School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan, China.
PeerJ. 2023 Aug 28;11:e15931. doi: 10.7717/peerj.15931. eCollection 2023.
Air quality has emerged as a critical concern in recent years, with the concentration of PM recognized as a vital index for assessing it. The accuracy of predicting PM concentrations holds significant value for effective air quality monitoring and management. In response to this, a combined model comprising CEEMDAN-RLMD-BiLSTM-LEC has been introduced, analyzed, and compared against various other models. The combined decomposition method effectively underlines the fundamental characteristics of the data compared to individual decomposition techniques. Additionally, local error correction (LEC) efficiently addresses the issue of prediction errors induced by excessive disturbances. The empirical results of nine steps indicate that the combined CEEMDAN-RLMD-BiLSTM-LEC model outperforms single prediction models such as RLMD and CEEMDAN, reducing MAE, RMSE, and SAMPE by 36.16%, 28.63%, 45.27% and 16.31%, 6.15%, 37.76%, respectively. Moreover, the inclusion of LEC in the model further diminishes MAE, RMSE, and SMAPE by 20.69%, 7.15%, and 44.65%, respectively, exhibiting commendable performance in generalization experiments. These findings demonstrate that the combined CEEMDAN-RLMD-BiLSTM-LEC model offers high predictive accuracy and robustness, effectively handling noisy data predictions and severe local variations. With its wide applicability, this model emerges as a potent tool for addressing various related challenges in the field.
空气质量近年来成为一个关键关注点，PM 浓度被认为是评估空气质量的重要指标。准确预测 PM 浓度对于有效进行空气质量监测和管理具有重要意义。针对这一问题，提出了一种组合模型，包括 CEEMDAN-RLMD-BiLSTM-LEC，并对其进行了分析和比较。与单独的分解技术相比，组合分解方法能够更有效地突出数据的基本特征。此外，局部误差校正（LEC）有效地解决了由于过度干扰引起的预测误差问题。九步经验结果表明，组合的 CEEMDAN-RLMD-BiLSTM-LEC 模型优于 RLMD 和 CEEMDAN 等单一预测模型，将 MAE、RMSE 和 SAMPE 分别降低了 36.16%、28.63%和 45.27%，以及 16.31%、6.15%和 37.76%。此外，在模型中加入 LEC 还分别将 MAE、RMSE 和 SMAPE 降低了 20.69%、7.15%和 44.65%，在泛化实验中表现出良好的性能。这些结果表明，组合的 CEEMDAN-RLMD-BiLSTM-LEC 模型具有较高的预测精度和鲁棒性，能够有效地处理噪声数据预测和严重的局部变化。该模型具有广泛的适用性，是解决该领域各种相关挑战的有力工具。
