基于改进麻雀搜索算法的空气质量指数预测

为更准确地预测空气质量指数（Air Quality Index，AQI），提出一种基于改进麻雀搜索算法（Improved Sparrow Search Algorithm，ISSA）的AQI预测模型（ISSA-BP）。利用麻雀搜索算法（Sparrow Search Algorithm，SSA）的全局搜索性能对BP神经网络的权值和阈值进行优化，解决传统BP神经网络在预测AQI过程中出现的收敛速度慢、易陷入局部最优等问题。同时，针对SSA在优化过程中的缺陷，引入立方映射和优化策略增强算法的全局搜索及收敛能力，进一步提高预测性能。应用ISSA-BP模型预测杭州市AQI，实验结果表明，与其他模型相比，该模型的预测精度有显著提升。本研究为大气污染防治提供了新的预测方法。

Air Quality Index Prediction Based on Improved Sparrow Search Algorithm

In order to predict Air Quality Index (AQI) more accurately, an AQI prediction model (ISSA-BP) based on Improved Sparrow Search Algorithm (ISSA) is proposed. The global search performance of Sparrow Search Algorithm (SSA) is used to optimize the weight and threshold of BP neural network, which solves the problems of slow convergence speed and easy to fall into local optimum in the process of predicting AQI by traditional BP neural network. At the same time, aiming at the defects of SSA in the optimization process, the cubic mapping and optimization strategy are introduced to enhance the global search and convergence ability of the algorithm and further improve the prediction performance. ISSA-BP model was used to predict AQI in Hangzhou. The experimental results show that the prediction accuracy of the model is significantly improved compared with other models. This study provides a new prediction method for air pollution prevention and control.