Modelling the fate of endocrine-disrupting chemicals during wastewater ozonation by fluorescence and artificial neural network
Bibliographic record
Abstract
Many endocrine-disrupting chemicals (EDCs) are discharged into the aquatic environment mainly due to their incomplete removal during biological treatment at municipal wastewater treatment plants. For this reason, advanced oxidation processes (AOPs), using ozone with other oxidant agents, like hydrogen peroxide, are effective in removing EDCs. Furthermore, to reduce the risk of drinking water contamination by EDCs, it is necessary to ensure a real-time monitoring of wastewater treatment processes. Fluorescence spectroscopy could be used for wastewater quality monitoring to control the fate of EDCs in water systems. However, the complex physical, biological and chemical process involved in wastewater treatment process exhibit non-linear behaviors, which are difficult to describe by linear mathematical models. The artificial neural networks (ANNs) have been applied with remarkable success in several modeling studies including the highly non-linear ones.The main objective of the present work was to use fluorescence data and ANN to monitor two EDCs, namely a pesticide (Diuron) and a pharmaceulical and corrosion inhibitor (Benzotriazole) during advanced wastewater treatments.The data used were obtained from the pilot plant installed and operated by AquaSoil at the municipal wastewater reclamation plant of Fasano (Brindisi, Italy). The influent wastewater was obtained from tertiary treatment consisting of a coagulation stage by aluminum polychloride, sedimentation stage in lamella clarifiers and disinfection stage by sodium hypochlorite. An aliquot of the tertiary effluent was redirected to the pilot plant employing the O3/H2O2 advanced oxidation process. This process was operated in the patented technology commercialized by AquaSoil as MITO3X.Diuron and Benzotriazole were analyzed using standard methos. Fluorescence data were collected using a Shimadzu RF-5301PC fluorescence spectrophotometer at different excitation emission wavelengths, while ANN model has been developed using Matlab software with ANN toolbox to match the measured and the predicted concentrations of EDCs.The concentrations of Diuron and Benzotriazole were well correlated with selected fluorescence indexes. The combination of differente fluorescence peaks enhanced the determination coefficients of the single and multiple linear regressions. The developed ANN model that incorporated as input parameters the values of the fluorescence indices strongly enhanced the prediction of the fate of Diuron and Benzotriazole during AOPs. Therefore, the ANN-based model have been found to provide an efficient and robust tool in predicting the fate of EDCs removal. The comparison between ANN predicted data and experimental data shows the ability of artificial intelligence tools to predict EDCs concentrations with high accuracy and precision. Moreover, this model requires no additional information on the mechanism and the kinetics of chemical degradation of target contaminants. Since ANN have valuable advantages such as learning ability, dealing with imprecise, noisy and highly complex non-linear data, and parallel processing ability and due to the high sensitivity of fluorescence, it is expected that the developed fluorescence-ANN based model can be successfully applied for real-time control of AOPs employed for EDCs removal. This may also lead to AOPs optimization and cost savings.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".