Modeling of a full-scale sewage treatment plant to predict the nutrient removal efficiency using a long short-term memory (LSTM) neural network. (October 2020)

• Record Type: Journal Article
• Authors: Yaqub, Muhammad; Asif, Hasnain; Kim, Seongboem; Lee, Wontae
• Is Part Of: Journal of water process engineering. Volume 37(2020)
• Publication Date: 2020-10
• Subjects: NH4-N ammonium -- A-A-O MBR anaerobic-anoxic-oxic membrane bioreactor -- ANN artificial neural network -- BP back-propagation -- COD chemical oxygen demand -- DO dissolved oxygen -- LSTM long short-term memory -- MSE mean square error -- MLSS mixed liquor suspended solids -- ORP oxidation reduction potential -- PVDF polyvinylidene fluoride -- Relu rectified linear unit -- RSM response surface methodology -- RE removal efficiency -- RSR root mean square error-observations standard deviation ratio -- SS suspended solids -- TMP trans‐membrane pressure -- TN total nitrogen -- TOC total organic carbon -- TP total phosphorous -- WWTP wastewater treatment plant; Ammonium -- Long short-term memory -- Removal efficiency -- Total nitrogen -- Total phosphorus; Water-supply engineering -- Periodicals; Saline water conversion -- Periodicals; Seawater -- Distillation -- Periodicals; Sanitary engineering -- Periodicals; Sewage -- Purification -- Periodicals; 627
• DOI: 10.1016/j.jwpe.2020.101388
• Languages: English
• ISSNs: 2214-7144

Abstract

Graphical abstract: Highlights: Presented data visualization and its importance in the soft modeling technique. Proposed LSTM model to estimate input-output relation in a complex A-A-O MBR process. Trained proposed LSTM model to predict RE of NH4 -N, TN, and TP in an A-A-O MBR process. Tested the proposed model using an unseen dataset to check the reliability of the model. Abstract: A long short-term memory (LSTM)-based neural network was proposed and developed to predict the ammonium (NH4 -N), total nitrogen (TN), and total phosphorus (TP) removal efficiency of an anaerobic-anoxic-oxic membrane bioreactor (A-A-O MBR) system after data visualization using Python programming. The influent wastewater characteristics, including, total organic contents, NH4 -N, TN, TP, chemical oxygen demand, suspended solids, and operating parameters, such as dissolved oxygen, oxidation-reduction potential, and mixed-liquor suspended solids, were considered as inputs, while removal efficiency was taken as an output parameter. First, data analysis and its normalization were conducted to improve the learning speed of the model. Performance criteria of the proposed model were evaluated based on statistical values, including the mean-square error (MSE) and root-mean-square error-observations standard deviation ratio (RSR). Based on the goodness-of-fit values, the proposed LSTM model achieved good performance in the testing dataset; calculation results deviated little, indicated by the MSE values of 0.0047, 0.015, and 0.018 for NH4 -N, TN, and TP, and RSR values of 0.0104, 0.129, and 0.141, respectively. The proposed LSTM model predicted the most precise removal efficiency for NH4 -N of A-A-O MBR system, while TN and TP predictions were comparatively less accurate, but still acceptable. The proposed LSTM model is promising for predicting the nutrient removal efficiency of the A-A-O MBR system in real-time and can aid in establishing process control strategies. Therefore, the proposed LSTM model is an adequate interpolation tool to predict the nutrient removal efficiency of the A-A-O MBR process in wastewater treatment systems.