Water Quality Analysis Using Deep Learning

Chahar, Ankit; Chowdhury, Ayanesh; Thulasidoss, Bharath Kumar; Reddy, Putta Vishal; Patel, Harshal; Patil, Ninad

doi:10.1109/icaccs54159.2022.9785189

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of Autoencoder-Long Short-Term Memory (AE-LSTM) models for water quality prediction was investigated by Zhang and Jin [5], who demonstrated how well these models capture temporal dependencies and forecast fluctuations in water quality over time. Furthermore, Chahar et al demonstrated how deep learning methods, such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs), may be used to identify complex patterns in water quality data and improve prediction accuracy [11,13,14].…”

Section: Literature Surveymentioning

confidence: 99%

Water Quality Prediction With Machine Learning Algorithms

Oliver North Rogers,

Ambili P S

2024

EPRA

View full text Add to dashboard Cite

Water quality prediction plays a significant role in safeguarding human health, preserving aquatic ecosystems, supporting sustainable water management practices, and ensuring regulatory compliance in aquatic environments. This study explores the use of machine learning (ML) models to predict water quality in various aquatic environments. By analyzing a comprehensive dataset of water quality indicators like pH, dissolved oxygen, and turbidity, the research employs several ML algorithms including Random Forest, Support Vector Machines, and Gradient Boosting Machines. Through rigorous training, validation, and optimization, the models are evaluated for their accuracy, sensitivity, and error rate. Additionally, the study identifies key factors impacting water quality variations through feature importance analysis. The study provides valuable insights for environmental monitoring, resource management, and regulatory compliance. Integrating advanced ML techniques with water quality assessment, this research aims to contribute to the development of effective early warning systems and decision-support tools that promote sustainable water management practices. KEYWORDS: Machine Learning, Water quality prediction, pH, Dissolved oxygen, Random Forest, Support Vector Machines (SVM), Gradient Boosting Machines.

show abstract

Section: Literature Surveymentioning

confidence: 99%