Machine learning: An efficient alternative to the variable infiltration capacity model for an accurate simulation of runoff rates

Hamidreza Ghasemi Damavandi, Dimitrios Stampoulis, Reepal Shah, Yuhang Wei, Dragan Boscovic, John Sabo

Research output: Contribution to journalArticle

Abstract

The present study aims to investigate the performance of the artificial intelligence to emulate the conventional physically-based hydrological models. Although these conventional models could accurately depict the underlying physical processes, but they require a lengthy preprocessing phase as well as a tedious calibration time. Therefore, a need to examine the potential efficient alternative for these models is highly felt. This need becomes imperative once we adopt fine temporal and spatial resolutions for our hydrological modeling, leading to a massive number of to-be-analyzed cells. To this end, we propose a learning framework towards an accurate prediction of runoff rates using meteorological variables, and hence, mimicking the Variable Infiltration Capacity (VIC) by a nimble systematized predictive model. We also present a novel strategy to optimally select the most informative subset of data to train our predictive model, out of the pool of accessible data. This strategy would then considerably enhance the performance of our prediction in terms of computation time. We reported our result as the Pearson correlation coefficient between the predicted and actual runoff rates. Our predictive model was able to forecast the runoff rates with the mean correlation coefficient of 0.9007 for the cells within the study basin.

Original languageEnglish (US)
Pages (from-to)288-293
Number of pages6
JournalInternational Journal of Environmental Science and Development
Volume10
Issue number9
DOIs
StatePublished - Jan 1 2019

Fingerprint

infiltration
runoff
simulation
artificial intelligence
hydrological modeling
prediction
train
machine learning
rate
spatial resolution
learning
calibration
basin

Keywords

  • Active learning
  • Artificial intelligence
  • Random forests
  • Variable infiltration capacity

ASJC Scopus subject areas

  • Environmental Science(all)

Cite this

Machine learning : An efficient alternative to the variable infiltration capacity model for an accurate simulation of runoff rates. / Damavandi, Hamidreza Ghasemi; Stampoulis, Dimitrios; Shah, Reepal; Wei, Yuhang; Boscovic, Dragan; Sabo, John.

In: International Journal of Environmental Science and Development, Vol. 10, No. 9, 01.01.2019, p. 288-293.

Research output: Contribution to journalArticle

@article{d8b87653e6194aea9db86ba5f9809de3,
title = "Machine learning: An efficient alternative to the variable infiltration capacity model for an accurate simulation of runoff rates",
abstract = "The present study aims to investigate the performance of the artificial intelligence to emulate the conventional physically-based hydrological models. Although these conventional models could accurately depict the underlying physical processes, but they require a lengthy preprocessing phase as well as a tedious calibration time. Therefore, a need to examine the potential efficient alternative for these models is highly felt. This need becomes imperative once we adopt fine temporal and spatial resolutions for our hydrological modeling, leading to a massive number of to-be-analyzed cells. To this end, we propose a learning framework towards an accurate prediction of runoff rates using meteorological variables, and hence, mimicking the Variable Infiltration Capacity (VIC) by a nimble systematized predictive model. We also present a novel strategy to optimally select the most informative subset of data to train our predictive model, out of the pool of accessible data. This strategy would then considerably enhance the performance of our prediction in terms of computation time. We reported our result as the Pearson correlation coefficient between the predicted and actual runoff rates. Our predictive model was able to forecast the runoff rates with the mean correlation coefficient of 0.9007 for the cells within the study basin.",
keywords = "Active learning, Artificial intelligence, Random forests, Variable infiltration capacity",
author = "Damavandi, {Hamidreza Ghasemi} and Dimitrios Stampoulis and Reepal Shah and Yuhang Wei and Dragan Boscovic and John Sabo",
year = "2019",
month = "1",
day = "1",
doi = "10.18178/ijesd.2019.10.9.1189",
language = "English (US)",
volume = "10",
pages = "288--293",
journal = "International Journal of Environmental Science and Development",
issn = "2010-0264",
publisher = "International Journal of Environmental Science and Development",
number = "9",

}

TY - JOUR

T1 - Machine learning

T2 - An efficient alternative to the variable infiltration capacity model for an accurate simulation of runoff rates

AU - Damavandi, Hamidreza Ghasemi

AU - Stampoulis, Dimitrios

AU - Shah, Reepal

AU - Wei, Yuhang

AU - Boscovic, Dragan

AU - Sabo, John

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The present study aims to investigate the performance of the artificial intelligence to emulate the conventional physically-based hydrological models. Although these conventional models could accurately depict the underlying physical processes, but they require a lengthy preprocessing phase as well as a tedious calibration time. Therefore, a need to examine the potential efficient alternative for these models is highly felt. This need becomes imperative once we adopt fine temporal and spatial resolutions for our hydrological modeling, leading to a massive number of to-be-analyzed cells. To this end, we propose a learning framework towards an accurate prediction of runoff rates using meteorological variables, and hence, mimicking the Variable Infiltration Capacity (VIC) by a nimble systematized predictive model. We also present a novel strategy to optimally select the most informative subset of data to train our predictive model, out of the pool of accessible data. This strategy would then considerably enhance the performance of our prediction in terms of computation time. We reported our result as the Pearson correlation coefficient between the predicted and actual runoff rates. Our predictive model was able to forecast the runoff rates with the mean correlation coefficient of 0.9007 for the cells within the study basin.

AB - The present study aims to investigate the performance of the artificial intelligence to emulate the conventional physically-based hydrological models. Although these conventional models could accurately depict the underlying physical processes, but they require a lengthy preprocessing phase as well as a tedious calibration time. Therefore, a need to examine the potential efficient alternative for these models is highly felt. This need becomes imperative once we adopt fine temporal and spatial resolutions for our hydrological modeling, leading to a massive number of to-be-analyzed cells. To this end, we propose a learning framework towards an accurate prediction of runoff rates using meteorological variables, and hence, mimicking the Variable Infiltration Capacity (VIC) by a nimble systematized predictive model. We also present a novel strategy to optimally select the most informative subset of data to train our predictive model, out of the pool of accessible data. This strategy would then considerably enhance the performance of our prediction in terms of computation time. We reported our result as the Pearson correlation coefficient between the predicted and actual runoff rates. Our predictive model was able to forecast the runoff rates with the mean correlation coefficient of 0.9007 for the cells within the study basin.

KW - Active learning

KW - Artificial intelligence

KW - Random forests

KW - Variable infiltration capacity

UR - http://www.scopus.com/inward/record.url?scp=85071377084&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071377084&partnerID=8YFLogxK

U2 - 10.18178/ijesd.2019.10.9.1189

DO - 10.18178/ijesd.2019.10.9.1189

M3 - Article

AN - SCOPUS:85071377084

VL - 10

SP - 288

EP - 293

JO - International Journal of Environmental Science and Development

JF - International Journal of Environmental Science and Development

SN - 2010-0264

IS - 9

ER -