Special Issue "Integration of Advanced Soft Computing Techniques in Hydrological Predictions"

A special issue of Atmosphere (ISSN 2073-4433). This special issue belongs to the section "Biosphere/Hydrosphere/Land - Atmosphere Interactions".

Deadline for manuscript submissions: 15 October 2018

Special Issue Editor

Guest Editor
Prof. Dr. Kwok-wing Chau

Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Hunghom, Kowloon, Hong Kong
Website | E-Mail
Interests: artificial intelligence; hydrology; soft computing; water quality; meta-heuristic algorithm; hydrodynamic; rainfall; runoff

Special Issue Information

Dear Colleagues,

Extreme weather events, occurring more frequently in recent years possibly due to climate change, result in enormous economic and human losses globally every year. It is important to have the capability to predict accurately both the occurrence time and magnitude of peak flow in advance of an impending extreme weather event. The integration of soft computing techniques in hydrological predictions is a growing field of endeavor in water resources engineering and management. It can be employed to optimally calibrate data-driven hydrological models so as to enhance the forecasting accuracy. This special edition of the Atmosphere journal is tailored to fill the existing gap by including papers on the advancement in the contemporary use of soft computing techniques in hydrological modelling. The information and analyses are intended to contribute to the development and implementation of effective hydrological prediction and thus appropriate precautionary measures.

Prof. Kwok Wing Chau
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Atmosphere is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • hydrological
  • prediction
  • modelling
  • soft computing
  • meta-heuristic
  • data-driven

Published Papers (2 papers)

View options order results:
result details:
Displaying articles 1-2
Export citation of selected articles as:

Research

Open AccessArticle Machine Learning Models Coupled with Variational Mode Decomposition: A New Approach for Modeling Daily Rainfall-Runoff
Atmosphere 2018, 9(7), 251; https://doi.org/10.3390/atmos9070251
Received: 24 May 2018 / Revised: 2 July 2018 / Accepted: 3 July 2018 / Published: 5 July 2018
PDF Full-text (4336 KB) | HTML Full-text | XML Full-text
Abstract
Accurate modeling for nonlinear and nonstationary rainfall-runoff processes is essential for performing hydrologic practices effectively. This paper proposes two hybrid machine learning models (MLMs) coupled with variational mode decomposition (VMD) to enhance the accuracy for daily rainfall-runoff modeling. These hybrid MLMs consist of
[...] Read more.
Accurate modeling for nonlinear and nonstationary rainfall-runoff processes is essential for performing hydrologic practices effectively. This paper proposes two hybrid machine learning models (MLMs) coupled with variational mode decomposition (VMD) to enhance the accuracy for daily rainfall-runoff modeling. These hybrid MLMs consist of VMD-based extreme learning machine (VMD-ELM) and VMD-based least squares support vector regression (VMD-LSSVR). The VMD is employed to decompose original input and target time series into sub-time series called intrinsic mode functions (IMFs). The ELM and LSSVR models are selected for developing daily rainfall-runoff models utilizing the IMFs as inputs. The performances of VMD-ELM and VMD-LSSVR models are evaluated utilizing efficiency and effectiveness indices. Their performances are also compared with those of VMD-based artificial neural network (VMD-ANN), discrete wavelet transform (DWT)-based MLMs (DWT-ELM, DWT-LSSVR, and DWT-ANN) and single MLMs (ELM, LSSVR, and ANN). As a result, the VMD-based MLMs provide better accuracy compared with the single MLMs and yield slightly better performance than the DWT-based MLMs. Among all models, the VMD-ELM and VMD-LSSVR models achieve the best performance in daily rainfall-runoff modeling with respect to efficiency and effectiveness. Therefore, the VMD-ELM and VMD-LSSVR models can be an alternative tool for reliable and accurate daily rainfall-runoff modeling. Full article
Figures

