Combined machine learning and biomolecular analysis for stability assessment of anaerobic ammonium oxidation under salt stress

Abstract

In this study, the stability of the total nitrogen removal efficiency (TNRE) was modeled using an artificial neural network (ANN)-based binary classification model for the anaerobic ammonium oxidation (AMX) process under saline conditions. The TNRE was stabilized to 80.2 ± 11.4% at the final phase under the salinity of 1.0 ± 0.02%. The results of terminal restriction fragment length polymorphism (T-RFLP) analysis showed the predominance of Candidatus Jettenia genus. Real-time quantitative PCR analysis revealed the average abundance of Ca. Jettenia and Kuenenia spp. increased in 3.2 ± 5.4 × 108 and 2.0 ± 2.2 × 105 copies/mL, respectively. The prediction accuracy using operational parameters with data augmentation was 88.2%. However, integration with T-RFLP and real-time qPCR signals improved the prediction accuracy by 97.1%. This study revealed the feasible application of machine learning and biomolecular signals to the stability prediction of the AMX process under increased salinity.