Sustainable Wastewater Treatment and Water Reuse via Electrochemical Advanced Oxidation of Trypan Blue Using Boron-Doped Diamond Anode - XGBoost-Based Performance Prediction

At a Glance

Metadata	Details
Publication Date	2025-10-15
Journal	Sustainability
Authors	Sevtap Tırınk
Institutions	Iğdır Üniversitesi
Analysis	Full AI Review Included

Executive Summary

This study presents a highly effective and sustainable framework for treating azo dye wastewater, integrating Boron-Doped Diamond (BDD) electrooxidation with eXtreme Gradient Boosting (XGBoost) machine learning for process optimization.

High Removal Efficiency: Achieved near-complete Trypan Blue (TB) dye removal (up to 99.73%) using BDD anodes, confirming the superior oxidative capacity of electrogenerated hydroxyl radicals (•OH).
Optimal Conditions Identified: Maximum efficiency was achieved under highly acidic conditions (pH 2.0), which enhances •OH generation and reduces electrostatic repulsion of anionic dye molecules.
Critical Parameter Sensitivity: System performance is highly sensitive to initial pH, current density, and electrolysis time, with optimal stirring speed determined to be 200 rpm.
ML Predictive Power: The XGBoost model demonstrated exceptional accuracy in predicting TB removal efficiency, achieving a coefficient of determination (R²) of 0.9966 on training data and 0.954 on unseen test data.
Energy Optimization: The integrated ML approach allows for the identification of optimal operating windows (e.g., 0.530-0.757 mA/cm²) that balance high removal rates with minimized energy consumption (EC).
Sustainable Framework: This data-driven methodology provides a robust, fast, and reliable tool for optimizing industrial electrooxidation systems, contributing to sustainable wastewater management and water reuse.

Technical Specifications

Parameter	Value	Unit	Context
Anode Material	Boron-Doped Diamond (BDD)	N/A	Non-active electrode, high OER potential
Cathode Material	Stainless Steel (SS 316)	N/A	Counter electrode
Effective Electrode Area	132	cm²	Geometric surface area
Optimal Initial pH	2.0	N/A	Maximizes TB degradation rate
Optimal Current Density Range	0.530 to 0.757	mA/cm²	Optimal balance of efficiency and EC
Optimal Electrolyte Conc. (Na₂SO₄)	40 to 60	mM	Minimizes ohmic losses and side reactions
Maximum TB Removal	99.73	%	Achieved at 60 min electrolysis
Lowest Energy Consumption (EC)	0.85	Wh/L	Measured at 0.152 mA/cm²
Highest Energy Consumption (EC)	2.65	Wh/L	Measured at 1.136 mA/cm²
TB Molecular Formula	C₃₄H₂₄N₆Na₄O₁₄S₄	N/A	Trypan Blue azo dye
XGBoost R² (Training Set)	0.9966	N/A	High model fit
XGBoost R² (Test Set)	0.954	N/A	High generalization ability
Optimal Stirring Speed	200	rpm	Maximizes mass transfer efficiency

Key Methodologies

The electrooxidation process was systematically investigated and modeled using the following steps:

Reactor Setup: Experiments were conducted in a 250 mL circular-bottom Plexiglas reactor under continuous stirring, utilizing BDD plates as the anode and SS 316 plates as the cathode.
Solution Preparation: Synthetic TB dye solutions (100, 200, 400 mg/L) were prepared. Anhydrous Na₂SO₄ was used as the supporting electrolyte (20-100 mM).
Condition Control: All runs were maintained at a constant temperature of 25 °C. Initial pH was adjusted across a wide range (2, 5, 6, 8, 11) using H₂SO₄ or NaOH.
Electrolysis Parameters: Current density was varied (0.152 to 1.136 mA/cm²), and electrolysis time was fixed at 60 minutes for each run. Stirring speed was tested at 200, 400, and 600 rpm.
Performance Measurement: TB degradation efficiency was determined spectrophotometrically by measuring absorbance at λ_max = 590 nm. Energy consumption (EC) was calculated in Wh/L.
Data Modeling (XGBoost): Experimental data (6 input parameters: pH, current density, time, electrolyte concentration, dye concentration, stirring speed) were split (80% training, 20% testing).
Hyperparameter Optimization: Grid Search was applied to optimize XGBoost parameters (e.g., nrounds=500, eta=0.1, max_depth=6) to maximize R² and minimize RMSE/MAE, ensuring model robustness and preventing overfitting.

Commercial Applications

The integration of BDD electrooxidation with machine learning optimization is highly relevant for industries requiring robust and energy-efficient Advanced Oxidation Processes (AOPs).

Textile Wastewater Treatment: Direct application for the decolorization and mineralization of persistent azo dyes, which constitute a major pollutant load in textile effluents.
Industrial Water Reuse: Enabling high-level mineralization of complex organic pollutants, making treated water suitable for industrial recycling and reducing fresh water intake.
Electrochemical Reactor Design: The XGBoost model serves as a predictive tool for scaling up BDD reactor systems, allowing engineers to rapidly determine optimal operational parameters (current density, flow rate, pH) without extensive pilot testing.
Chemical Manufacturing: Treatment of process streams containing toxic, non-biodegradable organic compounds where conventional biological methods fail.
Energy-Efficient AOPs: The ML framework provides real-time optimization potential to minimize energy consumption, crucial for reducing the high operational costs typically associated with BDD technology.

View Original Abstract

Azo dyes are widely used in the textile industry due to their vibrant colors and chemical stability; however, wastewater containing these dyes poses significant environmental and health risks due to their toxic, persistent, and potentially carcinogenic properties. In this study, the treatment of wastewater containing trypan blue dye was investigated using the electrooxidation process with boron-doped diamond electrodes, and the efficiency of the process was modeled through the Extreme Gradient Boosting (XGBoost) algorithm. In the experimental phase, the effects of key operational parameters, including current density, pH, electrolysis time, and supporting electrolyte concentration, on TB dye removal efficiency were systematically evaluated. Based on the experimental data obtained, a machine learning-based XGBoost prediction model was developed, and hyperparameter optimization was performed to enhance its predictive performance. The model achieved high accuracy (R2 = 0.996 for training and 0.954 for testing) and yielded low error metrics (RMSE and MAE), confirming its reliability in predicting removal efficiency. This study presents an integrated and data-driven approach for improving the efficiency and sustainability of electrooxidation processes and offers an environmentally friendly and effective method for the treatment of azo dye-contaminated wastewater.

Tech Support

Original Source

DOI: https://doi.org/10.3390/su17209134

References

2025 - Optimization of Coagulation Process Parameters for Reactive Red 120 Dye Using Ferric Chloride via Response Surface Methodology [Crossref]
2023 - A review of environmental impact of azo dyes
2024 - Electrocoagulation-based AZO DYE (P4R) removal rate prediction model using deep learning [Crossref]
2019 - Toxicity assessment of biologically degraded product of textile dye acid red g [Crossref]
2024 - Evaluation of parameters in the removal of azo Red 40 dye using electrocoagulation
2024 - Treatment of azo dye-containing wastewater in a combined UASB-EMBR system: Performance evaluation and membrane fouling study [Crossref]