Machine Learning Approach Reveals the Assembly of Activated Sludge Microbiome with Different Carbon Sources during Microcosm Startup.

Youngjun Kim,Seungdae Oh,Sangeun Park

doi:10.3390/microorganisms9071387

Abstract

Activated sludge (AS) microcosm experiments usually begin with inoculating a bioreactor with an AS mixed culture. During the bioreactor startup, AS communities undergo, to some extent, a distortion in their characteristics (e.g., loss of diversity). This work aimed to provide a predictive understanding of the dynamic changes in the community structure and diversity occurring during aerobic AS microcosm startups. AS microcosms were developed using three frequently used carbon sources: acetate (A), glucose (G), and starch (S), respectively. A mathematical modeling approach quantitatively determined that 1.7–2.4 times the solid retention time (SRT) was minimally required for the microcosm startups, during which substantial divergences in the community biomass and diversity (33–45% reduction in species richness and diversity) were observed. A machine learning modeling application using AS microbiome data could successfully (>95% accuracy) predict the assembly pattern of aerobic AS microcosm communities responsive to each carbon source. A feature importance analysis pinpointed specific taxa that were highly indicative of a microcosm feed source (A, G, or S) and significantly contributed for the ML-based predictive classification. The results of this study have important implications on the interpretation and validity of microcosm experiments using AS.

Highlights

Activated sludge (AS) processes have commonly been used in full-scale municipal wastewater treatment plants (WWTPs) for the past 100 years
The reactors were operated with 10.5 days of solid retention time (SRT) and 0.2kg COD/m3 ·d of organic loading rate (OLR), comparable to those of full-scale sequencing batch reactor (SBR) processes [2]
Three sets of laboratory microcosms inoculated from one identical AS culture were maintained over 77 days by feeding A, G, and S, respectively

Summary

Introduction

Activated sludge (AS) processes have commonly been used in full-scale municipal wastewater treatment plants (WWTPs) for the past 100 years. Microbial communities are intricately linked to the major ecosystem functions of AS, directly affecting the overall system performance (e.g., removal of bulk organic matter, nitrogen, and phosphorous compounds). Numerous studies are being performed currently to address ecological questions, because microbial ecology provides the scientific foundation underlying pollutant removal, thereby helping to achieve the system’s practical goals [1]. AS communities with practical and scientific significance have been studied in both laboratory microcosms and field (full-scale WWTPs) experiments [3]. Laboratory microcosms can be set up at a low cost, can be strictly controlled under laboratory conditions, and are replicated [4]. The precise control and manipulation of variables in replicates help researchers to test hypotheses with statistical power, advancing the mechanistic understanding of AS processes.

Objectives

Methods

Results