To overcome the difficulty that existing hydrological models cannot accurately simulate hydrological processes with limited information in irrigated paddy areas in southern China, this paper presents a prediction model combining the Ensemble Empirical Mode Decomposition (EEMD) method and the Long Short-Term Memory (LSTM) network. Meteorological factors were set as the multivariate input to the model. Rainfall, regarded as the main variable affecting runoff, was decomposed and reconstructed into a combination of new series with stronger regularity by using the EEMD and K-means algorithm. The LSTM was used to explore the data laws and then to simulate and predict the runoff of the irrigated paddy areas. The Yangshudang (YSD) watershed of the Zhanghe Irrigation System (ZIS) in Hubei Province, China was taken as the study area. Compared with the other models, the results show that the EEMD-LSTM multivariate model had better simulation performance, with an $NSE$ above 0.85. Among them, the $R^2$, $NSE$, $RMSE$ and $RAE$ of the EEMD-LSTM${}^{\left(3\right)}$ model were the best, and they were 0.85, 0.86, 1.106 and 0.35, respectively. The prediction accuracy of peak flows was better than other models, as well as the performance of runoff prediction in rainfall and nonrainfall events, while improving the $NSE$ by 0.05, 0.24 and 0.24, respectively, compared with the EEMD-LSTM${}^{\left(1\right)}$ model. Overall, the EEMD-LSTM multivariations model is suited for simulating and predicting the daily-scale rainfall–runoff process of irrigated paddy areas in southern China. It can provide technical support and help decision making for efficient utilization and management of water resources.

A experiment was conducted at the Jiangxi Province Center Station of Irrigation Experiment from 2019 to 2021 to study the water and nitrogen balance under water and fertilizer regulation modes. The study aimed to propose a recommended mode for paddy fields that could save water, control pollution, reduce gas emission, and improve fertilizer use efficiency. This study examined the impact of different irrigation methods and nitrogen application levels on water saving and emission reduction in paddy fields. The experiment included six treatments, which involved two irrigation methods (intermittent irrigation and flooding irrigation, referred to as W1 and W0, respectively) and three application rates of nitrogen fertilizer (0 kg/ha, 135 kg/ha, 180 kg/ha, referred to as N0, N1 and N2, respectively). The study found that irrigation methods had a significant effect on the amount of irrigation, drainage, leakage, nitrogen load from drainage, soil nitrification potential, and ammonia volatilization. The results showed that compared to flooding irrigation, intermittent irrigation reduced the amount of irrigation, drainage, leakage and nitrogen load from drainage by an average of 25.98%, 16.03%, 8.43% and 10.86%, respectively. However, the study also found that the nitrification potential and ammonia volatilization increased by an average of 6.45% and 4.32%, respectively. Fertilization levels had a significant effect on drainage nitrogen load, early soil nitrification potential and ammonia volatilization. Compared with the treatment of N2 (180 kg N/ha), the drainage nitrogen load under the treatment of N1 (135 kg N/ha) decreased by 10.86% on average, while nitrification potential and ammonia volatilization increased by 38.74% and 3.33%, respectively. In terms of nitrogen output, the amount of nitrogen absorbed by crops was the largest, followed by the nitrogen load from field drainage, then ammonia volatilization, and then denitrification. Considering the goals of water saving, emission reduction, and the efficient utilization of water and fertilizer in paddy fields, the optimal water and fertilizer regulation mode was the W1N1 mode (intermittent irrigation combined with reduced nitrogen fertilizer application rate, 135 kg N/ha).