WANN Model Research Articles

Simulating daily PM2.5 concentrations using wavelet analysis and artificial neural network with remote sensing and surface observation data

Accurate PM2.5 concentrations predicting is critical for public health and wellness as well as pollution control. However, traditional methods are difficult to accurately predict PM2.5. An adaptive model coupled with artificial neural network (ANN) and wavelet analysis (WANN) is utilized to predict daily PM2.5 concentrations with remote sensing and surface observation data. The four evaluation metrics, namely Pearson correlation coefficient (R), mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE), are utilized to evaluate the performances of the artificial neural network (ANN) and WANN methods. From the predicting results, The WANN model has a higher R (R = 0.9990) during the testing period compared with R (R = 0.6844) based on the ANN model. Similarly, the WANN model has a lower MAPE (3.6988%), RMSE (1.0145 μg/m3), MAE (1.3864 μg/m3), compared with MAPE (80.0086%), RMSE (16.5838 μg/m3), MAE (12.2420 μg/m3) of the ANN. In addition, comparing the outcomes of the proposed WANN method with the ANN method, it was observed that the error during the training and verification period has decreased significantly. Furthermore, the statistical methods are used to analyze WANN and ANN, showing that WANN has higher training accuracy and better stability. Therefore, it is feasible to establish WANN to predict PM2.5 concentrations (1 day in advance) by using remote sensing and surface observation data.

Predictive uncertainty assessment in flood forecasting using quantile regression

Abstract Floods and their associated impacts are topics of concern in land development planning and management, which call for efficient flood forecasting and warning systems. The performance of flood warning systems is affected by uncertainty in water level forecasts, which is due to their inability to measure or calculate a modeled value accurately. Predictive uncertainty is an emerging type of uncertainty modeling technique that emphasizes total uncertainty quantified as a probability distribution conditioned on all available knowledge. Predictive uncertainty analysis was done using quantile regression (QR) for machine learning-based flood models – Hybrid Wavelet Artificial Neural Network model (WANN) and Hybrid Wavelet Support Vector Machine model (WSVM) for different lead times. Comparing QR models of WANN and WSVM revealed that the slope, intercept, spread of forecast, and width of confidence band of the WANN model are more for each quantile indicating more uncertainty as compared to the WSVM model. In both models, with an increase in lead time, uncertainty has shown an increasing trend as well. The performance evaluation of inference obtained from QR models was evaluated using uncertainty statistics such as prediction interval coverage probability, average relative interval length (ARIL), and mean prediction interval (MPI).

Evaluation of Hybrid Soft Computing Model’s Performance in Estimating Wave Height

In coastal and port engineering, wind-generated waves have always been a crucial, fundamental, and important topic. As a result, various methods for estimating wave parameters, including field measurement and numerical methods, have been proposed over time. This study evaluates the wave height at Sri-Lanka Hambantota Port using soft computing models such as Artificial Neural Networks (ANNs) and the M5 model tree (M5MT). In order to overcome its nonstationarity, the primary wave height time series were divided into subtime series using the wavelet transform. The collected subtime series were then utilized as input data for ANN and M5MT in order to determine the wave height. For the sake of the model performance, the daily wind and wave data from the Acoustic Wave and Current (AWAC) sensor for Hambantota Port in 2020 and Sanmen Bay in 2017 were used in this study. The training state utilizes 80% of the available data, while the test state uses 20%. The Root Mean Square Error (RMSE) of the ANN, M5, WANN, and Wavelet-M5 models in the Hambantota Port for the test stage are 0.12, 0.11, 0.04, and 0.06, respectively. While in Sanmen Bay, the RMSE of the ANN, M5, WANN, and Wavelet-M5 models for the test stage are 0.14, 0.16, 0.06, and 0.08, respectively. According to the findings of this study, the accuracy of WANN and Wavelet-M5 hybrid models in evaluating wave height is superior to that of classic ANN and M5MT, and it is recommended that WANN and Wavelet-M5 hybrid models be used to estimate wave height.

