Showing papers in "Journal of Hydrology in 2020"

TL;DR: Overall, this survey provides a new milestone in water resource engineering on the AI model implementation, innovation and transformation in surface WQ modelling with many formidable problems in different blossoming area and objectives to be achieved in the future.

TL;DR: Two popular variants of Recurrent Neural Network named Long Short-Term Memory and Gated Recurrent Unit networks were employed to develop new data-driven flood forecasting models, showing that GRU models perform equally well as LSTM models and GRU may be the preferred method in short term runoff predictions.

TL;DR: In this article, the authors review how satellite remote sensing information is utilized to assess and manage agriculture, an important component of eco-hydrology, and conclude the review with an outlook of challenges and recommendations.

TL;DR: It is concluded that the proposed LSTM-ED that translates and links the rainfall sequence with the runoff sequence can improve the reliability of flood forecasting and increase the interpretability of model internals.

TL;DR: In this paper, the prediction accuracy of new heuristic methods, optimally pruned extreme learning machine (OP-ELM), least square support vector machine (LSSVM), multivariate adaptive regression splines (MARS) and M5 model tree (M5Tree), is examined in modeling monthly streamflows using precipitation and temperature inputs.

TL;DR: In this article, a machine learning algorithm (MLA) and a deep learning algorithm(DLA) were used to develop groundwater potential maps using support vector regression (SVR) and convolution neural network (CNN) functions, respectively.

TL;DR: The most popular convolutional neural network (CNN) is introduced to assess flood susceptibility in Shangyou County, China and three data presentation methods are designed in the CNN architecture to fit the two proposed frameworks.

TL;DR: The results show the integrated AI with GWO outperform the standard AI methods and can make better forecasting during training and testing phases for the monthly inflow in all input cases, revealing the superiority of GWO meta-heuristic algorithm in improving the accuracy of the standardAI in forecasting the monthly Inflow.

TL;DR: Numerical results demonstrate that the Theory-guided Neural Network model achieves much better predictability, reliability, and generalizability than ANN models due to the physical/engineering constraints in the former.

TL;DR: In this paper, the authors compared the performance of two multi-criteria decision analysis (MCDA) models including analytical hierarchical process (AHP) and analytical network process (ANP) and two machine learning models including random forest (RF) and support vector machine (SVM).

TL;DR: Wang et al. as mentioned in this paper developed a hybrid model for monthly runoff prediction, where observed runoff is decomposed into several subcomponents via variational mode decomposition, and support vector machine models based on quantum-behaved particle swarm optimization are adopted to identify the input-output relationships hidden in each subcomponent.

TL;DR: It is suggested that proposed models are more robust than the classifiers, which were used for benchmarking and they are good alternatives for flood susceptibility mapping given the availability of dataset.

TL;DR: In this paper, a comprehensive comparison between two widely used rainfall datasets, the Global Precipitation Climatology Project (GPCP) and the ERA-Interim reanalysis, and the recently released ERA-5, which will replace ERA-interim as the main European Centre for Medium-Range Weather and Forecasting (ECMWF) reanalysis by 2020, is presented.

TL;DR: This study developed two hybrid models, based on long short-term memory network (LSTM), for monthly streamflow and rainfall forecasting, and indicated that LSTM was applicable for time series prediction, but WL STM and CLSTM were superior alternatives.

TL;DR: In this paper, a comprehensive review of the role of remote sensing in assessing water security is presented, focusing on water quality, quantity, and hydroclimatic extreme events that play an important role in improving water security.

TL;DR: This study introduced a novel methodology for probabilistic water quality forecasting conditional on point forecasts using a Multivariate Bayesian Uncertainty Processor to probabilistically model the relationship between the point forecasts made by a deep learning artificial neural network and their corresponding observed water quality.

TL;DR: In this article, the authors developed a new flexible hybrid runoff generation modeling framework, which is named as spatial combination computing models (SCCMs) for runoff generation SCCMs can determine the dominant runoff generation mode, either saturation excess or infiltration excess, on the sub-watershed level and then adopt one of the XAJ, Xinanjiang-Green Ampt (XAJG) and Green-Ampt (GA) runoff generation schemes to compute runoff generation at each subwatershed.

TL;DR: A single-model forecasting (SF) scheme that assesses the validation distribution during the training stage to adapt to the boundary effect was designed, and it is indicated that SF-VMD-LSTM is robust and efficient for forecasting highly nonstationary and nonlinear streamflow.

TL;DR: The findings suggest that the LSTM could be advance in daily streamflow forecasting and thus would be helpful to assist in strategy decisions in water resource management.

TL;DR: In this article, a virtual sample was introduced in NETPATH hydrogeochemical modeling to compute the net chemical reactions in the lake water and showed that the lake evolved to be saline during 2004-2012 (stage I) and then tended to be fresh during 2013-2014 (stage II).

TL;DR: In this article, the authors proposed a hybrid CEEMD-RF-KRR model for forecasting rainfall at Gilgit, Muzaffarabad, and Parachinar in Pakistan at monthly time scale.

TL;DR: An overview of the formation and effects of acid mine drainage can be found in this paper, where the authors identify critical research gaps and explore the associated challenges and opportunities for environmental scientists and researchers.

TL;DR: Overall, the TCN and LSTM models performed markedly better than temperature-based empirical models beyond the study areas, and when radiation-based or humidity-based features were available, all of the proposed DL and CML models outperformed radiation- Based empirical equations beyond theStudy areas in which they were trained.

TL;DR: It can be inferred that XGBoost is applicable for streamflow forecasting, and in general, performs better than SVM; the cluster analysis-based modular model is helpful in improving accuracy and capturing the complicated patterns of hydrological process.

TL;DR: In this paper, the authors report on 23 gridded precipitation datasets (P-datasets) reliability across West Africa through direct comparisons with rain gauges measurement at the daily and monthly time scales over a 4-year period (2000-2003).

TL;DR: Wang et al. as discussed by the authors applied cross wavelet analysis to reveal the detailed associations between the Normalized Difference Vegetation Index (NDVI) and precipitation/air temperature, and a Support Vector Machine (SVM)-based simulation model was introduced to quantify the effects of climate change and human activities on vegetation cover dynamics.

TL;DR: In this paper, the authors combined the strengths of the Wavelet transformation, Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN) to test a new method of a hybrid model for their ability to accurately predict future droughts.

TL;DR: In this paper, the authors evaluated GPM IMERGv05, TMPA 3B42V7, ERA-Interim, and ERA5 precipitation products using 256 ground-based gauge stations between 2014 and 2018 over Turkey known to have complex topography and varying climate.

TL;DR: An innovative modelling approach based on a deep convolutional neural network (CNN) method for rapid prediction of fluvial flood inundation and shows that the CNN model outperforms SVR by a large margin.

TL;DR: In this article, a 3D fluid-solid coupled finite element model (FEM) is used to analyze the impact of leakage in the waterproof curtain during excavation dewatering, and the results demonstrate that the leakage rate, leakage volume, groundwater drawdown, and ground settlement are closely related to the hydraulic conductivity of the leakage point.