American Geophysical Union Become an AGU Member
Subscribe to AGU Journals		 AGU Home AGU Publications

Read Full Article (file size: 761078 bytes)    Cited by

WATER RESOURCES RESEARCH, VOL. 41, W08422, doi:10.1029/2004WR003577, 2005

Automatic rainfall recharge model induction by evolutionary computational intelligence

Yoon-Seok Timothy Hong

Institute of Geological and Nuclear Sciences, Wairakei Research Centre, Taupo, New Zealand


Paul A. White

Institute of Geological and Nuclear Sciences, Wairakei Research Centre, Taupo, New Zealand


David M. Scott

Environment Canterbury, Christchurch, New Zealand


Abstract

Genetic programming (GP) is used to develop models of rainfall recharge from observations of rainfall recharge and rainfall, calculated potential evapotranspiration (PET) and soil profile available water (PAW) at four sites over a 4 year period in Canterbury, New Zealand. This work demonstrates that the automatic model induction method is a useful development in modeling rainfall recharge. The five best performing models evolved by genetic programming show a highly nonlinear relationship between rainfall recharge and the independent variables. These models are dominated by a positive correlation with rainfall, a negative correlation with the square of PET, and a negative correlation with PAW. The best performing GP models are more reliable than a soil water balance model at predicting rainfall recharge when rainfall recharge is observed in the late spring, summer, and early autumn periods. The “best” GP model provides estimates of cumulative sums of rainfall recharge that are closer than a soil water balance model to observations at all four sites.

Received 17 August 2004; accepted 13 May 2005; published 26 August 2005.

Keywords: automatic rainfall recharge model induction; Canterbury Plains; evolutionary computational intelligence; genetic programming; New Zealand; soil moisture balance model.

Index Terms: 0555 Computational Geophysics: Neural networks, fuzzy logic, machine learning; 1805 Hydrology: Computational hydrology; 1816 Hydrology: Estimation and forecasting; 1829 Hydrology: Groundwater hydrology; 1847 Hydrology: Modeling.

Read Full Article (file size: 761078 bytes)    Cited by

Citation: Hong, Y.-S. T., P. A. White, and D. M. Scott (2005), Automatic rainfall recharge model induction by evolutionary computational intelligence, Water Resour. Res., 41, W08422, doi:10.1029/2004WR003577.