Showing papers in "Journal of Hydrology in 2018"

TL;DR: Wang et al. as mentioned in this paper proposed a new time series model based on Long Short-Term Memory (LSTM) as an alternative to computationally expensive physical models, which is composed of an LSTM layer with another fully connected layer on top of it.

TL;DR: In this paper, two advanced high resolution multi-satellite precipitation products namely, Integrated Multi-satellitE Retrievals for GPM (IMERG) and Global Satellite Mapping of Precipitation (GSMaP) version 6 are released.

TL;DR: Three AI models are employed to simulate reservoir operation at monthly, daily, and hourly time scales, using approximately 30 years of historical reservoir operation records to summarize the influence of the parameter settings on model performance and to explore the applicability of the LSTM model to reservoir operation simulation.

TL;DR: An integrated methodology is proposed by incorporating urban flood inundation model, improved entropy weight method and k-means cluster algorithm to evaluate urban flood risk to demonstrate that the proposed approach is feasible and exhibits the most reasonable classification result.

TL;DR: In this paper, a comparison of six high-resolution, daily and monthly gridded precipitation datasets over the Western United States was conducted, and the authors found that the greatest absolute differences among datasets occur in high-elevation areas and in the maritime mountain ranges of the Western USA, while the greatest percent differences relative to annual total precipitation occur in arid and rain shadowed areas.

TL;DR: Through a comparison of four different neural networks, namely multilayer perceptron (MLP), wavelet neural network (WNN), long short-term memory (LSTM) and gated recurrent unit (GRU), the LSTM and GRU present superior capabilities for multi-step-ahead time series prediction.

TL;DR: In this article, a three-step satellite and gauge precipitation merging method was formulated to improve the spatial resolution and quality of satellite precipitation, and eight algorithms, a combination of two geographically weighted regression methods and four weighting functions, were developed to merge CMORPH (CPC MORPHing technique) precipitation with station observations on a daily scale in the Ziwuhe Basin of China.

TL;DR: It was demonstrated that separating streamflow into different components such as base flow and surface flow can be useful for improving simulation and forecasting capabilities of machine learning models.

TL;DR: In this paper, the most common satellite precipitation products (SPPs) during the Tropical Rainfall Measuring Mission (TRMM) and Global Precipitation Mission (GPM) eras are reviewed.

TL;DR: The results show that the AEEMD-ANN model can improve forecast accuracy in flood seasons, but it is not as good as ANN, adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM) and seasonal first-order autoregressive (SAR) models in dry seasons.

TL;DR: In this paper, the authors used nonlinear autoregressive networks with exogenous inputs (NARX) to obtain groundwater level forecasts for several wells in southwest Germany, and the results are promising and indicate an outstanding suitability of NARX for groundwater level predictions with such a small set of inputs in all three aquifer types.

TL;DR: In this article, the authors suggest that future research should focus on better synthesising past research on soil compaction and runoff, tailored field experiments to obtain a mechanistic understanding of the coupled mechanical and hydraulic processes, new mapping methods of soil contaction that combine mechanical and remote sensing approaches, and an effort to bridge all disciplines relevant to soil compraction effects on floods.

TL;DR: In this article, an evaluation of stand-alone data mining models (i.e., reduced error pruning tree (REPT), M5P and instance-based learning (IBK)) and hybrid models, (e.g., bagging-M5P, random committee-REPT (RC)-REPT) and random subspace-rePT (RS-REpt)) for predicting suspended sediment loads (SSL) resulting from glacial melting at an Andean catchment in Chile has been conducted in this article.

TL;DR: In this paper, the authors compare two low-complexity tools, AutoRoute and HAND, with a two-dimensional hydrodynamic model (HEC-RAS 2D).

TL;DR: In this article, three types of artificial intelligence techniques, least square support vector machine (LSSVM), multivariate adaptive regression splines (MARS) and M5 model tree (M5T), are applied for modeling daily dissolved oxygen (DO) concentration using several water quality variables as inputs.

TL;DR: In this article, a critical question for understanding contemporary and future responses to environment change in high-latitude inland waters is addressed. But it is not addressed in this paper, nor in this article.

TL;DR: In this article, a holistic analysis of long-term records of water discharge, sediment transport, riverbed morphology and estuarine hydrology is used to quantify spatial and temporal variations in fluvial sediment fluxes along the Changjiang River.

TL;DR: This research investigates the capability and robustness of a novel hybrid model, namely the logistic model tree (LMT), and compares it with state-of-the-art models such as the support vector machine and C4.5 models that locate potential zones for groundwater springs.

TL;DR: It is concluded that WDDFF is a useful tool for forecasting real-world hydrological and water resources processes that overcomes the limitations of many earlier wavelet-based forecasting methods and should be explored further for forecasting different processes such as streamflow, rainfall, evaporation, etc.

TL;DR: In this paper, a random forest (RF)-based downscaling approach was proposed to disaggregate the Soil Moisture Active and Passive (SMAP) SSM product with the synergistic use of the Optical/Thermal infrared (TIR) observations from the MODIS onboard the Terra and Aqua satellites.

TL;DR: In this article, the role of hydraulic fracture on the pressure transient behavior of a vertical well producing from a bounded (or finite) dual-porosity formation was studied. And the authors used a combination of Laplace transform (LT) and the finite Fourier cosine transform (FFCT) to solve the diffusivity equation.

TL;DR: In this paper, an urban pluvial flood model, RUFIDAM, was developed using GIS technology with the intention of rapidly estimating flood extent, depth and its associated damage.

TL;DR: In this article, a comparative analysis on the quality of the TRMM Multi-satellite Precipitation Analysis 3B42V7 and the Integrated Multi-Satellite Retrievals for GPM (IMERG) Final Run version 05 precipitation products and their hydrological utilities in the Yellow River source region (YRSR), a mountainous Alpine region in northwestern China, from April 2014 to December 2016, was conducted.

TL;DR: In this paper, the authors investigated the temporal variation (mainly long-term) of uncertainty related to the choice of a GCM in predicting climate change impacts on hydrology by using multi-GCMs over multiple continuous future periods.

TL;DR: In this article, a sample of 142 catchments that have a documented increase in urban areas over the hydrometeorological record period in the United States was collected and the changes in river flow regimes due to urban spread were differentiated from climate variability using the GR4J conceptual hydrological model.

TL;DR: In this article, the authors proposed a trend analysis method based on innovative trend analysis (ITA) to identify categorical trends in rainfall, runoff and temperature time series, which is one of the main concerns in this paper.

TL;DR: A comprehensive review on the recent progress and applications of GP in the WRE fields is presented and discussions of the optimum selection of GP parameters and likely future research directions in theWRE are suggested.

TL;DR: In this paper, the authors examined whether the incorporation of remotely sensed and spatially distributed datasets can improve the overall performance of the hydrological model and found that the performance of this model was improved using both calibration techniques by achieving Nash-Sutcliffe efficiency (NSE) values < 0.5 (0.73-0.85).

TL;DR: In this paper, a coupled optimization-simulation model was developed by linking the U.S. EPA Stormwater Management Model (SWMM) to the Borg Multiobjective Evolutionary Algorithm (Borg MOEA).

TL;DR: In this article, a comprehensive overview of its hydrological regime changes by analyzing long time series of river discharges and sediment loads data at multiple gauge stations in the basin downstream of Three Gorges Dam (TGD) is provided.