Department of Civil and Environmental Engineering, KAIST, Daejeon, 34141, Republic of Korea.
School of Earth Sciences and Environmental Engineering, Gwangju Institute of Science and Technology, Gwangju, 61005, Republic of Korea.
Water Res. 2020 Oct 1;184:116144. doi: 10.1016/j.watres.2020.116144. Epub 2020 Jul 6.
Wastewater treatment plants (WWTPs) have long been recognized as point sources of NO, a potent greenhouse gas and ozone-depleting agent. Multiple mechanisms, both biotic and abiotic, have been suggested to be responsible for NO production from WWTPs, with basis on extrapolation from laboratory results and statistical analyses of metadata collected from operational full-scale plants. In this study, random forest (RF) analysis, a machine-learning approach for feature selection from highly multivariate datasets, was adopted to investigate NO production mechanism in activated sludge tanks of WWTPs from a novel perspective. Standardized measurements of NO effluxes coupled with exhaustive metadata collection were performed at activated sludge tanks of three biological nitrogen removal WWTPs at different times of the year. The multivariate datasets were used as inputs for RF analyses. Computation of the permutation variable importance measures returned biomass-normalized dissolved inorganic carbon concentration (DIC·VSS) and specific ammonia oxidation activity (sOUR) as the most influential parameters determining NO emissions from the aerated zones (or phases) of activated sludge bioreactors. For the anoxic tanks, dissolved-organic-carbon-to-NO/NO ratio (DOC·(NO-N + NO-N)) was singled out as the most influential. These data analysis results clearly indicate disparate mechanisms for NO generation in the oxic and anoxic activated sludge bioreactors, and provide evidences against significant contributions of NO carryover across different zones or phases or niche-specific microbial reactions, with aerobic NH/NH oxidation to NO and anoxic denitrification predominantly responsible from aerated and anoxic zones or phases of activated sludge bioreactors, respectively.
污水处理厂（WWTP）长期以来一直被认为是氮氧化物（NO）的一个重要来源，而氮氧化物是一种强有力的温室气体和消耗臭氧物质。已经提出了多种生物和非生物机制来解释 WWTP 中 NO 的产生，其依据是从实验室结果推断和对来自运行中全规模工厂的元数据进行统计分析。在这项研究中，随机森林（RF）分析——一种用于从高度多变量数据集中选择特征的机器学习方法，被采用从新的角度来研究 WWTP 中活性污泥罐中 NO 的产生机制。在一年中的不同时间，在三个生物脱氮 WWTP 的活性污泥罐中进行了标准化的 NO 通量测量，并收集了详尽的元数据。将多元数据集作为 RF 分析的输入。通过计算置换变量重要性度量，返回生物量归一化的溶解无机碳浓度（DIC·VSS）和特定氨氧化活性（sOUR），作为决定活性污泥生物反应器曝气区（或相）NO 排放的最具影响力的参数。对于缺氧罐，溶解有机碳与 NO/NO 比（DOC·（NO-N+NO-N））被单独列为最具影响力的参数。这些数据分析结果清楚地表明，好氧和缺氧活性污泥生物反应器中 NO 生成的机制不同，并且没有证据表明在不同的区或相或特定微生物反应之间存在明显的 NO 携带现象，有氧 NH/NH 氧化生成 NO 和缺氧反硝化分别是活性污泥生物反应器的曝气区和缺氧区的主要来源。
