Since predicting rapidly fluctuating water levels is very important in water resource engineering, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) were used to evaluate water-level-prediction accuracy at Hangang Bridge Station in Han River, South Korea, where seasonal fluctuations were large and rapidly changing water levels were observed. The hydrological data input to each model were collected from the Water Resources Management Information System (WAMIS) at the Hangang Bridge Station, and the meteorological data were provided by the Seoul Observatory of the Meteorological Administration. For high-accuracy high-water-level prediction, the correlation between water level and collected hydrological and meteorological data was analyzed and input into the models to determine the priority of the data to be trained. Multivariate input data were created by combining daily flow rate (DFR), daily vapor pressure (DVP), daily dew-point temperature (DDPT), and 1-hour-max precipitation (1HP) data, which are highly correlated with the water level. It was possible to predict improved high water levels through the training of multivariate input data of LSTM and GRU. In the prediction of water-level data with rapid temporal fluctuations in the Hangang Bridge Station, the accuracy of GRU’s predicted water-level data was much better in most multivariate training than that of LSTM. When multivariate training data with a large correlation with the water level were used by the GRU, the prediction results with higher accuracy (R2=0.7480−0.8318; NSE= 0.7524−0.7965; MRPE= 0.0807−0.0895) were obtained than those of water-level prediction results by univariate training.
Monitoring tidal dynamics is imperative to disaster management because it requires a high level of precision to avert possible dangers. Good knowledge of the physical drivers of tides is vital to achieving such a precision. The Taehwa River in Ulsan City, Korea experiences tidal currents in the estuary that drains into the East Sea. The contribution of wind to tide prediction is evaluated by comparing tidal predictions using harmonic analysis and three deep learning models. Harmonic analysis is conducted on hourly water level data from 2010–2021 using the commercial pytides toolbox to generate constituents and predict tidal elevations. Three deep learning models of long short-term memory (LSTM), gated recurrent unit (GRU), and bi-directional lstm (BiLSTM) are fitted to the water level and wind speed to evaluate wind and no-wind scenarios. Results show that Taehwa tides are categorized as semidiurnal tides based on a computed form ratio of 0.2714 in a 24-h tidal cycle. The highest tidal range of 0.60 m is recorded on full moon spring tide indicating the significant lunar pull. Wind effect improved tidal prediction NSE of optimal LSTM model from 0.67 to 0.90. Knowledge of contributing effect of wind will inform flood protection measures to enhance disaster preparedness.
Damage prevention from the local storms and typhoons in Korea, the development of a rainfall-runoff model reflecting local geological, meteorological and physical characteristics is necessary. The accuracy of the rainfall-runoff model is influenced by the various uncertainty factors that can occur in the modeling processes, including input data, model parameters, modeling simplification, and so on. Thus, the objectives of this study are (1) to estimate runoff for two rainfall events using Grid Rainfall-Runoff Model (GRM); (2) to quantify the uncertainty of the GRM model using the Generalized Likelihood Uncertainty Estimation (GLUE) method, and (3) to assess the uncertainty ranges of the GRM based on different likelihood functions. For this, two rainfall events were implemented to the GRM in the Cheongmicheon watershed, and informal likelihood functions (LNSE, LPBIAS, LRSR, and LLOG) based on the fitness indices (NSE, PBIAS, RSR, and Log-normal) were used for uncertainty analysis and quantification using GLUE method. As a result, the GRM parameters varied according to the different rainfall patterns even in the same watershed. In addition, among the GRM parameters, the CRC (Channel Roughness Coefficient) and CSHC (Correction factor for Soil Hydraulic Conductivity) characteristics are the most sensitive. Moreover, this study showed that the uncertainty range of the GRM model can be changed with the subjective selection of likelihood functions and thresholds. The GRM model is open source and has good accessibility. Especially, this open-source model allows various approaches to disaster prevention plans such as flood forecasting and flood insurance policies. In addition, if the parameter range of GRM is quantified and standardized at domestic watersheds, it is expected that the reliability of the rainfall-runoff simulation can be increased by the reduction of the uncertainty factors.
