Monthly runoff prediction is crucial for water resource allocation and flood prevention. Many existing methods use identical deep learning networks to understand monthly runoff patterns, neglecting the importance of predictor selection. To enhance predictive accuracy and reliability, this study proposes an RFECV–SSA–LSTM forecasting approach. It iteratively eliminates predictors derived from SSA decomposition and PACF using recursive feature elimination and cross-validation (RFECV) to identify the most relevant subset for predicting the target flow. LSTM modeling is then used to forecast flows 1–7 months into the future. Furthermore, the RFECV–SSA framework complements any machine-learning-based runoff prediction method. To demonstrate the method’s reliability and effectiveness, its outputs are compared across three scenarios: direct LSTM, MIR–LSTM, and RFECV–LSTM, using monthly runoff historical data from Yangxian and Hanzhong hydrological stations in the Hanjiang River Basin, China. The results show that the RFECV–LSTM method is more robust and efficient than the direct LSTM and MIR–LSTM counterparts, with the smallest number of outliers for NSE, NRMSE, and PPTS under all forecasting scenarios. The MIR–LSTM approach exhibits the worst performance, indicating that single-metric-based feature selection may eliminate valuable information. The SSA time–frequency decomposition is superior, with NSE values remaining stably around 0.95 under all scenarios. The NSE value of the RFECV–SSA–LSTM method is greater than 0.95 under almost all forecasting scenarios, outperforming other benchmark models. Therefore, the RFECV–SSA–LSTM method is effective for forecasting highly nonlinear runoff series, exhibiting high accuracy and generalization ability.

High-precision monthly runoff prediction results are of great significance to regional water resource management. However, with the changes in human activity, climate, and underlying surface conditions, the runoff sequence presents highly nonlinear and random characteristics. In order to improve the accuracy of runoff prediction, this study proposed a runoff prediction model based on fuzzy information granulation (FIG) and back propagation neural network (BPNN) improved with genetic algorithm (FIG-GA-BP). First, FIG was used to process the original runoff data to generate three sequences of minimum, average, and maximum that can reflect the rule of runoff changes. Then, genetic algorithms (GA) were used to obtain the optimal initial weights and thresholds of the BPNN through selection, crossover, and mutation. Finally, BPNN was used to predict the generated three sequences separately to obtain the prediction interval. The proposed model was applied to the monthly runoff interval prediction of Linjiacun and Weijiabu hydrological stations in the main stream of the Wei River and Zhangjiashan hydrological station on Jing River, a tributary of the Wei River. Compared with the interval prediction model FIG-BP, FIG-WNN, and traditional BP model. The results show that the FIG-GA-BP interval prediction model had a good prediction effect, with higher prediction accuracy and a narrower range of prediction intervals. Therefore, this model has superiority and practicability in monthly runoff interval prediction.