Efficient AI-based water quality prediction and classification for sustainable urban environments in Texas city

Shubham Kuppili (), Victor Sheng (), Kishore Kunal (), R. Murgadoss () and Vairavel Madeshwaren ()

Edelweiss Applied Science and Technology, 2025, vol. 9, issue 7, 536-549

Abstract: This study utilizes advanced technologies to address water contamination by analyzing data collected from the Red River, Rio Grande, and Trinity River in Texas City, USA, between March 2023 and March 2024. The dataset comprises seven critical water quality parameters—conductivity, pH, turbidity, dissolved oxygen (DO), total and fecal coliform, chemical oxygen demand (COD), and nitrate—ensuring compliance with U.S. government standards for safe and clean drinking water. The proposed Efficient AI-based Water Quality Prediction and Classification (EAI-WQP) model aims to accurately predict water pollution parameters, particularly those influenced by industrial activities. Leveraging Apache Spark, a powerful big data processing framework, the model enables real-time data handling and analysis for effective pollution management. To enhance prediction accuracy, the model's parameter tuning is optimized using the Firefly Algorithm (FA). Furthermore, an Adaptive Neuro-Fuzzy Inference System (ANFIS) classifier is integrated into the model, combining fuzzy logic with neural networks to classify water quality into pollutant and non-pollutant categories. Comparative evaluations against established machine learning techniques such as GRU-ARIMA, SVM, and Random Forest demonstrate the superior performance of the EAI-WQP model in terms of accuracy, precision, F1 score, and recall. The study aims to analyze water pollution in Texas City using advanced AI methodologies, develop the EAI-WQP model for accurate forecasting of water quality parameters, implement real-time big data processing with Apache Spark, optimize model performance using the Firefly Algorithm (FA), classify water quality using ANFIS, and demonstrate the model's superiority over traditional machine learning methods.

Keywords: Environmental management; GRU-ARIMA; machine learning; Industrial pollution; Water quality prediction. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://learning-gate.com/index.php/2576-8484/article/view/8654/2903 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ajp:edwast:v:9:y:2025:i:7:p:536-549:id:8654

Access Statistics for this article

More articles in Edelweiss Applied Science and Technology from Learning Gate
Bibliographic data for series maintained by Melissa Fernandes ().