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.
%0 Journal Article
%1 Hong:2005:WRR
%A Hong, Yoon-Seok Timothy
%A White, Paul A.
%A Scott, David M.
%D 2005
%J Water Resources Research
%K 0555 1805 1816 1829 1847 Canterbury Computational Estimation Geophysics: Groundwater Hydrology: Modelling Neural New Plains, Zealand, algorithms, and automatic balance computational evolutionary forecasting; fuzzy genetic hydrology; induction, intelligence, learning; logic, machine model model, moisture networks, programming, rainfall recharge soil
%N W08422
%R doi:10.1029/2004WR003577
%T Automatic rainfall recharge model induction by
evolutionary computational intelligence
%U http://www.agu.org/pubs/crossref/2005/2004WR003577.shtml
%V 41
%X 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.
@article{Hong:2005:WRR,
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.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Hong, Yoon-Seok Timothy and White, Paul A. and Scott, David M.},
biburl = {https://www.bibsonomy.org/bibtex/2906f90878ca74591f0a1e7fe79a8bb37/brazovayeye},
doi = {doi:10.1029/2004WR003577},
email = {T.Hong@gns.cri.nz},
interhash = {5ba84f7ed0b6859ba5815c0a29a537ee},
intrahash = {906f90878ca74591f0a1e7fe79a8bb37},
journal = {Water Resources Research},
keywords = {0555 1805 1816 1829 1847 Canterbury Computational Estimation Geophysics: Groundwater Hydrology: Modelling Neural New Plains, Zealand, algorithms, and automatic balance computational evolutionary forecasting; fuzzy genetic hydrology; induction, intelligence, learning; logic, machine model model, moisture networks, programming, rainfall recharge soil},
number = {W08422},
timestamp = {2008-06-19T17:41:42.000+0200},
title = {Automatic rainfall recharge model induction by
evolutionary computational intelligence},
url = {http://www.agu.org/pubs/crossref/2005/2004WR003577.shtml},
volume = 41,
year = 2005
}