The methods for improving the accuracy of water level prediction were proposed in this study by selecting the Gated Recurrent Unit (GRU) model, which is effective for multivariate learning at the Paldang Bridge station in Han River, South Korea, where the water level fluctuates seasonally. The hydrological data (i.e., water level and flow rate) for Paldang Bridge station were entered into the GRU model; the data were provided by the Water Resources Management Information System (WAMIS), and the meteorological data for Seoul Meteorological Observatory and Yangpyeong Meteorological Observatory were provided through the Korea Meteorological Administration. Correlation analysis was used to select the training data for hydrological and meteorological data. Important input data affecting the daily water level (DWL) were daily flow rate (DFR), daily vapor pressure (DVP), daily dew point temperature (DDPT), and 1 h max precipitation (1HP), and were used as the multivariate learning data for water level prediction. However, the DWL prediction accuracy did not improve even if the meteorological data from a single meteorological observatory far from the DWL prediction point were used as the multivariate learning data. Therefore, in this study, methods for improving the predictive accuracy of DWL through multivariate learning that effectively utilize meteorological data from each meteorological observatory were presented. First, it was a method of arithmetically averaging meteorological data for two meteorological observatories and using it as the multivariate learning data for the GRU model. Second, a method was proposed to use the meteorological data of the two meteorological observatories as multivariate learning data by weighted averaging the distances from each meteorological observatory to the water level prediction point. Therefore, in this study, improved water level prediction results were obtained even if data with some correlation between meteorological data provided by two meteorological observatories located far from the water level prediction point were used.
Abstract. Availability of abundant water resources data is a great concern hindering adoption of deep learning techniques (DL) for disaster mitigation in developing countries. However, over the last three decades, a sizeable amount of DL publication in disaster management emanated mostly from developed countries with efficient data management systems. To understand the current state of DL adoption for solving water-related disaster problems in developing countries, an extensive bibliometric review coupled with a theory-based analysis of related research documents is conducted from 1993–2022 using Web of Science, Scopus, VOSviewer software and PRISMA model schema. Results revealed a ‘slightly’ increasing trend of DL-based water disaster publication in developing countries (tau = 0.35, p = 0.00045, Sen-slope, s = 0.00 at confidence level of 95 %), as opposed to the ‘significantly’ increasing trend globally (tau = 0.910, p = 1.72 e-12, Sen-slope, s = 2.52 at confidence level of 95 %). Also, pluvio-fluvial flooding is found to constitute 78 % most disaster prevalence and China is the only ‘high human development’ developing country with an impressive 51 % DL adoption rate, due to China’s increasing need for AI-based solutions to persistent multiyear severe water stress, climate change, environmental degradation, recurrent flood, and saltwater intrusion into estuaries. COVID-19 among other factors is identified as a driver of DL adoption. Further analysis indicates that developing countries will experience implementation delay based on their low Human Development Indices (HDI) because model deployment in solving disaster problems in real life scenarios is currently lacking due to high cost. Therefore, data augmentation, transfer learning, intensive research, deployment using cheap web-based servers and APIs are recommended to enhance disaster preparedness. Developing countries can explore these solutions to foster inclusion in global DL-based disaster mitigation approaches.
Recently, there have been many abnormal natural phenomena caused by climate change. Anthropogenic factors associated with insufficient water resource management can be another cause. Among natural causes, rainfall intensity and volume often induce flooding. Therefore, accurate rainfall estimation and prediction can prevent and mitigate damage caused by these hazards. Sadly, uncertainties often hinder accurate rainfall forecasting. This study investigates the uncertainty of the Korean rainfall ensemble prediction data and runoff analysis model in order to enhance reliability and improve prediction. The objectives of this study include: (i) evaluating the spatial characteristics and applicability of limited area ensemble prediction system (LENS) data; (ii) understanding uncertainty using parameter correction and generalized likelihood uncertainty estimation (GLUE) and grid-based rainfall-runoff model (GRM); (iii) evaluating models before and after LENS-GRM correction. In this study, data from the Wicheon Basin was used. The informal likelihood (R2, NSE, PBIAS) and formal likelihood (log-normal) were used to evaluate model applicability. The results confirmed that uncertainty of the behavioral model exists using the likelihood threshold when applying the runoff model to rainfall forecasting data. Accordingly, this method is expected to enable more reliable flood prediction by reducing the uncertainties of the rainfall ensemble data and the runoff model when selecting the behavioral model for the user’s uncertainty analysis. It also provides a basis for flood prediction studies that apply rainfall and geographical characteristics for rainfall-runoff uncertainty analysis.
Afan et al. (2022) Iraq Natural Hazards Linear and stratified DL models (unclear) 3 Bui et al. (2020) Vietnam Journal of Hydroinformatics Grasshopper, Grey Wolf and Social Spider Optimizations, DNN 4 Cai and Yu (2022) China Urban Climate Hybrid RNN (CNN, LSTM, Bi-LSTM + ARIMAX) 5 Chen et al. (2015) China Neural processing letter RNN with Elman network 6 Chen et al. (2021) Iran Geocarto International CNN, CNN-GWO, CNN-ICA 7 Chen et al. (2021) China Computer Networks CNN with different batch normalizations 8 Chhetri et al. (2020) Bhutan Remote Sensing (MDPI)
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.