De-noising groundwater level modeling using data decomposition techniques in combination with artificial intelligence (case study Aspas aquifer)

Considering the recent significant drop in the groundwater level (GWL) in most of world regions, the importance of an accurate method to estimate GWL (in order to obtain a better insight into groundwater conditions) has been emphasized by researchers. In this study, artificial neural network (ANN) and support vector regression (SVR) models were initially employed to model the GWL of the Aspas aquifer. Secondly, in order to improve the accuracy of the models, two preprocessing tools, wavelet transform (WT) and complementary ensemble empirical mode decomposition (CEEMD), were combined with former methods which generated four hybrid models including W-ANN, W-SVR, CEEMD-ANN, and CEEMD-SVR. After these methods were implemented, models outcomes were obtained and analyzed. Finally, the results of each model were compared with the unit hydrograph of Aspas aquifer groundwater based on different statistical indexes to assess which modeling technique provides more accurate GWL estimation. The evaluation of the models results indicated that the ANN model outperformed the SVR model. Moreover, it was found that combining these two models with the preprocessing tools WT and CEEMD improved their performances. Coefficient of determination (R2) which indicates model accuracy was increased from 0.927 in the ANN model to 0.938 and 0.998 in the W-ANN and CEEMD-ANN models, respectively. It was also improved from 0.919 in the SVR model to 0.949 and 0.948 in the W-SVR and CEEMD-SVR models, respectively. According to these results, the hybrid CEEMD-ANN model is found to be the most accurate method to predict the GWL in aquifers, especially the Aspas aquifer.

Superiority of Hybrid Soft Computing Models in Daily Suspended Sediment Estimation in Highly Dynamic Rivers

Estimating sediment flow rate from a drainage area plays an essential role in better watershed planning and management. In this study, the validity of simple and wavelet-coupled Artificial Intelligence (AI) models was analyzed for daily Suspended Sediment (SSC) estimation of highly dynamic Koyna River basin of India. Simple AI models such as the Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were developed by supplying the original time series data as an input without pre-processing through a Wavelet (W) transform. The hybrid wavelet-coupled W-ANN and W-ANFIS models were developed by supplying the decomposed time series sub-signals using Discrete Wavelet Transform (DWT). In total, three mother wavelets, namely Haar, Daubechies, and Coiflets were employed to decompose original time series data into different multi-frequency sub-signals at an appropriate decomposition level. Quantitative and qualitative performance evaluation criteria were used to select the best model for daily SSC estimation. The reliability of the developed models was also assessed using uncertainty analysis. Finally, it was revealed that the data pre-processing using wavelet transform improves the model’s predictive efficiency and reliability significantly. In this study, it was observed that the performance of the Coiflet wavelet-coupled ANFIS model is superior to other models and can be applied for daily SSC estimation of the highly dynamic rivers. As per sensitivity analysis, previous one-day SSC (St-1) is the most crucial input variable for daily SSC estimation of the Koyna River basin.

Multi hours ahead prediction of surface ozone gas concentration: Robust artificial intelligence approach

Forecasting the Ozone concentration is a substantial process in many important environmental issues such air pollution management, risk assessment, public health, and global warming. Early and accurate prediction of Ozone is very significant for efficient monitoring of pollution towards constituting advanced early alarm systems. In this study, wavelet transform (WT) approach was applied to handle input variables prior to introduce them to artificial neural network (ANN). This approach attempts to remove the noise impacts which decreases the accuracy of simulation processes. Additionally, to improve ANN model performance, the selection of suitable type of transfer function with effective input combinations was thoroughly investigated before introducing the WT approach. The hybrid model (W-ANN) was also compared to the classical ANN in the prediction of 1 h ahead Ozone concentrations to insure the significance of this study. Based on statistical measures during all phases (i.e. training, validation, and testing), the W-ANN outperformed ANN model. The W-ANN model yielded fewer values of root mean square error (0.9313 ppm) and mean absolute error (0.6531 ppm) while, ANN model produced higher values of root mean square error (2.902 ppm) and mean absolute error (1.991 ppm) during the testing set. The quantity of predicted values that have absolute relative error between 1 and 3% represented 18% and 36.16% of all data points for each approach, ANN and W-ANN respectively. Additionally, the hybrid W-ANN managed successfully to forecast multiple time scales (2-, 3-, 4 and 5- ahead hour Ozone concentrations) and reported very fewer errors in comparison with modeling of one hour ahead Ozone gas concentration.

Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions

Air quality forecasting is a significant method of protecting public health because it provides early warning of harmful air pollutants. In this study, we used correlation analysis and artificial neural networks (ANNs; including wavelet ANNs [WANNs]) to identify the linear and nonlinear associations, respectively, between the air pollution index (API) and meteorological variables in Xi’an and Lanzhou. Evaluating twelve algorithms and nineteen network topologies for the ANN and WANN models, we discovered that the optimal input variables for an API forecasting model were the APIs from the 3 preceding days and sixteen selected meteorological factors. Additionally, the API could be accurately predicted based solely on the value recorded 3 days earlier. Based on the correlation coefficients between the air pollution index of the targeted day and the tested variables, the API displayed the closest relationship with the API 1 day earlier as well as stronger correlations with the average temperature, average water vapor pressure, minimum temperature, maximum temperature, API 2 days earlier, and API 3 days earlier. When Bayesian regularization was applied as a training algorithm, the WANN and ANN models accurately reproduced the APIs in both Xi’an and Lanzhou, although the WANN model (R = 0.8846 for Xi’an and R = 0.8906 for Lanzhou) performed better than the ANN (R = 0.8037 for Xi’an and R = 0.7742 for Lanzhou) during the forecasting stage. These results demonstrate that WANNs are effective in short-term API forecasting because they can recognize historic patterns and thereby identify nonlinear relationships between the input and output variables. Thus, our study may provide a theoretical basis for environmental management policies.

Development and Evaluation of Hybrid Artificial Neural Network Architectures for Modeling Spatio-Temporal Groundwater Fluctuations in a Complex Aquifer System

The proper design, development, and appropriate tuning of the Hybrid Neural Network architecture, mainly for its parsimoniousity and optimal training can help practitioners to generate a robust predictive tool for modeling several important hydrological processes within the water resources sector. In this paper, the Feedforward Artificial Neural Network (FFANN) and the hybrid WANN model have been developed, and later, coupled with the Gamma and M-tests (GT) approach for forecasting spatio-temporal groundwater fluctuations in a complex alluvial aquifer system. The performance of these hybrid models were evaluated using goodness-of-fit criteria. An analysis of the modeling results indicates that the GT coupled with the WANN model was able to provide significantly improved results, with lower values of the root mean square error (RMSE) and higher values of the NSE metric for the 1-week and 3-week lead times. Hence, utilizing this hybrid model, the groundwater level prediction tests were extended for 6-week and 12-week lead times with the GT approach, coupled with the WANN hybrid model only. The results showed that the accuracy of the GT-WANN hybrid model was better for the unconfined aquifer system compared to the leaky confined aquifer system. Furthermore, the present study also examined the interdependence between different model inputs and output variables for the selected study sites by means of the Wavelet Coherent Analysis (WCA). These results indicated that all the model’s input variables have a significant effect on the groundwater level of unconfined aquifers, and confirmed the nature of the aquifers tapped within the present study sites. The study finally concludes that the GT-WANN approach can be a robust predictive tool for modeling spatio-temporal fluctuations of groundwater levels.

Data mining based on wavelet and decision tree for rainfall-runoff simulation

Abstract This study introduced a new hybrid model (Wavelet-M5 model) which combines the wavelet transforms and M5 model tree for rainfall-runoff modeling. For this purpose, the main time series were decomposed to several sub-signals by the wavelet transform, at first. Then, the obtained sub-time series were imposed as input data to M5 model tree, and finally, the related linear regressions were presented by M5 model tree. This new technique was applied on the monthly time series of Sardrud catchment and the results were also compared with other models like WANN and sole M5 model tree. The results showed that the accuracy of the proposed model is better than the previous models and also indicated the effect of data pre-processing on the performance of M5 model tree. The determination coefficient of the training stage was 0.80 and improved 31% than the M5 model tree for Sardrud catchment which is recognized as a normal watershed with a regular four seasons' pattern.

Time series forecasting of river flow using an integrated approach of wavelet multi-resolution analysis and evolutionary data-driven models. A case study: Sebaou River (Algeria)

The complexity of hydrological processes and lack of data for modeling require the use of specific tools for non-linear natural phenomenon. In this paper, an effort has been made to develop a conjunction model – wavelet transformation, data-driven models, and genetic algorithm (GA) – for forecasting the daily flow of a river in northern Algeria using the time series of runoff. This catchment has a semi-arid climate and strong variability in runoff. The original time series was decomposed into multi-frequency time series by wavelet transform algorithm and used as inputs to artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models. Several factors must be optimized to determine the best model structures. Wavelet-based data-driven models using a GA are designed to optimize model structure. The performances of wavelet-based data-driven models (i.e. WANFIS and WANN) were superior to those of conventional models. WANFIS (RMSE = 12.15 m3/s, EC = 87.32%, R = .934) and WANN (RMSE = 15.73 m3/s, EC = 78.83%, R = .888) models improved the performances of ANFIS (RMSE = 23.13 m3/s, EC = 54.11%, R = .748) and ANN (RMSE = 22.43 m3/s, EC = 56.90%, R = .755) during the test period.

