Modeling Streamflow Enhanced by Precipitation from Atmospheric River Using the NOAA National Water Model: A Case Study of the Russian River Basin for February 2004

Han, Heechan; Kim, Jungho; Chandrasekar, V.; Choi, Jong-Hyuk; Lim, Sanghun

doi:10.3390/atmos10080466

Cited by 21 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the NWM utilizes a physically nonexplicit conceptual module for simulating baseflow (Knebl et al 2005). Although there have been studies involving the NWM (Souffront Alcantara et al 2017; Han et al 2019), to date no study has evaluated the NWM for its baseflow simulating capabilities.…”

Section: Introductionmentioning

confidence: 99%

Evaluating Baseflow Simulation in the National Water Model: A Case Study in the Northern High Plains Region, USA

Karki

Krienert

Hong

et al. 2021

J American Water Resour Assoc

View full text Add to dashboard Cite

The National Water Model (NWM) is a high‐resolution hydrological model capable of providing streamflow forecast at 2.7 million reaches across the conterminous United States (U.S.). It utilizes a conceptual (not physically explicit) module for estimating groundwater discharge (baseflow) to streams, and the baseflow module only allows for one‐way flux from the aquifer to the streams, with no interflow between surficial or groundwater catchments. This study evaluated the ability of the NWM to simulate baseflow in different geologic conditions with a case study in the Northern High Plains region. The study also evaluated two alternative formulations for the baseflow module in the NWM with the goal of improving simulated baseflow accuracy. The NWM simulated baseflow more accurately in a clayey catchment than in a sandy catchment. The model, however, over simulated baseflow during storm runoff events and under simulated during low flow events in both catchments. Analysis of groundwater recharge simulation showed that the NWM over simulated groundwater recharge for both catchment types, and reducing groundwater recharge using U.S. Geological Survey Baseflow Indexes improved the model performance for baseflow simulation, especially in the sandy catchment. Evaluation of the alteranative formulations showed that a modified Rorabaugh‐Rutledge formulation was able to improve the baseflow simulation with RMSE of 7.98 m3/s and R2 of 0.41 and also improved the timing of peak flows.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluating Baseflow Simulation in the National Water Model: A Case Study in the Northern High Plains Region, USA

Karki

Krienert

Hong

et al. 2021

J American Water Resour Assoc

View full text Add to dashboard Cite

show abstract

“…장단기 메모리(long short-term memory, LSTM)는 순환 신경망(recurrent neural network, RNN) 기법의 하나로 셀 (cell), 입력 게이트(input gate), 출력 게이트(output gate), 망각 게이트(forget gate)를 이용해 기존 순환 신경망(RNN) 의 단점인 기울기 소멸 문제(vanishing gradient problem)를 방지하도록 개발되었다 (Hochreiter and Schmidhuber, 1997;Agmls et al, 2009). 장단기 메모리는 순환 신경망의 일종이 지만 단점을 보완하여, 입력 자료에 대한 정보를 더욱 장기적 으로 기억하기 위해, 은닉층에 셀 상태(cell state)구조를 추가한 것이다 (Han et al, 2019;Le et al, 2019;Fig. 4).…”

Section: 장단기 메모리unclassified

Development of the Method for Flood Water Level Forecasting and Flood Damage Warning Using an AI-based Model

Kim¹,

Lee²,

Hwang-Bo³

et al. 2022

J. Korean Soc. Hazard Mitig

View full text Add to dashboard Cite

This study reviewed the applicability of AI-based models to predict flood water level and evaluate flood damage in small rivers with short arrival times. The Namyangju-si (Jingwan Bridge) watershed, where the most flood warnings have occurred, was selected as the target of study. Rainfall and water level data from 2008 to 2020 were collected for the watershed. A total of 40 rainfall events were identified when the water level was 1m or higher from June to September, corresponding to the flood season. Additionally, flood water level forecasting was performed using AI-based models such as deep neural network (DNN), long short term memory (LSTM), and storage function models. Predictive power evaluation revealed the DNN model displayed the lowest normalized root mean square error (NRMSE) with a value of 0.06. This study concludes that there are issues with the existing flood warning and heavy rain warning standards due to rainfall variability, correlation with the occurrence of damage caused by heavy rain, and the application of consistent standards nationwide. To solve this issue, the cause of flood damage was classified and the risk assessment criteria established by linking the water level and rainfall data. To develop an optimal flood damage classification prediction model based on the established criteria, two models were applied: XGBoost and random forest model. Evaluation of model predictive power revealed the F1-score for XGBoost was 0.92, indicating excellent predictive power. Based on the models presented herein, the flood damage assessment technique using the results of flood prediction can be used as basic data for disaster managers’ decision-making.

show abstract

“…The Russian River basin is located on the west coast of the United States with an average annual precipitation of 1180 mm and more than 80% of its annual precipitation was observed during wet season (from November to March). The Russian River basin is affected by various meteorological factors such as extratropical cyclones, jet streams, and atmospheric rivers from the Pacific oceans [46]. For runoff forecasting at outlet point, hourly runoff data were obtained from five United States Geological Survey (USGS) stations (Station ID: 11461500; 11462500; 11463000; 11464000; and 11467000) for the period from 2015 to 2019.…”

Section: Study Area and Datamentioning

confidence: 99%

Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation

Han

Choi

Jung

et al. 2021

Water

Self Cite

View full text Add to dashboard Cite

Accurate runoff prediction is one of the important tasks in various fields such as agriculture, hydrology, and environmental studies. Recently, with massive improvements of computational system and hardware, the deep learning-based approach has recently been applied for more accurate runoff prediction. In this study, the long short-term memory model with sequence-to-sequence structure was applied for hourly runoff predictions from 2015 to 2019 in the Russian River basin, California, USA. The proposed model was used to predict hourly runoff with lead time of 1–6 h using runoff data observed at upstream stations. The model was evaluated in terms of event-based performance using the statistical metrics including root mean square error, Nash-Sutcliffe Efficiency, peak runoff error, and peak time error. The results show that proposed model outperforms support vector machine and conventional long short-term memory models. In addition, the model has the best predictive ability for runoff events, which means that it can be effective for developing short-term flood forecasting and warning systems. The results of this study demonstrate that the deep learning-based approach for hourly runoff forecasting has high predictive power and sequence-to-sequence structure is effective method to improve the prediction results.

show abstract

Modeling Streamflow Enhanced by Precipitation from Atmospheric River Using the NOAA National Water Model: A Case Study of the Russian River Basin for February 2004

Cited by 21 publications

References 30 publications

Evaluating Baseflow Simulation in the National Water Model: A Case Study in the Northern High Plains Region, USA

Evaluating Baseflow Simulation in the National Water Model: A Case Study in the Northern High Plains Region, USA

Development of the Method for Flood Water Level Forecasting and Flood Damage Warning Using an AI-based Model

Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation

Contact Info

Product

Resources

About