本研究开发了机器学习 (ML) 模型，以使用厌氧-缺氧-好氧膜生物反应器 (A
2
O-MBR)预测养分去除。使用网格搜索策略 (Grid-XGBoost) 应用极端梯度提升 (XGBoost) 模型来预测营养物的去除，包括铵 (NH
4
)、总磷 (TP) 和总氮 (TN)。这些模型针对常用的多层感知器 (MLP) 神经网络进行了验证。输入参数分为操作条件，包括溶解氧、氧化还原电位和混合液悬浮固体。这些条件也根据进水特征（如 NH
4
、TN、TP、总有机物含量、化学需氧量和悬浮固体。为每种 ML 技术开发了总共九个模型，使用操作条件和进水特征作为单独的数据集，并将它们结合起来用于每个目标营养素。据观察，仅使用操作条件或进水特性作为 XGBoost 和 MLP 的输入参数会产生较差的结果。此外，当考虑目标养分去除预测的所有参数时，观察到模型预测功效的显着提高。XGBoost 模型对 NH
4
的预测具有最高的 R
2
当操作条件、进水特征和组合数据集用作输入参数时，分别为 0.763、0.814 和 0.876。总体而言，集成 XGBoost 模型在所有情况下都表现出比 MLP 模型更好的性能。然而，发现这两种模型的性能都不足以在任何情况下预测 TN 和 TP 去除。所提出的 XGBoost 模型是一种可靠且稳健的 ML 技术，用于预测 NH
4
去除，这可能有助于提前做出决策以提高 A
2
O-MBR 系统的功效。
This study developed machine learning (ML) models to predict nutrient removal using an anaerobic-anoxic-oxic membrane bioreactor (A
2
O-MBR). An extreme gradient boosting (XGBoost) model was applied using a grid search strategy (Grid-XGBoost) to predict the removal of nutrients, including ammonium (NH
4
), total phosphorus (TP), and total nitrogen (TN). The models were validated against a commonly used multilayer perceptron (MLP) neural network. The input parameters were divided into operating conditions, including dissolved oxygen, oxidation-reduction potential, and mixed liquor suspended solids. These conditions were also partitioned based on influent characteristics such as NH
4
, TN, TP, total organic content, chemical oxygen demand, and suspended solids. A total of nine models were developed for each ML technique using the operating conditions and influent characteristics as separate datasets and combining them for each target nutrient. It was observed that using only operating conditions or influent characteristics as input parameters for XGBoost and MLP yielded poor results. Moreover, a significant improvement in the predictive efficacy of the model was observed when all parameters for the target nutrient removal predictions were considered. The prediction of NH
4
by the XGBoost model had the highest R
2
values of 0.763, 0.814, and 0.876 when the operating conditions, influent characteristics, and combined dataset were used as input parameters, respectively. Overall, the ensemble XGBoost model demonstrated better performance than the MLP model in all cases. However, the performance of both the models was found to be inadequate for predicting TN and TP removal in any scenario. The proposed XGBoost model is a reliable and robust ML technique for predicting NH
4
removal, which may contribute to decision-making in advance to improve the efficacy of an A
2
O-MBR system.
