Recent Advances in Remote Sensing and Artificial Intelligence for River Water Quality Forecasting: A Review DOI Open Access

Daiwei Pan,

Ying Deng,

Simon X. Yang

et al.

Environments, Journal Year: 2025, Volume and Issue: 12(5), P. 158 - 158

Published: May 10, 2025

Rapid population growth and climate change have created challenges for managing water quality. Protecting sources devising practical solutions are essential restoring impaired inland rivers. Traditional quality monitoring forecasting methods rely on labor-intensive sampling analysis, which often costly. In recent years, real-time monitoring, remote sensing, machine learning significantly improved the accuracy of forecasting. This paper categorizes approaches into traditional, deep learning, hybrid models, evaluating their performance in parameters. long short-term memory (LSTMs), gated recurrent units (GRUs) LSTM- GRU-based models been widely used river Combining sensing with a network has enhanced data collection efficiency by capturing spatial variability within network, complementing high temporal resolution situ measurements, improving overall robustness predictive models. Additionally, leveraging weather prediction can further enhance better decision-making resource management.

Language: Английский

Recent Advances in Remote Sensing and Artificial Intelligence for River Water Quality Forecasting: A Review DOI Open Access

Daiwei Pan,

Ying Deng,

Simon X. Yang

et al.

Environments, Journal Year: 2025, Volume and Issue: 12(5), P. 158 - 158

Published: May 10, 2025

Rapid population growth and climate change have created challenges for managing water quality. Protecting sources devising practical solutions are essential restoring impaired inland rivers. Traditional quality monitoring forecasting methods rely on labor-intensive sampling analysis, which often costly. In recent years, real-time monitoring, remote sensing, machine learning significantly improved the accuracy of forecasting. This paper categorizes approaches into traditional, deep learning, hybrid models, evaluating their performance in parameters. long short-term memory (LSTMs), gated recurrent units (GRUs) LSTM- GRU-based models been widely used river Combining sensing with a network has enhanced data collection efficiency by capturing spatial variability within network, complementing high temporal resolution situ measurements, improving overall robustness predictive models. Additionally, leveraging weather prediction can further enhance better decision-making resource management.

Language: Английский

Citations

0