Sign in Subscribe
Genetic research

Artificial Intelligence Optimizes Polyaluminum Chloride Dosage in Drinking Water Treatment

Strategic Insights

— 1 min read

Researchers at the Universidad Nacional de Chimborazo have successfully applied a hybrid genetic algorithm-neural network approach to optimize the dosage of polyaluminum chloride (PAC) in drinking water treatment, leading to significant cost savings and improved water quality compliance. The study, published in the journal Computation, utilized operational data from 400 jar test experiments conducted between 2022 and 2024 at the Yanahurco water treatment plant in Ecuador. The team demonstrated that the proposed approach achieved excellent predictive accuracy and reduced median chemical costs by 49%.

Key Takeaways:

  • The study proposes a hybrid modeling framework that integrates artificial neural networks (ANN) with genetic algorithms (GA) to optimize PAC dosage under variable raw water conditions.
  • The ANN model achieved excellent predictive accuracy (R^2 0.95 for turbidity and color), supporting its use as a surrogate model within a GA-based optimization scheme.
  • The genetic algorithm evaluated dosage strategies by minimizing treatment costs while enforcing compliance with national water quality standards.
  • Optimization yielded a 49% reduction in median chemical costs and improved color compliance from 52% to 63%, while maintaining pH compliance above 97%.
  • Turbidity remained a challenge under some conditions, indicating the potential benefit of complementary coagulants.
  • The proposed ANN-GA approach offers a scalable and adaptive solution for enhancing chemical dosing efficiency in water treatment operations.
  • Dario Fernando Guaman-Lozada and his team from the Universidad Nacional de Chimborazo made significant contributions to this research, along with additional authors Lenin Santiago Orozco Cantos, Guido Patricio Santillan Lima, and Fabian Arias Arias.

Statistics:

  • 400 jar test experiments were conducted between 2022 and 2024 at the Yanahurco water treatment plant in Ecuador.
  • The Anniversary model achieved an R^2 of 0.95 for turbidity and color.
  • Optimization yielded a 49% reduction in median chemical costs.
  • Color compliance improved from 52% to 63%, while maintaining pH compliance above 97%.
  • Turbidity remained a challenge under some conditions, with a prevalence of 15%.

Sources:

  • "Artificial Intelligence Optimization of Polyaluminum Chloride (PAC) Dosage in Drinking Water Treatment: A Hybrid Genetic Algorithm-Neural Network Approach." Computation, 2025, 13(8), 179.
  • Universidad Nacional de Chimborazo, Grupo de Investigacion Estudios Interdisciplinarios, Facultad de Ingenieria. Av. Antonio Jose de Sucre km 1 1, via Guano, Riobamba 060103, Ecuador.

Read more