Development of hybrid wavelet-ANN model for hourly flood stage forecasting

Hourly flood forecasting with sufficient lead time is necessary to develop preparedness and facilitate quick response in adopting appropriate flood mitigation plans and rehabilitation actions. This study explores the potential of hybrid wavelet-ANN (wavelet-Artificial neural network) to model flood events in the Achankovil river basin in Kerala. Hourly water level at the Konni gauging site is predicted with 1-, 3- and 6-h lead times. The hybrid wavelet-ANN approach has proved its capabilities in hydrological studies due to the capability of wavelet in multi-resolution analysis and its ability to deal with non-stationarities. The three hybrid wavelet-ANN models developed were trained considering various combinations of flood events. The significant antecedent water level and precipitation values were selected based on statistical analysis and a study of the hydrology of the catchment. Decomposition of the input signals using wavelet was performed by selecting a suitable mother wavelet and an appropriate decomposition level. Results of this study clearly demonstrate the capability of the hybrid models to forecast floods satisfactorily up to 6 h lead time. The capability of the hybrid model is proved by comparison with a simple ANN model. The WANN models developed were able to predict the magnitude of peak value and the time to peak value more accurately when compared to the ANN models. These two parameters of a flood hydrograph are very important in many water resources applications.

Evaluation of nonlinear models for precipitation forecasting

ABSTRACTPrediction of factors affecting water resources systems is important for their design and operation. In hydrology, wavelet analysis (WA) is known as a new method for time series analysis. In this study, WA was combined with an artificial neural network (ANN) for prediction of precipitation at Varayeneh station, western Iran. The results obtained were compared with the adaptive neural fuzzy inference system (ANFIS) and ANN. Moreover, data on relative humidity and temperature were employed in addition to rainfall data to examine their influence on precipitation forecasting. Overall, this study concluded that the hybrid WANN model outperformed the other models in the estimation of maxima and minima, and is the best at forecasting precipitation. Furthermore, training and transfer functions are recommended for similar studies of precipitation forecasting.

Flow forecasting models using hydrologic and hydrometric data

River flow forecasting is important for successful water resources planning and management. The current study investigated the applicability of the artificial neural network (Ann), adaptive neuro-fuzzy inference system (Anfis), wavelet-Ann (Wann) and wavelet-Anfis (Wanfis) for daily river flow forecasting in Karaj River. Three scenarios were used. In the first scenario, meteorological data were used as input variables for model development. In the second, flow discharge data were used, while the third scenario used a combination of scenarios 1 and 2 as input variables for model development. For each scenario, different combinations of time series were considered. In the Wann and Wanfis models, the effective sub-time series components obtained by discrete wavelet transform were used as the new inputs to Ann and Anfis models to predict daily river flow time series. Wann was found to be the best technique for daily flow prediction throughout this study. The results indicate that the best Wann model (R2test = 0·993, RMSEtest = 0·004) outperformed the best Wanfis model (R2test = 0·976, RMSEtest = 0·008). The results show that only the input structures of scenarios 2 and 3 are efficient input structures for flow prediction in the study area. It was also shown that Wann models are capable of delivering an accurate flow prediction up to the next 4 d.

Modeling of Dissolved Oxygen Concentration and Its Hysteresis Behavior in Rivers Using Wavelet Transform‐Based Hybrid Models

Concentration of dissolved oxygen (DO) is an indicator to evaluate environmental health in many riverine systems. In this study, two hybrid models, the wavelet‐based regression model (WR) and the wavelet‐based artificial neural network model (WANN), are proposed for short‐interval (1 day ahead) and long‐interval (31 days ahead) prediction of DO concentration in Clackamas River near Oregon City, OR, USA. It was found that both in the short‐ and long‐prediction intervals, the hybrid models performed better than the multiple linear regression and artificial neural network models. Also, the performance of the models to predict seasonal DO variations, low (DO < 10 mg/L) and high (DO > 14 mg/L) DO ranges and simulating its hysteresis was evaluated. For the short‐interval modeling, results of the WR model were better than those of the other three models. For the long‐interval modeling during spring and summer, the WANN model presented better predictions of DO. And during autumn and winter, the WR model presented higher accuracy than the others. In addition, these hybrid models were able to simulate DO daily hysteresis behavior. The most accurate WR model predicted DO with the minimum root mean square error (RMSE) of 0.097 mg/L and the maximum Nash‐Sutcliffe coefficient of efficiency (E) of 0.996 for the short interval. For the long interval, the best performing model was the WANN model with RMSE and E‐statistics of 0.744 mg/L and 0.766, respectively.

