基于PSO-SVR模型的再生水利用潜力预测分析——以河北省为例

Prediction and Analysis of Reclaimed Water Utilization Potential Based on PSO-SVR Model:A Case Study of Hebei Province

选取制约河北省再生水利用的经济投资、设施建设和用水因素三方面9个指标,通过使用粒子群优化算法支持向量回归机PSO-SVR模型,建立了自变量与再生水利用量之间的非线性函数映射关系,并对河北省再生水利用量进行了预测分析。结果表明,PSO-SVM模型,具有较好的预测精度与泛化能力,优于PCR回归模型和逐步回归模型。运用该模型对2020年、2025年河北省再生水利用量进行了预测,并计算了再生水利用率,再生水利用量影响因素的敏感性分析表明,用水状况因素指标对再生水利用量的影响作用最大,是影响河北省再生水利用量的主要因素。

The development and utilization of reclaimed water is one of the important ways to alleviate the shortage of water resources.The establishment of a scientific and effective prediction model of reclaimed water utilization has important guiding significance for the development and utilization of reclaimed water.In this paper,9 indicators which restrict economic investment,facility construction,and water use factors that restrict the utilization of recycled water in Hebei Province are selected,and independent variables are established by using PSO-SVR model.The non-linear function mapping relationship with the reclaimed water utilization,and the prediction analysis of the reclaimed water utilization in Hebei Province.The results show that the PSO-SVM model have better prediction accuracy and generalization ability,better than PCR regression model and stepwise regression model.The model was used to predict the reclaimed water utilization in Hebei Province in 2020 and 2025,and calculate the reclaimed water utilization rate.The sensitivity analysis of the influencing factors of reclaimed water utilization shows that the indicators of water use status have the greatest effect on the reclaimed water utilization,and are the main factors affecting the reclaimed water utilization in Hebei Province.