/pdf/remote-sensing-of-the-environment-4yfxjaaswe.pdf

Remote sensing of the environment

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

https://ira.lib.polyu.edu.hk/bitstream/10397/1314/3/JH8.pdf

A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series

17 18 Lin Qiu 19 Professor, Institute of environmental & municipal engineering, North China Institute of Water 20 Conservancy and Hydroelectric power, ZhengZhou, 450011, P.R.Ch 21 22 Abstract. Developing a hydrological forecasting model based on past records is crucial to 23

A comparison of performance of several artificial intelligence

http://romisatriawahono.net/lecture/rm/survey/machine%20learning/Raghavendra%20-%20SVM%20for%20Hydrology%20-%202014.pdf

Support vector machine applications in the field of hydrology: A review

Machine learning techniques are finding more and more applications in the field of forecasting. A novel regression technique, called Support Vector Machine (SVM), based on the statistical learning theory is explored in this study. SVM is based on the principle of Structural Risk Minimization as opposed to the principle of Empirical Risk Minimization espoused by conventional regression techniques. The flood data at Dhaka, Bangladesh, are used in this study to demonstrate the forecasting capabilities of SVM. The result is compared with that of Artificial Neural Network (ANN) based model for one-lead day to seven-lead day forecasting. The improvements in maximum predicted water level errors by SVM over ANN for four-lead day to seven-lead day are 9.6 cm, 22.6 cm, 4.9 cm and 15.7 cm, respectively. The result shows that the prediction accuracy of SVM is at least as good as and in some cases (particularly at higher lead days) actually better than that of ANN, yet it offers advantages over many of the limitations of ANN, for example in arriving at ANN's optimal network architecture and choosing useful training set. Thus, SVM appears to be a very promising prediction tool.

Flood stage forecasting with support vector machines

Real time operation studies such as reservoir operation, flood forecasting, etc., necessitates good forecasts of the associated hydrologic variable(s). A significant improvement in such forecasting can be obtained by suitable pre-processing. In this study, a simple and efficient prediction technique based on Singular Spectrum Analysis (SSA) coupled with Support Vector Machine (SVM) is proposed. While SSA decomposes original time series into a set of high and low frequency components, SVM helps in efficiently dealing with the computational and generalization performance in a high-dimensional input space. The proposed technique is applied to predict the Tryggevaelde catchment runoff data (Denmark) and the Singapore rainfall data as case studies. The results are compared with that of the non-linear prediction (NLP) method. The comparisons show that the proposed technique yields a significantly higher accuracy in the prediction than that of NLP.

/pdf/rainfall-and-runoff-forecasting-with-ssa-svm-approach-4mdemh75vt.pdf

Rainfall and runoff forecasting with SSA-SVM approach

In recognition of the non-linear relationship between storage and discharge existing in most river systems, non-linear forms of the Muskingum model have been proposed, together with methods to calibrate the model parameters. However, most studies have focused only on routing a typical hypothetical flood hydrograph characterized by a single peak. In this study, we demonstrate that the storage–discharge relationship adopted for the non-linear Muskingum model is not adequate for routing flood hydrographs in natural channels, which are often characterized by multiple peaks. As an alternative, an evolutionary algorithm-based modelling approach, i.e. genetic programming (GP), is proposed, which is found to route complex flood hydrographs accurately. The proposed method is applied for constructing a routing model for a channel reach along the Walla Walla River, USA. The GP model performs extremely well with a root-mean-square error (RMSE) of 0·73 m3 s−1 as against an RMSE of 3·26 m3 s−1 for routing the multi-peaked hydrograph. The advantage of GP lies in the fact that, unlike other models, it establishes the routing relationship in an easy and simple mathematical form. Copyright © 2007 John Wiley & Sons, Ltd.

Genetic programming approach for flood routing in natural channels

It is often necessary to have stage discharge curve extended (extrapolated) beyond the highest (and sometimes lowest) measured discharges, for river forecasting, flood control and water supply for agricultural/industrial uses. During the floods or high stages, the river may become inaccessible for discharge measurement. Rating curves are usually extended using log–log axes, which are reported to have a number of problems. This paper suggests the use of Support Vector Machine (SVM) in the extrapolation of rating curves, which works on the principle of linear regression on a higher dimensional feature space. SVM is applied to extend the rating curves developed at three gauging stations in Washington, namely Chehalis River at Dryad and Morse Creek at Four Seasons Ranch (for extension of high stages) and Bear Branch near Naselle (for extension of low stages). The results obtained are significantly better as compared with widely used logarithmic method and higher order polynomial fitting method. A comparison of SVM results with ANN (Artificial Neural Network) indicates that SVM is better suited for extrapolation.

Discharge Rating Curve Extension – A New Approach

Prediction of high magnitude flows is of interest in many hydrological applications such as operation of flood control reservoirs, flood forecasting and gated spillways. Of the various types of existing streamflow prediction approaches, data driven models (such as ANN) are increasingly being preferred over the traditional conceptual models due to their simplicity, fast speed and ease of use. For models that consider only historical streamflow data, an attempt has been made to design a robust model over a wide range of streamflow magnitudes. The model inputs are the immediate past streamflow data which generally do not predict the typically high flows well, particularly for large lead times. In this study, the flow range is divided into three regions (low, medium and high flow regions) and the attributes are decided based on the underlying hydrological process of the flow region. A flow forecasting model is applied for each flow region, using only the historical streamflow data as input. The proposed approach is implemented in Tryggevaelde Catchment (Denmark) for 1- and 3-lead days, using the Support Vector Machine (SVM), which yields promising results, particularly for high flows in a 3-lead day model.

Chandrasekaran Sivapragasam

Papers

Flood stage forecasting with support vector machines

Rainfall and runoff forecasting with SSA-SVM approach

Genetic programming approach for flood routing in natural channels

Discharge Rating Curve Extension – A New Approach

Flow categorization model for improving forecasting