Figure 1

Open AccessArticle Analysis of the Influence of Rainfall Spatial Uncertainty on Hydrological Simulations Using the Bootstrap Method
Atmosphere 2018, 9(2), 71; https://doi.org/10.3390/atmos9020071
Received: 18 January 2018 / Revised: 9 February 2018 / Accepted: 10 February 2018 / Published: 15 February 2018
PDF Full-text (4412 KB) | HTML Full-text | XML Full-text
Abstract
Rainfall stations of a certain number and spatial distribution supply sampling records of rainfall processes in a river basin. Uncertainty may be introduced when the station records are spatially interpolated for the purpose of hydrological simulations. This study adopts a bootstrap method to
[...] Read more.
Rainfall stations of a certain number and spatial distribution supply sampling records of rainfall processes in a river basin. Uncertainty may be introduced when the station records are spatially interpolated for the purpose of hydrological simulations. This study adopts a bootstrap method to quantitatively estimate the uncertainty of areal rainfall estimates and its effects on hydrological simulations. The observed rainfall records are first analyzed using clustering and correlation methods and possible average basin rainfall amounts are calculated with a bootstrap method using various combinations of rainfall station subsets. Then, the uncertainty of simulated runoff, which is propagated through a hydrological model from the spatial uncertainty of rainfall estimates, is analyzed with the bootstrapped rainfall inputs. By comparing the uncertainties of rainfall and runoff, the responses of the hydrological simulation to the rainfall spatial uncertainty are discussed. Analyses are primarily performed for three rainfall events in the upstream of the Qingjian River basin, a sub-basin of the middle Yellow River; moreover, one rainfall event in the Longxi River basin is selected for the analysis of the areal representation of rainfall stations. Using the Digital Yellow River Integrated Model, the results show that the uncertainty of rainfall estimates derived from rainfall station network has a direct influence on model simulation, which can be conducive to better understand of rainfall spatial characteristic. The proposed method can be a guide to quantify an approximate range of simulated error caused by the spatial uncertainty of rainfall input and the quantified relationship between rainfall input and simulation performance can provide useful information about rainfall station network management in river basins. Full article
Figures

Figure 1

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Tentative Title: Performance evaluation and improvement in regional applicability of Satellite Precipitation products in a Transboundary River Basin
Authors: Rana Zain Nabi Khan1, Ijaz Ahmad1, Muhammad Tayyab2, Xiaohua Dong2,3*, Muhammad Naveed Anjum4
Affiliations:
1   Centre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore 54890, Pakistan
2   College of Hydraulic and Environmental Engineering, China Three Gorges University, Yichang 443002, China
3   Hubei Provincial Collaborative Innovation Center for Water Security, Wuhan, 430070, China
4   State Key Laboratory of Cryospheric Science, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, PR China
2,3*Corresponding author: xhdong@ctgu.edu.cn; Telephone number: +86 717 6394339
Abstract:
This study aims to evaluate the performance and the hydrological utility of various satellite products such as, integrated multi-satellite retrievals for GPM (IMERG V04A, IMERG V03D), the tropical rainfall measuring mission (TRMM-3B42) ­­­­and the climate prediction center Morphing technique (CMORPH-CRT) against the gauge precipitation estimates at multiple spatiotemporal scales over a transboundary river between India-Pakistan named Degh Nullah. In this transboundary basin, hydrological and metrological data availability, sharing and acquisition is a major issue due to lack of infrastructure/measuring devices and political conflicts. However, Satellite data maybe one of the solutions to address this problem. A critical evaluation of the newly released precipitation data set is very important for both the end users and data developers. Meanwhile, the evaluation may provide a benchmark for the product’s continued development and future improvement. To evaluate these products, statistical indicator metrics including Mean Error (ME), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Correlation Coefficient (CC) are employed on daily, monthly, and seasonal as well as on annual timescales. After developing correlation, a new algorithm being developed by using Simultaneous compromise constraint technique which has the ability to ensemble different products by making a compromise? As the latest generation SPP built on the legacy of TRMM, the GPM IMERG products provide a wider-covering, finer spatial-temporal resolution, more accurate near-real-time and post-real-time precipitation estimation for the hydrological and metrological applications.
Keywords: Precipitation; Global Precipitation Measurement Mission; Tropical Rainfall Measurement Mission; Transboundary river basin; Atmosphere

