Multiple regression and Artificial Neural Network for long-term rainfall forecasting using large scale climate modes

Mekanik, Fatemeh; Imteaz, Monzur Alam; Gato-Trinidad, Shirley; Elmahdi, Amgad

doi:10.1016/j.jhydrol.2013.08.035

Cited by 244 publications

(119 citation statements)

References 45 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…The choice of air temperatures and climate indices followed the approach of related studies on rainfall prediction problems in Australia (e.g. Marohasy, 2012, 2014;Mekanik et al, 2013) and the prediction of the Effective Drought Index elsewhere (e.g. Iran and South Africa, Masinde, 2013;Morid et al, 2007).…”

Section: Climate Datamentioning

confidence: 99%

“…Consequently many studies are using different ML algorithms to demonstrate nearly coincident or in some cases, even better prediction yields than the GCM models. In fact, recent studies that compared rainfall predictions using ML models with the physical models demonstrated dramatic improvements in the prediction capability of the former models Marohasy, 2012, 2014;Luk et al, 2000;Mekanik et al, 2013;Nasseri et al, 2008). In particular, the work of Marohasy (2012, 2014) that compared rainfall prediction from an ML algorithm with the POAMA used in Australia over geographically distinct regions in Queensland found that the former approach was superior as evidenced by the lower root mean square errors, lower mean absolute errors and higher correlation coefficients between the observed and modeled rainfall values.…”

Section: Introductionmentioning

confidence: 99%

“…A suite of 13 inputs for each model was used for training, where the primary meteorological inputs are the observed monthly rainfall and air temperature data at 4 observational sites in the region. Together, the primary large-scale climate mode indices known to impact drought events in eastern Australia, namely the Southern Oscillation Index (SOI), Indian Ocean Dipole (IOD), Southern Annular Mode (SAM) and Pacific Decadal Osculation (PDO) were used, which have recently been proven useful in rainfall prediction problems Marohasy, 2012, 2014;Mekanik et al, 2013). Our study was also motivated by many research works that showed greater potential of ELM algorithm over the simple arithmetic means approach and the singular value decomposition in predicting rainfall and drought events (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia

Deo

Şahin

2015

Atmospheric Research

255

102

View full text Add to dashboard Cite

The prediction of future drought is an effective mitigation tool for assessing adverse consequences of drought events on vital water resources, agriculture, ecosystems and hydrology. Data-driven model predictions using machine learning algorithms are promising tenets for these purposes as they require less developmental time, minimal inputs and are relatively less complex than the dynamic or physical model. This paper authenticates a computationally simple, fast and efficient non-linear algorithm known as extreme learning machine (ELM) for the prediction of Effective Drought Index (EDI) in eastern Australia using input data trained from 1957-2008 and the monthly EDI predicted over the period 2009-2011. The predictive variables for the ELM model were the rainfall and mean, minimum and maximum air temperatures, supplemented by the large-scale climate mode indices of interest as regression covariates, namely the Southern Oscillation Index, Pacific Decadal Oscillation, Southern Annular Mode and the Indian Ocean Dipole moment. To demonstrate the effectiveness of the proposed datadriven model a performance comparison in terms of the prediction capabilities and learning speeds was conducted between the proposed ELM algorithm and the conventional artificial neural network (ANN) algorithm trained with Levenberg-Marquardt back propagation. The prediction metrics certified an excellent performance of the ELM over the ANN model for the overall test sites, thus yielding Mean Absolute Errors, Root-Mean Square Errors, Coefficients of Determination and Willmott's Indices of Agreement of 0.277, 0.008, 0.892 and 0.93 (for ELM) and 0.602, 0.172, 0.578 and 0.92 (for ANN) models. Moreover, the ELM model was executed with learning speed 32 times faster and training speed 6.1 times faster than the ANN model. An improvement in the prediction capability of the drought duration and severity by the ELM model was achieved. Based on these results we aver that out of the two machine learning algorithms tested, the ELM was the more expeditious tool for prediction of drought and its related properties.

