Applicability of Monte Carlo cross validation technique for model development and validation using generalised least squares regression

Haddad, Khaled; Rahman, Ataur; Zaman, Mohammad A; Shrestha, Surendra

doi:10.1016/j.jhydrol.2012.12.041

Cited by 60 publications

(26 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The performance of different interpolation methods (OK, OCK, KED, IDW, and RBF) used in this study are evaluated and compared through cross-validation process. The cross-validation is a simple leave-one-out FIGURE 5 Experimental variograms and fitted variogram models based on the collocated elevation data for (a) Middle Yarra River catchment, and (b) Ovens River catchment validation procedure (Haddad, Rahman, Zaman, & Shrestha, 2013) in which observations are removed one at a time from the dataset and then re-estimated from the remaining observations using the adopted model. Cross-validation provides important evidence of the performance measures for the interpolation methods.…”

Section: Assessment Of Interpolation Methodsmentioning

confidence: 99%

Cokriging for enhanced spatial interpolation of rainfall in two Australian catchments

Adhikary

Muttil

Yilmaz

2017

Hydrological Processes

View full text Add to dashboard Cite

Rainfall data in continuous space provide an essential input for most hydrological and water resources planning studies. Spatial distribution of rainfall is usually estimated using ground-based point rainfall data from sparsely positioned rain-gauge stations in a rain-gauge network. Kriging has become a widely used interpolation method to estimate the spatial distribution of climate variables including rainfall. The objective of this study is to evaluate three geostatistical (ordinary that among the geostatistical methods, the OCK method is found to be the best interpolator for estimating spatial rainfall distribution in both the catchments with the lowest prediction error between the observed and estimated monthly rainfall. Thus, this study demonstrates that the use of elevation as an auxiliary variable in addition to rainfall data in the geostatistical framework can significantly enhance the estimation of rainfall over a catchment.

show abstract

Section: Assessment Of Interpolation Methodsmentioning

confidence: 99%

Cokriging for enhanced spatial interpolation of rainfall in two Australian catchments

Adhikary

Muttil

Yilmaz

2017

Hydrological Processes

View full text Add to dashboard Cite

show abstract

“…These are mainly Monte Carlo (Haddad et al, 2013), leave-one-out (Jaafar et al, 2011) or k-fold cross-validation. In this case, the k-fold cross-validation method was used, which is based on splitting the data set into k similarly large subsamples and running the calibration and validation k times when using always one subsample for validation while using the others together for calibration.…”

Section: Methodology Parameterisation and Validationmentioning

confidence: 99%

Methodology for flood frequency estimations in small catchments

David

Davidová

2014

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Estimations of flood frequencies in small catchments are difficult due to a lack of measured discharge data. This problem is usually solved in the Czech Republic by hydrologic modelling when there is a reason not to use the data provided by the Czech hydrometeorological institute, which are quite expensive and have a very low level of accuracy. Another way is to use a simple method which provides sufficient estimates of flood frequency based on the available spatial data. A new methodology is being developed considering all important factors affecting flood formation in small catchments. The relationship between catchment descriptors and flood characteristics has been analysed first to get an overview of the importance of each considered descriptor. The results for different descriptors vary from a highly correlated relationship of an expected shape to a relationship which is opposite to that expected, mainly in the case of land use. The parameterisation of the methodology is also presented, including the sensitivity tests on each involved catchment descriptor and cross-validation of achieved results. In its present form, the methodology achieves an R 2 adj value of about 0.61 for 10-and 0.60 for 100-year return periods.

show abstract

“…Then, the explanatory power of the variables was tested. The choice to include a variable in the model was conditioned by the improvement of the coefficient of determination and Nash criterion in cross-validation (Wan Jaafar et al, 2011;Cipriani et al, 2012;Haddad et al, 2013;Gao and Xie, 2014). The leave-one-out cross-validation (LOOCV) test was based on (n -1) sites in each of the n iterations, where n is the number of sites in the homogeneous region of interest.…”

Section: -Cv L-cs and L-ck (H < 1) Regions I Ii And Iii Were Foundmentioning

confidence: 99%

Application of the L-moments approach to the analysis of regional flood frequency in Northern Algeria

Meddi

Toumi

Assani

2017

IJHST

View full text Add to dashboard Cite

Algeria is periodically affected by severe and repeated flooding. Flood hazard studies require the estimation of extreme flood flows. To predict and estimate the characteristics of maximum flows, knowledge of their distribution law is essential. The L-moments method was used to determine homogeneous regions and the appropriate distribution for these regions. Three homogeneous regions were delineated. This technique produced a Pearson type III distribution for the coastal region and the Tell Atlas and a Pareto distribution for the steppe regions and high plateaus of Eastern and Western Algeria. To estimate maximum flow at ungauged sites for different return periods, the 'index-flood' method was used. An empirical formula was developed that uses the average annual maximum flow as a function of catchment area and the average slope of the main channel to estimate maximum flow at any point on the Oued. The coefficient of determination and the Nash criterion, for the three regions, are superiors to 88% and 83% respectively. The root mean squared error, for the three regions, is less than 12%. These values show the robustness of the developed models.

show abstract

Applicability of Monte Carlo cross validation technique for model development and validation using generalised least squares regression

Cited by 60 publications

References 40 publications

Cokriging for enhanced spatial interpolation of rainfall in two Australian catchments

Cokriging for enhanced spatial interpolation of rainfall in two Australian catchments

Methodology for flood frequency estimations in small catchments

Application of the L-moments approach to the analysis of regional flood frequency in Northern Algeria

Contact Info

Product

Resources

About