Tentative Title: Application of Integrated Artificial Neural Networks at Upper Indus Basin, Pakistan
Authors: Muhammad Tayyab1,3, Ijaz Ahmad4, Na Sun3, Xiaohua Dong1,2*
Affiliations:
1   College of Hydraulic and Environmental Engineering, China Three Gorges University, Yichang 443002, China
2   Hubei Provincial Collaborative Innovation Center for Water Security, Wuhan, 430070, China
3  School of Hydropower and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
4  Centre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore 54890, Pakistan
1,2*Corresponding author: xhdong@ctgu.edu.cn
Abstract:
Consistent streamflow forecasts play a fundamental part in flood risk mitigation. Population increase and water cycle intensification are extending not only globally, but also Pakistan’s water resources. The frequency of floods has increased in the last few decades in the country, which emphasizes the importance of the fact that efficient practices needs to adopted for various aspects of water resources management such as reservoir scheduling, water sustainability and water supply. Purpose of this study is to develop a novel hybrid model for streamflow forecasting and validates its efficiency at upper Indus basin (UIB), Pakistan. The hybrid models are design by incorporating artificial intelligence (AI) models which includes Feedforward backpropagation (FFBP) and Radial basis function (RBF) with decomposition methods which includes discrete wavelet transform (DWT) and ensemble empirical mode decomposition (EEMD). On basis of autocorrelation function and the cross-correlation function of streamflow, precipitation and temperature inputs are selected all developed models. Data have been analyzed by comparing the simulation outputs of the models with the correlation coefficient (R) root mean square errors, mean absolute errors, mean absolute percentage error and Nash–Sutcliffe Efficiency. The proposed hybrid models have been applied to monthly streamflow observations from three hydrological stations and eight meteorological stations in the UIB. The results show that prediction accuracy of the decomposition based models is usually better than those of AI-based models. Among DWT and EEMD based hybrid model, EEMD has performed significantly well as compared to all other hybrid and individual AI models. The detailed comparative analysis showed that the RBFNN integrated with EEMD has better forecasting capabilities as compared to other developed models and EEMD-RBF can capture the nonlinear characteristics of the streamflow time series and thus provides more accurate forecasting results.
Keywords: Artificial intelligence (AI), Feedforward backpropagation (FFBP), Radial basis function (RBF), Discrete wavelet transform (DWT), Ensemble empirical mode decomposition (EEMD)

Tentative Title: Typhoon rainfall forecasting by means of ensemble numerical weather predictions with a GA-based integration strategy
Abstract:
Typhoon rainfall is one of the most important water resources in Taiwan. But heavy typhoon rainfall often leads to serious disasters, such as flood and inundation, and then results in loss of lives and property. Hence, accurate forecasts of typhoon rainfall are always required as an important information for water resources management and typhoon rainfall-induced disaster warning. In this study, a methodology is proposed for providing the forecasts of 24 h cumulative rainfall during typhoons. Firstly, ensemble typhoon rainfall forecasts are obtained from an ensemble numerical weather prediction (NWP) system in Taiwan. Then, an evolutionary algorithm, i.e. genetic algorithm (GA), is adopted to real-time integrate these ensemble forecasts for yielding more accurate results. That is, through the GA-based integration strategy, ensemble forecasts are well combined by optimal weights. Actual application is conducted to verify the performance of the typhoon rainfall forecasts resulting from ensemble NWP forecasts with a GA-based integration strategy. The results indicate that the forecasts from the proposed methodology are in good agreement with observations. Besides, as compared to the results by simple averaging all ensemble forecasts, the results from the GA-based strategy are more accurate, especially for extreme values. In conclusion, accurate typhoon rainfall forecasts are obtained by the proposed methodology. Accurate rainfall forecasts are expected to be useful for disaster warning and water resources management during typhoons.

Tentative Title: Statistical model for predicting river volume flux into the ocean
Abstract:
The operational numerical regional ocean model needs the information of predicted river flux. Traditional conceptual hydrological models involve many parameters, and the determination of parameters is difficult, which limits their application in the regional ocean model. This study took Jiulong river as an example and use regression model to predict river runoff. The hourly numerical precipitation data from weather research and forecasting model, the measured Jiulong river runoff data of 2010-2016 were collected to develop the regression model. Considering the rainfall-runoff delayed effect and the hourly temporal resolution, we tried to find the most effective way of determining weighting coefficient, where we tested a variety of precipitation weighting methods. In terms of handling multi-collinearity, we tested the principal component regression, ridge regression, as well as the method of combining explanatory variables. Through the comparison of these three methods, we choose the most suitable one, i.e., the method of combining explanatory variables, which is more efficient and accurate.

Back to Top