Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions

By Holger R. Maier, Ashu Jain, Graeme C. Dandy, K. Sudheer. Environmental Modelling & Software, 2010

857 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Environmental Engineering, Water Science and Technology

View Paper: https://www.semanticscholar.org/paper/b0e4a2cba183bceaf514de1dc5633949e460c41b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

In Environmental Engineering

In Water Science and Technology

Citations in the corpus

A review of artificial neural network models for ambient air pollution prediction (2019, methodology): “In order to achieve this, Bayesian methods are commonly used (Bishop, 1995; Maier et al., 2010).”
Secchi Disk Depth Estimation from Water Quality Parameters: Artificial Neural Network versus Multiple Linear Regression Models? (2016, methodology): “Contrary to empirical models, in which the physical interpretations of the problem in question can help considerably in the selection of the relevant input and are often influential in the determination of the final topological structure of the models, this it is not the case in ANN models: prior kn”
Quantification of the predictive uncertainty of artificial neural network based river flow forecast models (2012, background): “This interest has been motivated by the complex nature of hydrological systems and the ability of ANNs to model nonlinear relationships (Maier et al. 2010).”
Bootstrap rank‐ordered conditional mutual information (broCMI): A nonlinear input variable selection method for water resources modeling (2016, methodology): “We also have an interest in applying the bootstrap rankordering approach to the standard partial mutual information selection algorithm to assess its added value as it is currently the most popular nonlinear input variable selection method in water resources modeling [Maier et al., 2010].”
Flood Prediction Using Machine Learning Models: Literature Review (2018, neutral): “typhoon rainfall, and daily flows [59].”
Artificial neural network simulation of hourly groundwater levels in a coastal aquifer system of the Venice lagoon (2012, methodology): “A detailed review of ANNs applications for modelling water resource variables can be found in Maier and Dandy (2000) and Maier et al. (2010).”
Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms (2016, positive): “…the advantages of the work compared with other investigations in different domains of hydrology without accurate evaluations of peak points (Ju et al., 2009; Maier et al., 2010; Valipour and Montazar, 2012a, 2012b; Valipour, 2014d, 2014e, 2015d, 2015e, 2015f, 2015g, 2015h; Kan et al., 2015).”
Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada (2012, background): “Two very recent publications [ Solomatine and Ostfeld , 2008; Maier et al. , 2010] on the current status and future directions of the use of data-based modeling in the area of water resources variable forecasting highlighted several critical issues that need to be explored in greater detail,…”
A Review of the Artificial Neural Network Models for Water Quality Prediction (2020, methodology): “The hybrid models in this review are three classes: model-intensive, technique-intensive, and data-intensive [27].”
A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning (2020, methodology): “Although robust ANN model development approaches are still needed (Maier et al., 2010), studies have shown that ANNs can predict the runoff more accurately than can the classical regression models (Mosavi et al., 2018; Riad et al., 2004).”
The Future of Sensitivity Analysis: An essential discipline for systems modeling and policy support (2020, positive): “…providing insight into and extracting knowledge from ML models can be improved significantly by using state-of-the-art model development practices (Maier et al., 2010; Wu et al., 2014) that improve parameter identifiability (Guillaume et al., 2019), such as input variable selection (see Galelli…”