No abstract

With the operation and maintenance of streamgauging networks in many developing countries coming under increasing pressure through lack of funds and suitably trained personnel, greater reliance must be placed on procedures for transferring information from gauged to ungauged catchment areas. These approaches to generalizing hydrological variables, such as the quantiles of the frequency distributions of floods and low flows, are collectively referred to as regionalization methods. An important feature of these methods is the demarcation of hydrologically homogeneous regions. The latter may be regarded as an example of the wider problem of classification of data sets, for which a variety of modern informatic tools, such as artificial neural networks and fuzzy sets, may be invoked. Application of examples of these techniques to flood data for the southwest of England and Wales has demonstrated that classes may be defined by Representative Regional Catchments (RRCs), whose characteristics are hydrologically more appealing than those imparted merely by geographical proximity. The techniques employed, Kohonen networks and fuzzy c-means, are straightforward in application, and were found to identify broadly similar RRCs. The results indicate the feasibility of employing these methodologies on a country-wide basis.

Flood quantile estimation for ungauged catchment areas continues to be a routine problem faced by the practising Engineering Hydrologist, yet the hydrometric networks in many countries are reducing rather than expanding. The result is an increasing reliance on methods for regionalising hydrological variables. Among the most widely applied techniques is the Method of Residuals, an iterative method of classifying catchment areas by their geographical proximity based upon the application of Multiple Linear Regression Analysis (MLRA). Alternative classification techniques, such as cluster analysis, have also been applied but not on a routine basis. However, hydrological regionalisation can also be regarded as a problem in data mining -a search for useful knowledge and models embedded within large data sets. In particular, Artificial Neural Networks (ANNs) can be applied both to classify catchments according to their geomorphological and climatic characteristics and to relate flow quantiles to those characteristics. This approach has been applied to three data sets from the south-west of England and Wales; to England, Wales and Scotland (EWS); and to the islands of Java and Sumatra in Indonesia. The results demonstrated that hydrologically plausible clusters can be obtained under contrasting conditions of climate. The four classes of catchment found in the EWS data set were found to be compatible with the three classes identified in the earlier study of a smaller data set from south-west England and Wales. Relationships for the parameters of the at-site distribution of annual floods can be developed that are superior to those based upon MLRA in terms of root mean square errors of validation data sets. Indeed, the results from Java and Sumatra demonstrate a clear advantage in reduced root mean square error of the dependent flow variable through recognising the presence of three classes of catchment. Wider evaluation of this methodology is recommended.

The last decade has seen increasing interest in the application of Artificial Neural Networks (ANNs) for the modelling of the relationship between rainfall and streamflow. Since multi-layer, feed-forward ANNs have the property of being universal approximators, they are able to capture the essence of most input–output relationships, provided that an underlying deterministic relationship exists. Unfortunately, owing to the standardisation of inputs and outputs that is required to run ANNs, a problem arises in extrapolation: if the training data set does not contain the maximum possible output value, an unmodified network will be unable to synthesise this peak value. The occurrence of high magnitude, low frequency events within short periods of record is largely fortuitous. Therefore, the confidence in the neural network model can be greatly enhanced if some methodology can be found for incorporating domain knowledge about such events into the calibration and verification procedure in addition to the available measured data sets. One possible form of additional domain knowledge is the Estimated Maximum Flood (EMF), a notional event with a small but non-negligible probability of exceedence. This study investigates the suitability of including an EMF estimate in the training set of a rainfall–runoff ANN in order to improve the extrapolation characteristics of the network. A study has been carried out in which EMFs have been included, along with recorded flood events, in the training of ANN models for six catchments in the south west of England. The results demonstrate that, with prior transformation of the runoff data to logarithms of flows, the inclusion of domain knowledge in the form of such extreme synthetic events improves the generalisation capabilities of the ANN model and does not disrupt the training process. Where guidelines are available for EMF estimation, the application of this approach is recommended as an alternative means of overcoming the inherent extrapolation problems of multi-layer, feed-forward ANNs.

No abstract