Neuro-Drip: Estimation of subsurface wetting patterns for drip irrigation using neural networks

A. C. Hinnell, N. Lazarovitch, A. Furman, Mary M Poulton, A. W. Warrick

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Design of efficient drip irrigation systems requires information about the subsurface water distribution of added water during and after infiltration. Further, this information should be readily accessible to design engineers and practitioners. Neuro-Drip combines an artificial neural network (ANN) with a statistical description of the spatio-temporal distribution of the added water from a single drip emitter to provide easily accessible, rapid illustrations of the spatial and temporal subsurface wetting patterns. In this approach, the ANN is an approximator of a flow system. The ANN is trained using close to 1,000 numerical simulations of infiltration. Moment analysis is used to encapsulate the spatial distribution of water content. In practice, the user provides soil hydraulic properties and discharge rate; the ANN is then used to estimate the depth to the center of mass of the added water, and the vertical and radial spreading around the center of mass; finally, this statistical description of the added water is used to visualize the fate of the added water during and after the infiltration event.

Original languageEnglish (US)
Pages (from-to)535-544
Number of pages10
JournalIrrigation Science
Volume28
Issue number6
DOIs
StatePublished - 2010

Fingerprint

drip irrigation
microirrigation
wetting
neural networks
artificial neural network
infiltration (hydrology)
infiltration
water
emitters (equipment)
soil hydraulic properties
water distribution
irrigation system
hydraulic property
irrigation systems
engineers
temporal distribution
water content
spatial distribution
simulation
soil

ASJC Scopus subject areas

  • Agronomy and Crop Science
  • Water Science and Technology
  • Soil Science

Cite this

Neuro-Drip : Estimation of subsurface wetting patterns for drip irrigation using neural networks. / Hinnell, A. C.; Lazarovitch, N.; Furman, A.; Poulton, Mary M; Warrick, A. W.

In: Irrigation Science, Vol. 28, No. 6, 2010, p. 535-544.

Research output: Contribution to journalArticle

Hinnell, A. C. ; Lazarovitch, N. ; Furman, A. ; Poulton, Mary M ; Warrick, A. W. / Neuro-Drip : Estimation of subsurface wetting patterns for drip irrigation using neural networks. In: Irrigation Science. 2010 ; Vol. 28, No. 6. pp. 535-544.
@article{35444a8c36144aed8eb37622c695a73d,
title = "Neuro-Drip: Estimation of subsurface wetting patterns for drip irrigation using neural networks",
abstract = "Design of efficient drip irrigation systems requires information about the subsurface water distribution of added water during and after infiltration. Further, this information should be readily accessible to design engineers and practitioners. Neuro-Drip combines an artificial neural network (ANN) with a statistical description of the spatio-temporal distribution of the added water from a single drip emitter to provide easily accessible, rapid illustrations of the spatial and temporal subsurface wetting patterns. In this approach, the ANN is an approximator of a flow system. The ANN is trained using close to 1,000 numerical simulations of infiltration. Moment analysis is used to encapsulate the spatial distribution of water content. In practice, the user provides soil hydraulic properties and discharge rate; the ANN is then used to estimate the depth to the center of mass of the added water, and the vertical and radial spreading around the center of mass; finally, this statistical description of the added water is used to visualize the fate of the added water during and after the infiltration event.",
author = "Hinnell, {A. C.} and N. Lazarovitch and A. Furman and Poulton, {Mary M} and Warrick, {A. W.}",
year = "2010",
doi = "10.1007/s00271-010-0214-8",
language = "English (US)",
volume = "28",
pages = "535--544",
journal = "Irrigation Science",
issn = "0342-7188",
publisher = "Springer Verlag",
number = "6",

}

TY - JOUR

T1 - Neuro-Drip

T2 - Estimation of subsurface wetting patterns for drip irrigation using neural networks

AU - Hinnell, A. C.

AU - Lazarovitch, N.

AU - Furman, A.

AU - Poulton, Mary M

AU - Warrick, A. W.

PY - 2010

Y1 - 2010

N2 - Design of efficient drip irrigation systems requires information about the subsurface water distribution of added water during and after infiltration. Further, this information should be readily accessible to design engineers and practitioners. Neuro-Drip combines an artificial neural network (ANN) with a statistical description of the spatio-temporal distribution of the added water from a single drip emitter to provide easily accessible, rapid illustrations of the spatial and temporal subsurface wetting patterns. In this approach, the ANN is an approximator of a flow system. The ANN is trained using close to 1,000 numerical simulations of infiltration. Moment analysis is used to encapsulate the spatial distribution of water content. In practice, the user provides soil hydraulic properties and discharge rate; the ANN is then used to estimate the depth to the center of mass of the added water, and the vertical and radial spreading around the center of mass; finally, this statistical description of the added water is used to visualize the fate of the added water during and after the infiltration event.

AB - Design of efficient drip irrigation systems requires information about the subsurface water distribution of added water during and after infiltration. Further, this information should be readily accessible to design engineers and practitioners. Neuro-Drip combines an artificial neural network (ANN) with a statistical description of the spatio-temporal distribution of the added water from a single drip emitter to provide easily accessible, rapid illustrations of the spatial and temporal subsurface wetting patterns. In this approach, the ANN is an approximator of a flow system. The ANN is trained using close to 1,000 numerical simulations of infiltration. Moment analysis is used to encapsulate the spatial distribution of water content. In practice, the user provides soil hydraulic properties and discharge rate; the ANN is then used to estimate the depth to the center of mass of the added water, and the vertical and radial spreading around the center of mass; finally, this statistical description of the added water is used to visualize the fate of the added water during and after the infiltration event.

UR - http://www.scopus.com/inward/record.url?scp=77955713634&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955713634&partnerID=8YFLogxK

U2 - 10.1007/s00271-010-0214-8

DO - 10.1007/s00271-010-0214-8

M3 - Article

AN - SCOPUS:77955713634

VL - 28

SP - 535

EP - 544

JO - Irrigation Science

JF - Irrigation Science

SN - 0342-7188

IS - 6

ER -