Over the past 15 years, artificial neural networks (ANNs) have been used increasingly for prediction and forecasting in water resources and environmental engineering. However, despite this high level of research activity, methods for developing ANN models are not yet well established. In this paper, the steps in the development of ANN models are outlined and taxonomies of approaches are introduced for each of these steps. In order to obtain a snapshot of current practice, ANN development methods are assessed based on these taxonomies for 210 journal papers that were published from 1999 to 2007 and focus on the prediction of water resource variables in river systems. The results obtained indicate that the vast majority of studies focus on flow prediction, with very few applications to water quality. Methods used for determining model inputs, appropriate data subsets and the best model structure are generally obtained in an ad-hoc fashion and require further attention. Although multilayer perceptrons are still the most popular model architecture, other model architectures are also used extensively. In relation to model calibration, gradient based methods are used almost exclusively. In conclusion, despite a significant amount of research activity on the use of ANNs for prediction and forecasting of water resources variables in river systems, little of this is focused on methodological issues. Consequently, there is still a need for the development of robust ANN model development approaches.

Review: Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions

Daily suspended sediment concentration simulation using ANN and neuro-fuzzy models.

Advances in the understanding of physical, chemical, and biological processes influencing water quality, cou- pled with improvements in the collection and analysis of hydrologic data, provide opportunities for significant innovations in the manner and level with which watershed-scale processes may be explored and modeled. This paper provides a re- view of current trends in watershed modeling, including use of stochastic-based methods, distributed versus lumped pa- rameter techniques, influence of data resolution and scalar issues, and the utilization of artificial intelligence (AI) as part of a data-driven approach to assist in watershed modeling efforts. Important findings and observed trends from this work include (i) use of AI techniques artificial neural networks (ANN), fuzzy logic (FL), and genetic algorithms (GA) to im- prove upon or replace traditional physically-based techniques which tend to be computationally expensive; (ii) limitations in scale-up of hydrological processes for watershed modeling; and (iii) the impacts of data resolution on watershed model- ing capabilities. In addition, detailed discussions of individual watershed models and modeling systems with their fea- tures, limitations, and example applications are presented to demonstrate the wide variety of systems currently available for watershed management at multiple scales. A summary of these discussions is presented in tabular format for use by water resource managers and decision makers as a screening tool for selecting a watershed model for a specific purpose.

https://www.tucson.ars.ag.gov/agwa/download/docs/publications/Watershed%20Modeling%20and%20its%20Applications_A%20State-of-the-Art%20Review.pdf

Watershed Modeling and its Applications: A State-of-the-Art Review

The accuracy of an adaptive neurofuzzy computing technique in estimation of reference evapotranspiration ( ET0 ) is investigated in this paper. The daily climatic data, solar radiation, air temperature, relative humidity, and wind speed from two stations, Pomona and Santa Monica, in Los Angeles, Calif., are used as inputs to the neurofuzzy model to estimate ET0 obtained using the FAO-56 Penman–Monteith equation. In the first part of the study, a comparison is made between the estimates provided by the neurofuzzy model and those of the following empirical models: The California Irrigation Management System, Penman, Hargreaves, and Ritchie. In this part of the study, the empirical models are calibrated using the standard FAO-56 PM ET0 values. The estimates of the neurofuzzy technique are also compared with those of the calibrated empirical models and artificial neural network (ANN) technique. Mean-squared errors, mean-absolute errors, and determination coefficient statistics are used as comparing criteria f...

Adaptive Neurofuzzy Computing Technique for Evapotranspiration Estimation

The potential of three different artificial neural network (ANN) techniques, the multi-layer perceptrons (MLPs), radial basis neural networks (RBNNs) and generalized regression neural networks (GRNNs), in modelling of reference evapotranspiration (ET0) is investigated in this paper. Various daily climatic data, that is, solar radiation, air temperature, relative humidity and wind speed from two stations, Pomona and Santa Monica, in Los Angeles, USA, are used as inputs to the ANN techniques so as to estimate ET0 obtained using the FAO-56 Penman–Monteith (PM) equation. In the first part of the study, a comparison is made between the estimates provided by the MLP, RBNN and GRNN and those of the following empirical models: The California Irrigation Management Information System (CIMIS) Penman (1985), Hargreaves (1985) and Ritchie (1990). In this part of the study, the empirical models are calibrated using the standard FAO-56 PM ET0 values. The estimates of the ANN techniques are also compared with those of the calibrated empirical models. Mean square errors, mean absolute errors and determination coefficient statistics are used as comparing criteria for the evaluation of the models' performances. Based on the comparisons, it is found that the MLP and RBNN techniques could be employed successfully in modelling the ET0 process. In the second part of the study, the potential of ANN techniques and the empirical methods in ET0 estimation using nearby station data is investigated. Among the models, the calibrated Hargreaves model is found to perform better than the others. Copyright © 2007 John Wiley & Sons, Ltd.

The potential of different ANN techniques in evapotranspiration modelling

Accurate estimation of both runoff and sediment yield is required for proper watershed management. Artificial neural network (ANN) models were developed, to predict both runoff and sediment yield on a daily and weekly basis, for a small agricultural watershed. A total of five models were developed for predicting runoff and sediment yield, of which three models were based on a daily interval and the other two were based on a weekly interval. All five models were developed both with one and two hidden layers. Each model was developed with five different network architectures by selecting a different number of hidden neurons. The models were trained using monsoon season (June to October) data of five years (1991–1995) for different sizes of architecture, and then tested with respective rainfall and temperature data of monsoon season (June to October) of two years (1996–1997). Training was conducted using the Levenberg–Marquardt backpropagation where the input and output were presented to the neural network a...

L. S. Reddy

Papers

Runoff and Sediment Yield Modeling using Artificial Neural Networks: Upper Siwane River, India