Improving event-based rainfall-runoff simulation using an ensemble artificial neural network based hybrid data-driven model

Kan, Guangyuan; Yao, Cheng; Li, Qiaoling; Li, Zhijia; Yu, Zhongbo; Liu, Zhiyu; Ding, Liuqian; He, Xu; Liang, Ke

doi:10.1007/s00477-015-1040-6

Cited by 65 publications

(27 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In generally, LSTM model is better than the traditional ANN model. Because of the typical flood characteristics, the ANN models can not make accurate simulation [31], but the ANN models are still better than the physical models in this region. It is the progress of the AI based techniques making the revolutionary strides for hydrology [4].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2018

Water

416

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

Section: Discussionmentioning

confidence: 99%

“…Compared with other network models, Kan [31] used a hybrid data-driven (network model and physical model) models for event-based rainfall-runoff simulation. PEK model (hybrid model) outperformed other models with values of NSE and R 2 are 0.51 and 0.73, respectively in validation stage.…”

Section: Discussionmentioning

confidence: 99%

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

et al. 2018

Water

416

180

View full text Add to dashboard Cite

show abstract

“…In addition, the analysis of peak precipitation shows that deforestation creates difficulty for forecasting processes by disrupting the region's ecosystem and increasing the probability of wet years and drought occurrences and causes more damage to the agricultural fields. The distinguishing aspect of this study is the optimization of ANNs to increase the accuracy of forecasting peak points, which indicates the advantages of the work compared with other investigations in different domains of hydrology without accurate evaluations of peak points (Ju et al, ; Maier et al, ; Valipour and Montazar, , ; Valipour, , , , , , , ; Kan et al, ).…”

Section: Resultsmentioning

confidence: 99%

Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms

Valipour

2015

Meteorological Applications

286

View full text Add to dashboard Cite

ABSTRACT:In this study, annual precipitation was forecast by coding in MATLAB software environment based on a non-linear autoregressive neural network (NARNN), non-linear input-output (NIO) and NARNN with exogenous input (NARNNX). Historical precipitation data (27 precipitation gauge stations located in Gilan, Iran) were used as two 21 year sets from 1968 to 1988 and from 1989 to 2009 for calibration and testing of the networks, respectively. Results showed that the accuracy of the NARNNX was better than that of the NARNN and NIO, based on r values. However, performance of the networks was not satisfactory because the number of neurons in the hidden layer and the roles of training, validation and testing phases were lacking flexibility and change. Optimization of the number of neurons in the hidden layer and the determination of the best role among the different phases led to improvement of network accuracy. The r values were <0.73 only for five stations in the optimized NARNN and <0.74 only for those stations with optimized NIO.

show abstract

“…The PEK approximator can be used to simulate the mapping relationship of the multi-input single-output (MISO) system and was proposed by Kan [29][30]. The output is simulated according to the selected input variables, which are selected by the PMI-based separate input variable selection (IVS) scheme.…”

Section: Pek-based Machine Learning Methodsmentioning

confidence: 99%

Investigating China’s Urban Air Quality Using Big Data, Information Theory, and Machine Learning

Chen¹,

Kan²,

Li³

et al. 2018

Pol. J. Environ. Stud.

Self Cite

View full text Add to dashboard Cite

Improving event-based rainfall-runoff simulation using an ensemble artificial neural network based hybrid data-driven model

Cited by 65 publications

References 47 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

Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms

Investigating China’s Urban Air Quality Using Big Data, Information Theory, and Machine Learning

Contact Info

Product

Resources

About