and identifying small-scale precipitation. The TSMLF significantly outperforms both traditional two-stage QPE models and existing near-real-time precipitation products such as IMERG-E and GSMap_NRT. This study provides new insights into handling precipitation data imbalance and constructing novel QPE structures.

Satellite precipitation products serve as valuable global data sources for hydrological modeling, yet their applicability across different hydrological models remains insufficiently explored. The distributed physics-informed deep learning model (DPDL), as a representative of emerging differentiable, physics-based hydrological models, requires a systematic evaluation of the suitability of multi-source precipitation products within its modeling framework. This study focuses on the Xiangjiang River Basin in southern China, where both a DPDL model and a Soil and Water Assessment Tool (SWAT) model were constructed. In addition, two model training strategies were designed: S1 (fixed parameters) and S2 (product-specific recalibration). Multiple precipitation products were used to drive both hydrological models, and their streamflow simulation performance was evaluated under different training schemes to analyze the compatibility between precipitation products and hydrological modeling frameworks. The results show that: (1) In the Xiangjiang River Basin of southern China, GSMaP demonstrated the best overall performance with a Critical Success Index of 0.70 and a correlation coefficient (Corr) of 0.79; IMERG-F showed acceptable accuracy with a Corr of 0.75 but had a relatively high false alarm rate (FAR) of 0.32; while CMORPH exhibited the most significant systematic underestimation with a relative bias (RBIAS) of −8.48%. (2) The DPDL model more effectively captured watershed hydrological dynamics, achieving a validation period correlation coefficient of 0.82 and a Nash–Sutcliffe efficiency (NSE) of 0.79, outperforming the SWAT model. However, the DPDL model showed a higher RBIAS of +16.69% during the validation period, along with greater overestimation fluctuations during dry periods, revealing inherent limitations of differentiable hydrological models when training samples are limited. (3) The S2 strategy (product-specific recalibration) improved the streamflow simulation accuracy for most precipitation products, with the maximum increase in the NSE coefficient reaching 15.8%. (4) The hydrological utility of satellite products is jointly determined by model architecture and training strategy. For the DPDL model, IMERG-F demonstrated the best overall robustness, while GSMaP achieved the highest accuracy under the S2 strategy. This study aims to provide theoretical support for optimizing differentiable hydrological modeling and to offer new perspectives for evaluating the hydrological utility of satellite precipitation products.