Forecasting effective drought index using a wavelet extreme learning machine (W-ELM) model

A drought forecasting model is a practical tool for drought-risk management. Drought models are used to forecast drought indices (DIs) that quantify drought by its onset, termination, and subsequent properties such as the severity, duration, and peak intensity in order to monitor and evaluate the impacts of future drought. In this study, a wavelet-based drought model using the extreme learning machine (W-ELM) algorithm where the input data are first screened through the wavelet pre-processing technique for better accuracy is developed to forecast the monthly effective DI (EDI). The EDI is an intensive index that considers water accumulation with a weighting function applied to rainfall data with the passage of time in order to analyze the drought-risk. Determined by the autocorrelation function (ACF) and partial ACFs, the lagged EDI signals for the current and past months are used as significant inputs for 1 month lead-time EDI forecasting. For drought model development, 97 years of data for three hydrological stations (Bathurst Agricultural, Wilsons Promontory and Merredin in Australia) are partitioned in approximately 90:5:5 ratios for training, cross-validation and test purposes, respectively. The discrete wavelet transformation (DWT) is applied to the predictor datasets to decompose inputs into their time–frequency components that capture important information on periodicities. DWT sub-series are used to develop new EDI sub-series as inputs for the W-ELM model. The forecasting capability of W-ELM is benchmarked with ELM, artificial neural network (ANN), least squares support vector regression (LSSVR) and their wavelet-equivalent (W-ANN, W-LSSVR) models. Statistical metrics based on agreement between the forecasted and observed EDI, including the coefficient of determination, Willmott’s index, Nash–Sutcliffe coefficient, percentage peak deviation, root-mean-square error, mean absolute error, and model execution time are used to assess the effectiveness of the models. The results demonstrate enhanced forecast skill of the drought models that use wavelet pre-processing of the predictor dataset. Based on statistical measures, W-ELM outperformed traditional ELM, LSSVR, ANN and their wavelet-equivalent counterparts (W-ANN, W-LSSVR). It is found that the W-ELM model is computationally efficient as shown by a faster running time with the majority of forecasting errors in lower frequency bands. The results demonstrate the usefulness of W-ELM over W-ANN and W-LSSVR models and the benefits of wavelet transformation of input data to improve the performance of drought forecasting models.

A wavelet–linear genetic programming model for sodium (Na+) concentration forecasting in rivers

Summary The prediction of water quality parameters in water resources such as rivers is of importance issue that needs to be considered in better management of irrigation systems and water supplies. In this respect, this study proposes a new hybrid wavelet–linear genetic programming (WLGP) model for prediction of monthly sodium (Na + ) concentration. The 23-year monthly data used in this study, were measured from the Asi River at the Demirkopru gauging station located in Antakya, Turkey. At first, the measured discharge (Q) and Na + datasets are initially decomposed into several sub-series using discrete wavelet transform (DWT). Then, these new sub-series are imposed to the ad hoc linear genetic programming (LGP) model as input patterns to predict monthly Na + one month ahead. The results of the new proposed WLGP model are compared with LGP, WANN and ANN models. Comparison of the models represents the superiority of the WLGP model over the LGP, WANN and ANN models such that the Nash–Sutcliffe efficiencies (NSE) for WLGP, WANN, LGP and ANN models were 0.984, 0.904, 0.484 and 0.351, respectively. The achieved results even points to the superiority of the single LGP model than the ANN model. Continuously, the capability of the proposed WLGP model in terms of prediction of the Na + peak values is also presented in this study.

