Forecasting nitrous oxide emissions from a full-scale wastewater treatment plant using LSTM-based deep learning models

IF 11.4 1区 环境科学与生态学 Q1 ENGINEERING, ENVIRONMENTAL Water Research Pub Date : 2024-11-05 DOI:10.1016/j.watres.2024.122754
Siddharth Seshan, Johann Poinapen, Marcel H. Zandvoort, Jules B. van Lier, Zoran Kapelan
{"title":"Forecasting nitrous oxide emissions from a full-scale wastewater treatment plant using LSTM-based deep learning models","authors":"Siddharth Seshan, Johann Poinapen, Marcel H. Zandvoort, Jules B. van Lier, Zoran Kapelan","doi":"10.1016/j.watres.2024.122754","DOIUrl":null,"url":null,"abstract":"Nitrous oxide (N<sub>2</sub>O) emissions from wastewater treatment plants (WWTPs) exhibit significant seasonal variability, making accurate predictions with conventional biokinetic models difficult due to complex and poorly understood biochemical processes. This study addresses these challenges by exploring data-driven alternatives, using long short-term memory (LSTM) based encoder-decoder models as basis. The models were developed for future integration into a model predictive control framework, aiming to reduce N<sub>2</sub>O emissions by forecasting these over varying prediction horizons. The models were trained on 12 months and tested on 3 months of data from a full-scale WWTP in Amsterdam West, the Netherlands. The dataset encompasses seasonal peaks in N<sub>2</sub>O emissions typical for winter and spring months. The best performing model, featuring a 256-256 LSTM architecture, achieved the highest accuracy with test R<sup>2</sup> values up to 0.98 across prediction horizons spanning 0.5 to 6.0 hours ahead. Feature importance analysis identified past N<sub>2</sub>O emissions, influent flowrate, NH<sub>4</sub><sup>+</sup>, NO<sub>x</sub>, and dissolved oxygen (DO) in the aerobic tank as most significant inputs. The observed decreasing influence of historical N<sub>2</sub>O emissions over extended prediction horizons highlights the importance and significance of process variables for the model's performance. The model's ability to accurately forecast short-term N<sub>2</sub>O emissions and capture immediate trends highlights its potential for operational use in controlling emissions in WWTPs. Further research incorporating diverse datasets and biochemical process inputs related to microbial activities in the N<sub>2</sub>O production pathways could improve the model's accuracy for longer forecasting horizons. These findings advocate for hybridising deep learning models with biokinetic and mechanistic insights to enhance prediction accuracy and interpretability.","PeriodicalId":443,"journal":{"name":"Water Research","volume":null,"pages":null},"PeriodicalIF":11.4000,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Water Research","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1016/j.watres.2024.122754","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}
引用次数: 0

