发表机构
University of Birjand; Clemson University（比尔詹德大学; 克莱姆森大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出一种基于LSTM与粒子群优化的多时间步长集成模型，用于预测伊朗阿吉恰伊河日径流，在2017-2018年数据上取得74.95%-91.42%的R²精度，并识别了关键影响变量。
AI 中文摘要
准确预报河流径流对于水资源管理、防洪和农业规划至关重要。本研究以伊朗西北部的阿吉恰伊河为研究对象，该河是乌尔米耶湖的主要支流，近年来面临日益严重的水资源压力。我们提出了一种基于长短期记忆（LSTM）网络的日径流预测模型。该模型结合了五个LSTM单元，每个单元在2至6天不等的不同时间间隔上进行训练，以更好地捕捉河流流量模式的变化。为了提高性能，每个模型均使用粒子群优化（PSO）——一种基于群体的优化算法——进行微调。所提出的方法在2017-2018年的未见数据上进行了评估，采用$R^2$、RMSE和MSE作为性能指标。结果显示模型具有较高的预测精度，$R^2$值介于74.95%至91.42%之间。此外，应用了多种特征重要性方法来确定最具影响力的变量，从而进一步深入了解驱动径流变化的因素。
英文摘要
Accurately forecasting river runoff is key to managing water resources, controlling floods, and planning agriculture. This study examines the Ajichay River in northwest Iran, a major tributary of Lake Urmia that has experienced increasing water-related stress in recent years. We introduce a daily runoff prediction model based on Long Short-Term Memory (LSTM) networks. The model combines five LSTM units, each trained on different time intervals ranging from 2 to 6 days, to better capture variations in river flow patterns. To improve performance, each model was fine-tuned using Particle Swarm Optimization (PSO), a population-based optimization algorithm. The proposed approach was evaluated on unseen data from 2017-2018 using $R^2$, RMSE, and MSE as performance metrics. The results showed strong predictive accuracy, with $R^2$ values ranging from 74.95% to 91.42%. In addition, multiple feature-importance methods were applied to identify the most influential variables, providing further insight into the factors that drive runoff variations.