Computational approaches for annual maximum river flow series

Abstract Studies of annual peak discharge and its temporal variations are widely used in the planning and decision making process of water resources management. Very recently, soft computing techniques are gaining ground for time series analysis of hydrological events such as rainfall and runoff. In this study Artificial Neural Network (ANN) has been used in combination with wavelet to model the annual maximum flow discharge of rivers. The results of ANN-Wavelet (WANN) model indicate overall low coherence (R2 = 0.39) better than ANN (R2 = 0.31) in isolation. In the present analysis, the authors also conceded a probabilistic distributional analysis of river flow time series which has greater potential to better reflect peak flow dynamics. The results highlight that the overall performance of probability distribution models is superior to WANN model. Instead of that WANN is better than probabilistic models to find the global maxima of the series.

Forecasting of chlorophyll-a concentrations in South San Francisco Bay using five different models

Accurate and reliable eutrophication level forecasting models are necessary for characterizing complicated water quality processes in bays. In this study, the ability of coupled discrete wavelet transform (DWT) with artificial neural network (ANN) and multi linear regression (MLR) (WANN and WMLR), ANN, MLR and genetic algorithm-support vector regression (GA-SVR) models for chlorophyll-a level forecasting applications were considered. The data used to develop and validate the models were monthly chlorophyll-a (Chl-a) data recorded from January 1994 to December 2013 were obtained from the NO.36 station located in the South San Francisco bay, USA. In the proposed WANN and WMLR models, the observed time series of Chl-a were decomposed to sub time series at different scales by DWT. Afterwards, the sub time series were used as input data to the ANN and MLR systems to predict the 1 month ahead Chl-a. Also the genetic algorithm was linked to SVR models to search for the optimal SVR parameters. The relative performance of the proposed models was compared together and the results showed that the WANN models were found to provide more accurate monthly Chl-a forecasts compared to the other models. The determination coefficient was 0.87, −0.04, 0.31, −2.36 and 0.24 for the WANN, WMLR, ANN, MLR and GA-SVR models, respectively. In addition, the WANN model predicted extreme Chl-a values precisely. The results indicate that the WANN models are a promising new method for eutrophication level forecasting in bays such as those found in South San Francisco Bay.

Evaluation of wavelet performance via an ANN-based electrical conductivity prediction model.

The prediction of water quality parameters plays an important role in water resources and environmental systems. The use of electrical conductivity (EC) as a water quality indicator is one of the important parameters for estimating the amount of mineralization. This study describes the application of artificial neural network (ANN) and wavelet-neural network hybrid (WANN) models to predict the monthly EC of the Asi River at the Demirköprü gauging station, Turkey. In the proposed hybrid WANN model, the discrete wavelet transform (DWT) was linked to the ANN model for EC prediction using a feed-forward back propagation (FFBP) training algorithm. For this purpose, the original time series of monthly EC and discharge (Q) values were decomposed to several sub-time series by DWT, and these sub-time series were then presented to the ANN model as an input dataset to predict the monthly EC. Comparing the values predicted by the models indicated that the performance of the proposed WANN model was better than the conventional ANN model. The correlation of determination (R (2)) were 0.949 and 0.381 for the WANN and ANN models, respectively. The results indicate that the peak EC values predicted by the WANN model are closer to the observed values, and this model simulates the hysteresis phenomena at an acceptable level as well.

Intermittent Streamflow Forecasting and Extreme Event Modelling using Wavelet based Artificial Neural Networks

Forecasting of intermittent stream flow is necessary for water resource planning and management at catchment scale. Forecasting of extreme events and events outside the range of training data used for artificial neural network (ANN) model development has been a major bottleneck in their generalization capabilities till date. Despite of several studies using wavelet analysis in water resource modelling, no study has yet been conducted to explore capabilities of hybrid ANN modelling techniques for extreme events outside the training range. In this study a wavelet based ANN model (WANN) is proposed for intermittent streamflow forecasting and extreme event modelling. This study is carried out in a watershed in semi arid middle region of Gujarat, India. 6 years of hydro-climatic data are used in this study. 4 years of data are used for model training, 1 year for cross-validation and remaining 1 year data are used to evaluate the effectiveness of the WANN model. Two different approaches of data arrangement are considered in this study, in one approach testing data are within the range of training dataset, whereas in another approach testing data are outside the training dataset range. Performance of four different training algorithms and different types of wavelet functions are also evaluated for WANN model development. In this study it is found that WANN model performed significantly better than standard ANN models. It is observed in this study that different wavelet functions have different role in modelling complexities of normal and extreme events. WANN model simulated peak values very well and it shows that WANN model has the potential to be applied successfully for intermittent streamflow forecasting even for the data outside the training range and for extreme events.