Physical Hybrid Neural Network Model to Forecast Typhoon Floods

Jhong, You Da; Chen, Chang Shian; Lin, Hsin Ping; Chen, Shien Tsung

doi:10.3390/w10050632

Cited by 30 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The process of rainfall-runoff simulation is critical for hydrology [27]. However, the process of rainfall-runoff is a complex problem for the hydrological modelling.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning with a Long Short-Term Memory Networks Approach for Rainfall-Runoff Simulation

et al. 2018

Water

447

180

View full text Add to dashboard Cite

Considering the high random and non-static property of the rainfall-runoff process, lots of models are being developed in order to learn about such a complex phenomenon. Recently, Machine learning techniques such as the Artificial Neural Network (ANN) and other networks have been extensively used by hydrologists for rainfall-runoff modelling as well as for other fields of hydrology. However, deep learning methods such as the state-of-the-art for LSTM networks are little studied in hydrological sequence time-series predictions. We deployed ANN and LSTM network models for simulating the rainfall-runoff process based on flood events from 1971 to 2013 in Fen River basin monitored through 14 rainfall stations and one hydrologic station in the catchment. The experimental data were from 98 rainfall-runoff events in this period. In between 86 rainfall-runoff events were used as training set, and the rest were used as test set. The results show that the two networks are all suitable for rainfall-runoff models and better than conceptual and physical based models. LSTM models outperform the ANN models with the values of R 2 and N S E beyond 0.9, respectively. Considering different lead time modelling the LSTM model is also more stable than ANN model holding better simulation performance. The special units of forget gate makes LSTM model better simulation and more intelligent than ANN model. In this study, we want to propose new data-driven methods for flood forecasting.

show abstract

“…The process of rainfall-runoff simulation is critical for hydrology [27]. However, the process of rainfall-runoff is a complex problem for the hydrological modelling.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning with a Long Short-Term Memory Networks Approach for Rainfall-Runoff Simulation

et al. 2018

Water

447

180

View full text Add to dashboard Cite

show abstract

“…Using hybrid neural network models (self-organizing map and back-propagation neural networks) to model the rainfall-runoff process for flood forecasts [13]; 6.…”

mentioning

confidence: 99%

Building an Intelligent Hydroinformatics Integration Platform for Regional Flood Inundation Warning Systems

Chang

Yang

et al. 2018

Water

View full text Add to dashboard Cite

Flood disasters have had a great impact on city development. Early flood warning systems (EFWS) are promising countermeasures against flood hazards and losses. Machine learning (ML) is the kernel for building a satisfactory EFWS. This paper first summarizes the ML methods proposed in this special issue for flood forecasts and their significant advantages. Then, it develops an intelligent hydroinformatics integration platform (IHIP) to derive a user-friendly web interface system through the state-of-the-art machine learning, visualization and system developing techniques for improving online forecast capability and flood risk management. The holistic framework of the IHIP includes five layers (data access, data integration, servicer, functional subsystem, and end-user application) and one database for effectively dealing with flood disasters. The IHIP provides real-time flood-related data, such as rainfall and multi-step-ahead regional flood inundation maps. The interface of Google Maps fused into the IHIP significantly removes the obstacles for users to access this system, helps communities in making better-informed decisions about the occurrence of floods, and alerts communities in advance. The IHIP has been implemented in the Tainan City of Taiwan as the study case. The modular design and adaptive structure of the IHIP could be applied with similar efforts to other cities of interest for assisting the authorities in flood risk management.

show abstract

“…Artificial intelligence and machine learning methods that have low computational cost and are easy to implement have been adopted in hydrologic forecasting. Among the various methods, artificial neural networks (ANNs) [14][15][16][17], support vector machines (SVMs) [18][19][20][21][22], and fuzzy inference models (FIMs) [23][24][25][26][27] are commonly and successfully used for forecasting various hydrologic variables. Regarding wave forecasting, ANNs were used by Deo and Sridhar Naidu [28], Tsai et al [29], and Mandal and Prabaharan [30] to forecast wave heights with inputs of present and previous wave heights.…”

Section: Introductionmentioning

confidence: 99%

Improving Coastal Ocean Wave Height Forecasting during Typhoons by using Local Meteorological and Neighboring Wave Data in Support Vector Regression Models

Chen

Wang

2020

JMSE

Self Cite

View full text Add to dashboard Cite

This study is aimed at applying support vector regression to perform real-time typhoon wave height forecasting with lead times of 1 to 3 h. Two wave rider buoys in the coastal ocean northeast of Taiwan provided real-time observation wave and meteorological data for the study. Information from actual typhoon events was collected and used for model calibration and validation. Three model structures were developed with different combinations of input variables, including wave, typhoon, and meteorological data. Analysis of forecasting results indicated that the proposed models have good generalization ability, but forecasts with longer lead times underestimate extreme wave heights. Comparisons of models with different inputs indicated that adding local meteorological data enhanced forecasting accuracy. Backup models were also developed in case local wave and meteorological data were unavailable. Analysis of these models revealed that when local wave heights are unknown, using neighboring wave heights can improve forecasting performance.

show abstract

Physical Hybrid Neural Network Model to Forecast Typhoon Floods

Cited by 30 publications

References 35 publications

Deep Learning with a Long Short-Term Memory Networks Approach for Rainfall-Runoff Simulation

Deep Learning with a Long Short-Term Memory Networks Approach for Rainfall-Runoff Simulation

Building an Intelligent Hydroinformatics Integration Platform for Regional Flood Inundation Warning Systems

Improving Coastal Ocean Wave Height Forecasting during Typhoons by using Local Meteorological and Neighboring Wave Data in Support Vector Regression Models

Contact Info

Product

Resources

About