A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
State-of-the-Art Development of Two-Waves Artificial Intelligence Modeling Techniques for River Streamflow Forecasting
https://orcid.org/0000-0002-7143-4805
Abstract Streamflow forecasting is the most well studied hydrological science but still portray numerous unknown knowledge. The conventional physical-based model is unable to yield a high accuracy of forecast due to the embedded noises, non-linear and stochastic nature of hydrological data. This paper is to review the recent development of the artificial intelligence (AI) methods for river streamflow forecasting over the last two decades. The original establishments of forecasting model are derived from the neural network theory, supervised machine learning and fuzzy logic theory. The first wave of development comes with evolutional theory of optimization algorithm and the probabilistic theory. The distinction of AI model is the ability to process complex data that are non-linear, non-stationary and stochastic without prior physical knowledge. However, due to the limitations of the AI model, issues arise in the form of over-fitting, trap in local minima and slow learning process; and subsequently limit the possibility of gaining higher accuracy. This has prompted researchers to try numerous new approaches to increase the efficiency of data processing. The second wave comes with the hybrid models, modular techniques and ensemble models which has revolutionize into contemporary streamflow forecasting. With the latest hybrid models, results have shown retrieval of additional information are made possible that lead to better conclusion. This paper has suggested the research gaps and some future recommendations. It will be useful for new researcher and existing one to identify and be acquainted with the trends of different techniques of artificial intelligence.
State-of-the-Art Development of Two-Waves Artificial Intelligence Modeling Techniques for River Streamflow Forecasting
https://orcid.org/0000-0002-7143-4805
Abstract Streamflow forecasting is the most well studied hydrological science but still portray numerous unknown knowledge. The conventional physical-based model is unable to yield a high accuracy of forecast due to the embedded noises, non-linear and stochastic nature of hydrological data. This paper is to review the recent development of the artificial intelligence (AI) methods for river streamflow forecasting over the last two decades. The original establishments of forecasting model are derived from the neural network theory, supervised machine learning and fuzzy logic theory. The first wave of development comes with evolutional theory of optimization algorithm and the probabilistic theory. The distinction of AI model is the ability to process complex data that are non-linear, non-stationary and stochastic without prior physical knowledge. However, due to the limitations of the AI model, issues arise in the form of over-fitting, trap in local minima and slow learning process; and subsequently limit the possibility of gaining higher accuracy. This has prompted researchers to try numerous new approaches to increase the efficiency of data processing. The second wave comes with the hybrid models, modular techniques and ensemble models which has revolutionize into contemporary streamflow forecasting. With the latest hybrid models, results have shown retrieval of additional information are made possible that lead to better conclusion. This paper has suggested the research gaps and some future recommendations. It will be useful for new researcher and existing one to identify and be acquainted with the trends of different techniques of artificial intelligence.
State-of-the-Art Development of Two-Waves Artificial Intelligence Modeling Techniques for River Streamflow Forecasting
https://orcid.org/0000-0002-7143-4805
Abstract Streamflow forecasting is the most well studied hydrological science but still portray numerous unknown knowledge. The conventional physical-based model is unable to yield a high accuracy of forecast due to the embedded noises, non-linear and stochastic nature of hydrological data. This paper is to review the recent development of the artificial intelligence (AI) methods for river streamflow forecasting over the last two decades. The original establishments of forecasting model are derived from the neural network theory, supervised machine learning and fuzzy logic theory. The first wave of development comes with evolutional theory of optimization algorithm and the probabilistic theory. The distinction of AI model is the ability to process complex data that are non-linear, non-stationary and stochastic without prior physical knowledge. However, due to the limitations of the AI model, issues arise in the form of over-fitting, trap in local minima and slow learning process; and subsequently limit the possibility of gaining higher accuracy. This has prompted researchers to try numerous new approaches to increase the efficiency of data processing. The second wave comes with the hybrid models, modular techniques and ensemble models which has revolutionize into contemporary streamflow forecasting. With the latest hybrid models, results have shown retrieval of additional information are made possible that lead to better conclusion. This paper has suggested the research gaps and some future recommendations. It will be useful for new researcher and existing one to identify and be acquainted with the trends of different techniques of artificial intelligence.
State-of-the-Art Development of Two-Waves Artificial Intelligence Modeling Techniques for River Streamflow Forecasting
Tan, Woon Yang (author) / Lai, Sai Hin (author) / Teo, Fang Yenn (author) / El-Shafie, Ahmed (author)
2022
Article (Journal)
Electronic Resource
English
Streamflow Prediction Based on Artificial Intelligence Techniques
| Springer Verlag | 2022
Columbia River System Streamflow Forecasting Model
| British Library Conference Proceedings | 1995
Streamflow Forecasting Using Artificial Neural Networks
| British Library Conference Proceedings | 1998
Streamflow Forecasting for Han River Basin, Korea
| Online Contents | 1994
Streamflow Forecasting for Han River Basin, Korea
| Online Contents | 1996