Medium-Term Rainfall Forecasts Using Artificial Neural Networks with Monte-Carlo Cross-Validation and Aggregation for the Han River Basin, Korea

Lee, Jeongwoo; Kim, Chul-Gyum; Lee, Jeong Eun; Kim, Nam Won; Kim, Hyeon-Jun

doi:10.3390/w12061743

Cited by 11 publications

(15 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the readjusted hydrological images were used for the training and testing of the CNN model and the data were used for training, verification, and testing of the model, there is no standard set for the data ratio. However, training and verification data were used in the ratio of 7:3 or 8:2 in several previous studies [57][58][59][60]. Therefore, the data were divided as shown in Table 4, and the model was divided into Cases 1, 2, and 3, used herein for training, verification, and testing, respectively.…”

Section: Results Of Building the Hydrological Imagementioning

confidence: 99%

Developing a Discharge Estimation Model for Ungauged Watershed Using CNN and Hydrological Image

Kim

Song²

2020

Water

View full text Add to dashboard Cite

This study aimed to estimate the discharge in ungauged watersheds. To this end, we herein deviated from the model development methodology of previous studies and used convolution neural network (CNN), a deep training algorithm, and hydrological images. As the CNN model was developed for solving classification issues in general, it is unsuitable for simulating the discharge, which is a continuous variable. Therefore, the fully connected layer of the CNN model was improved. Moreover, images reflecting the hydrological conditions rather than a general photograph were used as input data for the CNN model. Three study areas that have discharge gauged data were set for the model’s training and testing. The data from two of the three study areas were used for CNN model training, and the data of the other were used to evaluate model prediction performance. The results of this study demonstrate a moderate predictive success of the discharge of an ungauged watershed using the CNN model and hydrological images. Therefore, it can be suitable as a methodology for the discharge estimation of ungauged watersheds. Simultaneously, it is expected that our methodology can be applied to the field of remote sensing or to the field of real-time discharge simulation using satellite imagery on a global scale or across a wide area.

show abstract

Section: Results Of Building the Hydrological Imagementioning

confidence: 99%

Developing a Discharge Estimation Model for Ungauged Watershed Using CNN and Hydrological Image

Kim

Song²

2020

Water

View full text Add to dashboard Cite

show abstract

“…This approach is known to significantly reduce the variance of the model output [28]. Xu et al [29], Barrow and Crone [30], and Lee et al [31] successfully applied the MCCV To use the SIUVFH method, independent flood hydrographs are first selected and the hourly flows in each of them are then standardized and divided by V n+1 . The standardized hourly hydrograph is named as an unit volume flood hydrograph (UVFH).…”

Section: Development Of Artificial Neural Network (Ann)-based Instantaneous Peak Flow (Ipf) Estimation Methodsmentioning

confidence: 99%

“…Xu et al [29], Barrow and Crone [30], and Lee et al [31] successfully applied the MCCV method to hydrological prediction problems. However, the MCCV method has not been focused on flood peak estimation using ANN models with the input of the mean daily flows.…”

Section: Development Of Artificial Neural Network (Ann)-based Instantaneous Peak Flow (Ipf) Estimation Methodsmentioning

confidence: 99%

Estimation of Hourly Flood Hydrograph from Daily Flows Using Artificial Neural Network and Flow Disaggregation Technique

Lee

Kim

2020

Water

Self Cite

View full text Add to dashboard Cite

Flood data on a high temporal scale are required for the design of hydraulic structures, flood risk assessment, flood protection, and reservoir operations. Such flood data are typically generated using rainfall-runoff models through an accurate calibration process. The data also can be estimated using a simple relationship between the daily and the sub-daily flow records as an alternative to rainfall–runoff modelling. In this study, we propose an approach combining an artificial neural network (ANN) model for peak flow estimation and the steepness index unit volume flood hydrograph (SIUVFH) method for sub-daily flow disaggregation to generate hydrographs on an hourly time scale. The SIUVFH method is based on the strong relationship between the flood peak and the steepness index, which is defined as the difference between the daily flood peak and daily flow several days before the peak; it is also used for selecting a reference unit volume flood hydrograph to be scaled to obtain the sub-daily flood hydrograph. In this study, to improve the applicability of the SIUVFH method for locations with a weak relationship between the flood peak and steepness index, the ANN-based flood peak estimation was used as an additional indicator to determine a reference unit volume flood hydrograph. To apply the proposed method, ANN models for estimating the peak flows from the mean daily flows during peak and adjacent days were constructed for the studied dam sites. The optimal ANN structures were determined through Monte Carlo cross-validation. The results showed a good performance with statistical measurements of relative root mean square errors of 0.155–0.224, 0.208–0.301, and 0.244–0.382 for the training, validation, and testing datasets, respectively. An application of the combined use of the ANN-based peak estimation and the SIUVFH-based flow disaggregation revealed that the disaggregated hourly flows satisfactorily matched the observed flood hydrograph.

show abstract

“…Similarly, Haidar and Verma (2018) employed CNNs for monthly forecasts in eastern Australia. Lee et al (2020) forecasted monthly precipitation for the Han River Basin, South Korea using lagged climate indices.…”

Section: D Rainfall Forecastingmentioning

confidence: 99%

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

Sit¹,

Demiray²,

Demir³

2022

Preprint

View full text Add to dashboard Cite

With technological enhancements, the volume, velocity, and variety (3Vs) of the raw digital Earth data have increased in recent years. Due to the increased availability of computer resources and the growing popularity of deep learning applications, this data has been a crucial source for data-driven studies that have transformed the fields of climate and earth science. One of the critical data sources is precipitation supporting climate and earth science studies on modeling, forecasting, and preparedness for extreme events (i.e., floods, droughts, pollution transport). In this study, we worked on an extensive review of manuscripts focusing on use of deep learning methods to tackle challenges either to improve the quality or extrapolate (forecast) rainfall datasets. The purpose of this study is to summarize the most recent developments in deep learning approaches for forecasting rainfall or improving rainfall datasets, as well as highlighting issues, shortcomings, and open questions with insightful recommendations for future directions.

show abstract

Medium-Term Rainfall Forecasts Using Artificial Neural Networks with Monte-Carlo Cross-Validation and Aggregation for the Han River Basin, Korea

Cited by 11 publications

References 33 publications

Developing a Discharge Estimation Model for Ungauged Watershed Using CNN and Hydrological Image

Developing a Discharge Estimation Model for Ungauged Watershed Using CNN and Hydrological Image

Estimation of Hourly Flood Hydrograph from Daily Flows Using Artificial Neural Network and Flow Disaggregation Technique

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

Contact Info

Product

Resources

About