ANN-based prediction of 17α-ethinylestradiol removal using green magnetic nanoparticles synthesized from celery extract
17α-Ethinylestradiol (EE2), a persistent endocrine-disrupting contaminant in natural waters, poses significant challenges for elimination through conventional wastewater treatment systems. In this study, eco-friendly magnetic nanoparticles (C-FeMNPs) were synthesized using celery leaf extract as bot...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Results in Chemistry |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2211715625005740 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | 17α-Ethinylestradiol (EE2), a persistent endocrine-disrupting contaminant in natural waters, poses significant challenges for elimination through conventional wastewater treatment systems. In this study, eco-friendly magnetic nanoparticles (C-FeMNPs) were synthesized using celery leaf extract as both a reducing and stabilizing agent for EE2 adsorption. X-ray diffraction (XRD), Fourier-transform infrared spectroscopy (FTIR), field-emission scanning electron microscopy (FESEM), and transmission electron microscopy (TEM) were employed to characterize the crystalline structure and surface functionalities of the synthesized nanoparticles. Adsorption efficiency was investigated under different conditions, and EE2 concentrations were quantified using high-performance liquid chromatography with UV detection (HPLC–UV). To optimize the adsorption process, an artificial neural network (ANN) model was developed using solution pH, adsorbent dosage, contact time, and initial EE2 concentration as input parameters. The optimized ANN model exhibited a strong predictive relationship (R2 = 0.96) with a prediction error of less than ±2 %. The maximum removal efficiency of 96 % was achieved under the following conditions: pH 3.0, C-FeMNP dosage of 50 mg·L−1, contact time of 30 min, and initial EE2 concentration of 1.0 mg·L−1. This experimental and modelling methodology is demonstrated to be a cost-effective and sustainable approach to removing emerging contaminants from freshwater, thereby reducing reliance on trial-and-error experiments through machine learning-based optimization. |
|---|---|
| ISSN: | 2211-7156 |