Input determination for neural network models in water resources applications. Part 1—background and methodology

By Gavin J. Bowden, Graeme C. Dandy, Holger R. Maier. 2005

550 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Environmental Engineering, Water Science and Technology

View Paper: https://www.semanticscholar.org/paper/9e257a6cf55d0a51f67105019cc118f3bc64bd88

How researchers see this paper

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

In Artificial Intelligence

In Environmental Engineering

In Water Science and Technology

Citations in the corpus

Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application (2008, methodology): “The issue of dividing data into training, testing, and validation subsets in ANN models development was addressed by Bowden et al. (2002). This issue is one of the most important in the development of ANN models.”
Quantification of the predictive uncertainty of artificial neural network based river flow forecast models (2012, methodology): “One of the most important steps in the ANN hydrologic model development process is the determination of significant input variables (Bowden et al. 2004a, b).”
Tree‐based iterative input variable selection for hydrological modeling (2013, methodology): “Bowden et al. [2005a] improve the PMI criterion by Sharma [2000] using artificial neural networks for salinity prediction in the River Murray, South Australia [Bowden et al., 2005b].”
Artificial neural network simulation of hourly groundwater levels in a coastal aquifer system of the Venice lagoon (2012, background): “However, more systematic approaches for input and lag selection have been proposed in the literature (Bowden et al., 2005), and should be employed especially when dealing with higher dimensional input domains.”
Data-driven modelling: some past experiences and new approaches (2008, methodology): “An expert can contribute to building a DDM by bringing in the knowledge about the system under question (like is done in the dimensionally aware GP considered above), determining the model structure (as in the M5flex algorithm by Solomatine & Siek (2004)), in performing advanced analysis to select t”
Protocol for developing ANN models and its application to the assessment of the quality of the ANN model development process in drinking water quality modelling (2014, methodology): “Dimensionality reduction can be achieved by using principal component analysis (with rotation of inputs) (Cho et al., 2011), or by clustering the input or inputeoutput space, as is the case when using clustering analysis and self-organizing maps (Bowden et al., 2005a, 2005b).”
A Brief Review of Random Forests for Water Scientists and Practitioners and Their Recent History in Water Resources (2019, methodology): “[21] Artificial neural networks Rainfall-runoff modeling and flood forecasting Preprocessing, variable selection, training, testing, modeling practices [22,23] Artificial neural networks Water resources applications Methods for variable selection”
A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists (2017, background): “Its applications extend to rainfall runoff modeling, streamflow, groundwater management, water quality, stream salinity, rainfall estimation, ocean wave heights, and real-time forecasting (Bowden et al., 2005; Dawson & Wilby, 2001; Deo & Naidu, 1998; Govindaraju & Rao, 2000; Gupta et al., 2000; Maie”
A hybrid support vector regression framework for streamflow forecast (2019, methodology): “An important step of ANN and SVR models is to determine the significant input variables (Bowden et al., 2005a,b), some of which are correlated, noisy, and some input variables are less informative (Bowden et al., 2005a; Chen et al., 2013).”
Evolutionary algorithms and other metaheuristics in water resources: Current status, research challenges and future directions (2014, methodology): “Alternatively, the use of techniques for the selection of inputs to data-driven models (Bowden et al., 2005a, 2005b; Fernando et al., 2009; Galelli and Castelletti, 2013; Galelli et al., 2014; May et al., 2008a; May et al., 2008b) might be worthwhile.”
Prediction of rainfall time series using modular soft computingmethods (2013, methodology): “Input 25 selection is one of the important tasks in the identification but is very subjective although 26 many methods have been documented (Bowden et al., 2005).”