Machine learning-based prediction of non-aeration linear alkylbenzene sulfonate mineralization in an oxygenic microalgal-bacteria biofilm

Libo Xia; Beibei Wu; Xiaocai Cui; Ting Ran; Qian Li; Yun Zhou

doi:10.1016/j.biortech.2024.132028

Machine learning-based prediction of non-aeration linear alkylbenzene sulfonate mineralization in an oxygenic microalgal-bacteria biofilm

Bioresour Technol. 2024 Dec 28:419:132028. doi: 10.1016/j.biortech.2024.132028. Online ahead of print.

Authors

Libo Xia¹, Beibei Wu¹, Xiaocai Cui¹, Ting Ran¹, Qian Li¹, Yun Zhou²

Affiliations

¹ College of Resources and Environment, Huazhong Agricultural University, Wuhan 430070, China.
² College of Resources and Environment, Huazhong Agricultural University, Wuhan 430070, China. Electronic address: yzhou112@mail.hzau.edu.cn.

PMID: 39736338
DOI: 10.1016/j.biortech.2024.132028

Abstract

Microalgal-bacteria biofilm shows great potential in low-cost greywater treatment. Accurately predicting treated greywater quality is of great significance for water reuse. In this work, machine learning models were developed for simulating and predicting linear alkylbenzene sulfonate (LAS) removal using 152-days collected data from a battled oxygenic microalgal-bacteria biofilm reactor (MBBfR). By using nine variables including influent LAS, hydraulic retention time (HRT), biofilm density and thickness, specific oxygen production and consumption rates, microalgae and bacteria concentrations, and dissolved oxygen (DO), the support vector machine (SVM) model enabled the accurate LAS removal prediction (training set: R² = 0.995, (root mean square error, RMSE) = 0.076, (mean absolute error, MAE) = 0.069; testing set: R² = 0.961, RMSE = 0.251, MAE = 0.153). SVM can be also successfully applied for MBBfR operation optimization (HRT = 4.28 h, DO = 0.25 mg/L) that achieving accurate prediction of LAS mineralization.

Keywords: Greywater; Linear alkylbenzene sulfonate; Machine learning; Microalgal-bacteria biofilm; Model explanation.