Related Experiment Video
Updated: Aug 16, 2025
07:13
Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
Published on: February 25, 2021
3.9K
Remote Sensing and Nonlinear Auto-regressive Neural Network (NARNET) Based Surface Water Chemical Quality Study: A
M Ramaraj1, Ramamoorthy Sivakumar2
1Department of Civil Engineering, College of Engineering and Technology, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu, Chennai, TN, 603 203, India. ramraj03893@gmail.com.
Bulletin of Environmental Contamination and Toxicology
|December 27, 2022
Summary
Remote sensing and Artificial Intelligence (AI) effectively monitor inland water quality. The Spatio-Temporal Hybrid Novel Technique (STHNT) accurately predicts pollution levels using satellite data and AI, aiding water resource management.
Area of Science:
- Environmental Science
- Remote Sensing
- Artificial Intelligence
Background:
- Inland water quality is increasingly threatened by natural and human activities.
- Continuous monitoring is essential to manage pollution in surface water bodies.
Purpose of the Study:
- To develop and evaluate a novel technique (STHNT) for predicting and monitoring chemical water quality pollution.
- To assess the effectiveness of integrating remote sensing with AI for Water Quality Index (WQI) assessment.
Main Methods:
- Utilized remote sensing technology with an Artificial Intelligence (AI) algorithm, specifically the Spatio-Temporal Hybrid Novel Technique (STHNT).
- Employed the Two Bands Regression Empirical (TBRE) model to retrieve water quality parameters from Sentinel-2 MSI satellite imagery.
- Applied the Nonlinear Auto-regressive Neural Network (NARNET), a type of Artificial Neural Network (ANN), for WQI prediction.
Main Results:
- The NARNET model demonstrated high accuracy in predicting WQI, achieving a Coefficient of Determination (R²) of 0.9911, Root Mean Square Error (RMSE) of 1.693, and Sum of Squares of Error (SSE) of 14.33.
- The integrated approach proved effective in retrieving water quality parameters and predicting pollution levels.
Conclusions:
- The combination of remote sensing and AI, particularly STHNT with NARNET, offers a powerful tool for water quality monitoring and management.
- This technology plays a pivotal role in reducing pollution levels in surface water bodies and ensuring sustainable water resource management.
