Statistical downscaling of GCM simulations to streamflow using relevance vector machine

Ghosh, Subimal; Mujumdar, P. P.

doi:10.1016/j.advwatres.2007.07.005

Cited by 309 publications

(219 citation statements)

References 35 publications

Supporting

Mentioning

214

Contrasting

Unclassified

Order By: Relevance

“…These techniques include linear and multiple linear regression, canonical correlation analysis, principal components analysis (or empirical orthogonal functions), artificial neural networks, and kriging (Barrow, 2002;Wilby and others, 2004;e.g., Heyen and others, 1996;others, 2001 andWidmann and others, 2003;Benestad, 2007;Ghosh and Mujumdar, 2008;Hoar and Nychka, 2008). Statistical downscaling approaches typically are less computationally demanding than dynamic downscaling approaches and, as a result, can downscale a large number of GCMs relatively easily.…”

Section: Statistical Downscalingmentioning

confidence: 99%

Downscaled climate projections for the Southeast United States: evaluation and use for ecological applications

Wootten¹,

Smith²,

Boyles³

et al. 2014

Open-File Report

View full text Add to dashboard Cite

show abstract

Section: Statistical Downscalingmentioning

confidence: 99%

Downscaled climate projections for the Southeast United States: evaluation and use for ecological applications

Wootten¹,

Smith²,

Boyles³

et al. 2014

Open-File Report

View full text Add to dashboard Cite

show abstract

“…Hadley center's regional climatic model (RCM) data were analyzed to study the variation induced in the climate parameters through the GHG scenarios (Chen et al 2011;Ghosh and Mujumdar 2008;Willems and Vrac 2011). Long term variations in temprature (maximum, minimum and average) have been shown in Fig.…”

Section: Climate Change Assessmentmentioning

confidence: 99%

Climate change impact assessment on hydrology of a small watershed using semi-distributed model

Pandey

Gosain

Paul³

et al. 2016

Appl Water Sci

View full text Add to dashboard Cite

This study is an attempt to quantify the impact of climate change on the hydrology of Armur watershed in Godavari river basin, India. A GIS-based semi-distributed hydrological model, soil and water assessment tool (SWAT) has been employed to estimate the water balance components on the basis of unique combinations of slope, soil and land cover classes for the base line and future climate scenarios (2071-2100). Sensitivity analysis of the model has been performed to identify the most critical parameters of the watershed. Average monthly calibration (1987-1994) and validation (1995-2000) have been performed using the observed discharge data. Coefficient of determination (R 2 ), Nash-Sutcliffe efficiency (ENS) and root mean square error (RMSE) were used to evaluate the model performance. Calibrated SWAT setup has been used to evaluate the changes in water balance components of future projection over the study area. HadRM3, a regional climatic data, have been used as input of the hydrological model for climate change impact studies. In results, it was found that changes in average annual temperature (?3.25°C), average annual rainfall (?28 %), evapotranspiration (28 %) and water yield (49 %) increased for GHG scenarios with respect to the base line scenario.

show abstract

“…General circulation models (GCMs) are regarded as the most reliable and advanced tools available to simulate global climate hundreds of years into future (Anandhi et al, 2008;Ghosh and Mujumdar, 2008). Heyen et al (1996) stated that GCMs are powerful tools for the analysis of the global climate.…”

Section: Introductionmentioning

confidence: 99%

“…GAMs, generalized linear models, aggregated boosted trees and ANN were used for predicting daily streamflows by Tisseuil et al (2010). Ghosh and Mujumdar (2008) implemented SVM and relevance vector machine to predict monthly streamflows. The ANN technique was utilized by Cannon and Whitfield (2002) for downscaling GCM outputs to 5-day mean streamflows.…”

Section: Introductionmentioning

confidence: 99%

Least square support vector and multi‐linear regression for statistically downscaling general circulation model outputs to catchment streamflows

Sachindra

Huang

Barton

et al. 2012

Intl Journal of Climatology

108

View full text Add to dashboard Cite

This study employed least square support vector machine regression (LS-SVM-R) and multi-linear regression (MLR) for statistically downscaling monthly general circulation model (GCM) outputs directly to monthly catchment streamflows. The scope of the study was limited to calibration and validation of the downscaling models. The methodology was demonstrated by its application to a streamflow site in the Grampian water supply system in northwestern Victoria, Australia. Probable predictors for the study were selected from the National Center for Environmental Prediction/National Center for Atmospheric Research (NCEP/NCAR) reanalysis data set based on the past literature and hydrology. Probable variables that displayed the best significant correlations, consistently with the streamflows over the entire period of the study and under three 20-year time slices (1950-1969, 1970-1989 and 1990-2010) were selected as potential predictors. To better capture seasonal variations of streamflows, downscaling models were developed for each calendar month. The standardized potential predictors were introduced to the LS-SVM-R and MLR models, starting from the best correlated three and then, others one by one, based on their correlations with the streamflows, until the model performance in validation was maximized. This stepwise model development enabled the identification of the optimum number of potential variables for each month. The model calibration was performed over the period 1950-1989 and validation was done for 1990-2010. LS-SVM-R model parameter optimization was achieved using simplex algorithm and leave-one-out cross-validation. The MLR models were optimized by minimizing the sum of squared errors. In both modelling techniques, validation was performed as an independent simulation. In calibration, LS-SVM-R and MLR models displayed equally good performances with a trend of under-predicting high flows. During validation, LS-SVM-R outperformed MLR, though both techniques over-predicted most of the streamflows. It was concluded that LS-SVM-R is a better technique for statistically downscaling GCM outputs to streamflows than MLR, but still MLR is a potential technique for the same task.

show abstract

Statistical downscaling of GCM simulations to streamflow using relevance vector machine

Cited by 309 publications

References 35 publications

Downscaled climate projections for the Southeast United States: evaluation and use for ecological applications

Downscaled climate projections for the Southeast United States: evaluation and use for ecological applications

Climate change impact assessment on hydrology of a small watershed using semi-distributed model

Least square support vector and multi‐linear regression for statistically downscaling general circulation model outputs to catchment streamflows

Contact Info

Product

Resources

About