Abstract

Nitrous oxide (N2O) emissions from wastewater treatment plants (WWTPs) exhibit significant seasonal variability, making accurate predictions with conventional biokinetic models difficult due to complex and poorly understood biochemical processes. This study addresses these challenges by exploring data-driven alternatives, using long short-term memory (LSTM) based encoder-decoder models as basis. The models were developed for future integration into a model predictive control framework, aiming to reduce N2O emissions by forecasting these over varying prediction horizons. The models were trained on 12 months and tested on 3 months of data from a full-scale WWTP in Amsterdam West, the Netherlands. The dataset encompasses seasonal peaks in N2O emissions typical for winter and spring months. The best performing model, featuring a 256-256 LSTM architecture, achieved the highest accuracy with test R2 values up to 0.98 across prediction horizons spanning 0.5 to 6.0 hours ahead. Feature importance analysis identified past N2O emissions, influent flowrate, NH4+, NOx, and dissolved oxygen (DO) in the aerobic tank as most significant inputs. The observed decreasing influence of historical N2O emissions over extended prediction horizons highlights the importance and significance of process variables for the model's performance. The model's ability to accurately forecast short-term N2O emissions and capture immediate trends highlights its potential for operational use in controlling emissions in WWTPs. Further research incorporating diverse datasets and biochemical process inputs related to microbial activities in the N2O production pathways could improve the model's accuracy for longer forecasting horizons. These findings advocate for hybridising deep learning models with biokinetic and mechanistic insights to enhance prediction accuracy and interpretability.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用基于 LSTM 的深度学习模型预测全规模污水处理厂的氧化亚氮排放量
污水处理厂(WWTPs)的氧化亚氮(N2O)排放具有显著的季节性变化,由于生化过程复杂且鲜为人知,因此传统的生物动力学模型很难进行准确预测。本研究以基于长短期记忆(LSTM)的编码器-解码器模型为基础,通过探索数据驱动的替代方法来应对这些挑战。开发这些模型是为了将来集成到模型预测控制框架中,目的是通过预测不同预测范围内的 N2O 排放量来减少排放。模型在荷兰阿姆斯特丹西区一个大型污水处理厂 12 个月的数据基础上进行了训练,并在 3 个月的数据基础上进行了测试。数据集包含了冬季和春季典型的 N2O 排放季节性峰值。性能最好的模型采用 256-256 LSTM 架构,在提前 0.5 到 6.0 小时的预测范围内,测试 R2 值高达 0.98,达到了最高准确度。特征重要性分析表明,过去的一氧化二氮排放量、进水流量、NH4+、氮氧化物和好氧池中的溶解氧 (DO) 是最重要的输入。观察到历史 N2O 排放量的影响随着预测时间的延长而减小,这凸显了工艺变量对模型性能的重要性和意义。该模型能够准确预测短期 N2O 排放量并捕捉即时趋势,这凸显了其在控制污水处理厂排放方面的应用潜力。进一步研究纳入与 N2O 生产途径中微生物活动相关的各种数据集和生化过程输入,可以提高该模型在更长预测期限内的准确性。这些研究结果主张将深度学习模型与生物动力学和机理见解相结合,以提高预测的准确性和可解释性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Water Research
Water Research 环境科学-工程:环境
CiteScore
20.80
自引率
9.40%
发文量
1307
审稿时长
38 days
期刊介绍: Water Research, along with its open access companion journal Water Research X, serves as a platform for publishing original research papers covering various aspects of the science and technology related to the anthropogenic water cycle, water quality, and its management worldwide. The audience targeted by the journal comprises biologists, chemical engineers, chemists, civil engineers, environmental engineers, limnologists, and microbiologists. The scope of the journal include: •Treatment processes for water and wastewaters (municipal, agricultural, industrial, and on-site treatment), including resource recovery and residuals management; •Urban hydrology including sewer systems, stormwater management, and green infrastructure; •Drinking water treatment and distribution; •Potable and non-potable water reuse; •Sanitation, public health, and risk assessment; •Anaerobic digestion, solid and hazardous waste management, including source characterization and the effects and control of leachates and gaseous emissions; •Contaminants (chemical, microbial, anthropogenic particles such as nanoparticles or microplastics) and related water quality sensing, monitoring, fate, and assessment; •Anthropogenic impacts on inland, tidal, coastal and urban waters, focusing on surface and ground waters, and point and non-point sources of pollution; •Environmental restoration, linked to surface water, groundwater and groundwater remediation; •Analysis of the interfaces between sediments and water, and between water and atmosphere, focusing specifically on anthropogenic impacts; •Mathematical modelling, systems analysis, machine learning, and beneficial use of big data related to the anthropogenic water cycle; •Socio-economic, policy, and regulations studies.
期刊最新文献
Development of a deep learning–based feature stream network for forecasting riverine harmful algal blooms from a network perspective Improved ultrafiltration performance through dielectric barrier discharge/sulfite pretreatment: Effects of water matrices and mechanistic insights Key Process of Ethanol Hydrogen Donor Promoting the Conversion of Organic Matter in Sludge to Bio-Oil Reconsideration of the role of hydrogen peroxide in peroxymonocarbonate-based oxidation system for pollutant control Forecasting nitrous oxide emissions from a full-scale wastewater treatment plant using LSTM-based deep learning models
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1