show abstract

Section: Climate Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia

Deo

Şahin

2015

Atmospheric Research

255

102

View full text Add to dashboard Cite

show abstract

“…Widely applied in hydrology, the popular ANN FFBP class of ANN models, equipped with multilayer perceptron functional neurons [ABBOT, MARO-HASY 2012;ADAMOWSKI et al 2012c;DEO, ŞAHIN 2015a;KESKIN, TERZI 2006;MEKANIK et al 2013] was used in the present study. The ANN architecture is designed to successively update the model parameters (weighted connections and neuron biases) to drive the empirical error to a set tolerance through each iteration (epochs) of forward passing of updated parameters and backward propagation of the errors to tune them.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Water demand forecasting using extreme learning machines

Tiwari¹,

Adamowski²,

Adamowski³

2016

Journal of Water and Land Development

View full text Add to dashboard Cite

The capacity of recently-developed extreme learning machine (ELM) modelling approaches in forecasting daily urban water demand from limited data, alone or in concert with wavelet analysis (W) or bootstrap (B) methods (i.e., ELM, ELM W , ELM B ), was assessed, and compared to that of equivalent traditional artificial neural network-based models (i.e., ANN, ANN W , ANN B ). The urban water demand forecasting models were developed using 3-year water demand and climate datasets for the city of Calgary, Alberta, Canada. While the hybrid ELM B and ANN B models provided satisfactory 1-day lead-time forecasts of similar accuracy, the ANN W and ELM W models provided greater accuracy, with the ELM W model outperforming the ANN W model. Significant improvement in peak urban water demand prediction was only achieved with the ELM W model. The superiority of the ELM W model over both the ANN W or ANN B models demonstrated the significant role of wavelet transformation in improving the overall performance of the urban water demand model.

show abstract

“…In recent years, artificial neural networks (ANNs), under nonparametric category, have found their ways to solve many problems related to rainfall such as rainfall forecasting [13][14][15][16][17][18][19][20], rainfall-runoff model [21][22][23], rainfall estimation by radars [1,24,25] and satellites [26][27][28][29][30][31], and temporal and spatial rainfall disaggregation [32,33]. e advantage of an ANN approach is that it can be used to develop a functional relationship, including a nonlinear relationship, amongst the various parameters of the process under study even in the absence of full understanding of its mathematical model [34].…”

Section: Introductionmentioning

confidence: 99%

Simulation of Daily Rainfall from Concurrent Meteorological Parameters over Core Monsoon Region of India: A Novel Approach

Misra

Deshamukhya

Sharma³

et al. 2018

Advances in Meteorology

View full text Add to dashboard Cite

In the present work, daily rainfall is simulated over the core monsoon region of India by using a feedforward multilayer perceptron (MLP) model. Daily rainfall is found to be optimally dependent on four concurrent meteorological parameters, namely, geopotential height, specific humidity, zonal, and meridional wind at 1000 mb, 925 mb, 850 mb, and 700 mb pressure levels during 00, 06, 12, and 18 Greenwich Mean Time (GMT). e architecture of the optimized feedforward MLP model consists of 64 nodes in the input layer, 10 nodes in the hidden layer, and 1 node in the output layer. e results from the model are compared with the 3B42 (version 7) rainfall product. In terms of root mean square error (rmse) and correlation coefficient (cc), the model is performing better compared to the satellite-derived 3B42 rainfall product, whereas in terms of bias, the performance of the 3B42 product is better compared to the model. e weight matrices of the feedforward MLP model are estimated at a particular location (22.5°N, 82.5°E). ese weight matrices are able to simulate daily rainfall at neighbourhood locations also with reasonably good accuracy with cc in the range of 0.41 to 0.55. e performance of the model improves in case of an aerial average of daily rainfall with significantly enhanced cc (0.72). e model is able to capture monthly and intraseasonal variation of rainfall with reasonably good accuracy, with cc of 0.88 and 0.68, respectively. e simulation model has a limitation that it is not able to simulate extreme high rainfall events (>60 mm/day). Overall, the developed model is performing reasonably well. is approach has a potential to be used as a rain parameterization scheme in the dynamical atmospheric and coupled models to simulate daily rainfall. Nevertheless, the present approach can also be used for multistep prediction of rainfall.

show abstract

Multiple regression and Artificial Neural Network for long-term rainfall forecasting using large scale climate modes

Cited by 244 publications

References 45 publications

Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia

Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia

Water demand forecasting using extreme learning machines

Simulation of Daily Rainfall from Concurrent Meteorological Parameters over Core Monsoon Region of India: A Novel Approach

Contact Info

Product

Resources

About