Optimizing struvite recovery from wastewater treatment: insights from machine learning models
文献类型：期刊论文
| 作者 | Zhang, Xiaoran1; Sun, Siao2,3; Han, Xiaomeng1; Shu, Shihu1 |
| 刊名 | JOURNAL OF WATER PROCESS ENGINEERING
 |
| 出版日期 | 2025-09-01 |
| 卷号 | 77页码:108520 |
| 关键词 | Phosphorus recovery Struvite crystallization High purity struvite Multi-objective optimization Model interpretation |
| ISSN号 | 2214-7144 |
| DOI | 10.1016/j.jwpe.2025.108520 |
| 产权排序 | 2 |
| 文献子类 | Article |
| 英文摘要 | Struvite crystallization provides a sustainable solution for phosphorus recovery from wastewater, contributing to resource conservation and the mitigation of environmental impacts. Machine learning models have emerged as powerful tools to simulate struvite crystallization performance to help inform effective control strategies. However, existing studies focus primarily on recovery efficiency while neglecting struvite purity and substratespecific effects. This study aims to address these gaps by developing a novel machine learning framework to simultaneously predict and optimize both struvite recovery efficiency and product purity. A comprehensive dataset comprising 1036 experimental records was compiled from 51 peer-reviewed papers, covering a broad range of operational conditions. Among three models evaluated, Random Forest and eXtreme Gradient Boosting were selected for their superior performances on recovery efficiency and product purity, respectively. Model interpretation revealed distinct key drivers, with pH and Mg:P ratio being the most influential for recovery efficiency, while temperature, Ca2+, and K+ concentrations governed product purity. The Non-dominated Sorting Genetic Algorithm II (NSGA-II) was then performed for multi-objective optimization. The resulting Pareto front revealed a clear trade-off between recovery efficiency (ranging from 86.42 % to 99.43 %) and product purity (ranging from 68.39 % to 97.83 %), providing actionable insights into optimal operational strategies under varying wastewater conditions. This framework can be used to support the achievement of high-efficiency, highpurity struvite recovery in practical applications. |
| URL标识 | 查看原文 |
| WOS关键词 | FLUIDIZED-BED REACTOR ; PHOSPHORUS RECOVERY ; MUNICIPAL |
| WOS研究方向 | Engineering ; Water Resources |
| 语种 | 英语 |
| WOS记录号 | WOS:001553839800001 |
| 出版者 | ELSEVIER |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/215614]  |
| 专题 | 区域可持续发展分析与模拟院重点实验室_外文论文 |
| 通讯作者 | Sun, Siao; Shu, Shihu |
| 作者单位 | 1.Donghua Univ, Coll Environm Sci & Engn, Shanghai 201620, Peoples R China; 2.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Reg Sustainable Dev Modeling, Beijing 100101, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Zhang, Xiaoran,Sun, Siao,Han, Xiaomeng,et al. Optimizing struvite recovery from wastewater treatment: insights from machine learning models[J]. JOURNAL OF WATER PROCESS ENGINEERING,2025,77:108520. |
| APA | Zhang, Xiaoran,Sun, Siao,Han, Xiaomeng,&Shu, Shihu.(2025).Optimizing struvite recovery from wastewater treatment: insights from machine learning models.JOURNAL OF WATER PROCESS ENGINEERING,77,108520. |
| MLA | Zhang, Xiaoran,et al."Optimizing struvite recovery from wastewater treatment: insights from machine learning models".JOURNAL OF WATER PROCESS ENGINEERING 77(2025):108520. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。