Optimal division of data for neural network models in water resources applications

By Gavin J. Bowden, Holger R. Maier, Graeme C. Dandy. 2002

324 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/2276df6aef7814cbef250bfc3477a80ae7da3c65

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

1. Holger R. Maier
2. Graeme C. Dandy
3. Avi Ostfeld
4. Aman Mohammad Kalteh
5. Wenyan Wu
6. Peder Hjorth
7. Ronny Berndtsson
8. Dimitri P. Solomatine

In Electrical and Electronic Engineering

1. Holger R. Maier
2. Wenyan Wu
3. Graeme C. Dandy
4. Aman Mohammad Kalteh
5. Peder Hjorth
6. Ronny Berndtsson
7. Sheen Mclean Cabaneros
8. John Kaiser Calautit

In Environmental Engineering

1. Holger R. Maier
2. Graeme C. Dandy
3. Wenyan Wu
4. Avi Ostfeld
5. Sheen Mclean Cabaneros
6. John Kaiser Calautit
7. Ben Richard Hughes
8. Aman Mohammad Kalteh

Citations in the corpus

• Data-driven modelling: some past experiences and new approaches (2008, methodology): “This can be achieved by careful selection of examples for each dataset to ensure such statistical similarity, by random sampling data from the whole dataset, or employing an optimisation procedure resulting in sets with predefined properties (Bowden et al. 2002).”
• HydroTest: A web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts (2007, background): “It records as a ratio the level of overall agreement between the observed and modelled datasets and is often expressed in percentage terms; the mean absolute percent error (MAPE; Armstrong and Collopy, 1992; Maier and Dandy, 1996; Bowden et al., 2002).”
• 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): “Data splitting methods based on optimization (Bowden et al., 2002), such as genetic algorithms, are also classified as supervised methods (Maier et al., 2010).”
• A review of artificial neural network models for ambient air pollution prediction (2019, methodology): “Multivariate methods include regression-based imputation, nearest neighbour interpolation, SOM and MLP. Additionally, other modellers address the issue of missing data by deletion, in which predictors with a large fraction of missing values are left out.”
• Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application (2008, methodology): “Bowden et al. (2002) presented two methods based on a genetic algorithm and an SOM which were able to divide the available data into subsets with common statistical properties.”