What question did this study set out to answer?

This research aims to develop an intelligent system for assessing water quality using machine learning techniques.

May 21, 20260 citationsOpen Access

Water Analysis And Prediction ADCET26

CKChinmay Kulkarni Chinmay Kulkarni SSShivtej Sul Shivtej Sul SLSamadhan Lade Samadhan Lade

Puntos clave

This research aims to develop an intelligent system for assessing water quality using machine learning techniques.
Developed a water analysis and prediction system utilizing machine learning algorithms.
Trained models on physico-chemical parameters like pH, dissolved oxygen, and turbidity.
Employed Random Forest, SVM, and Gradient Boosting for prediction and classification.
Ensemble methods achieved up to 97.2% accuracy in classifying water potability.
Successfully predicted the Water Quality Index using trained models.

Resumen

—The degradation of global water quality,driven by rapid industrialization and urbanization,poses a severe threat to public health. Traditionalmonitoring methods are often slow and labor-intensive,struggling to handle the non-linear, high-volume datafrom modern sensor networks. This paper presents anintelligent "Water Analysis and Predictions System"that leverages Machine Learning (ML) to provideaccurate water quality assessment. By processingphysico-chemical parameters such as pH, DissolvedOxygen, and Turbidity, we trained models includingRandom Forest, SVM, and Gradient Boosting(XGBoost). Our results indicate that ensemble methodsachieve superior accuracy (up to 97.2%) in classifyingpotability and predicting the Water Quality Index(WQI). This data-driven framework offers a proactivesolution for environmental resource management

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo