Developing an ANN Based Streamflow Forecast Model Utilizing Data-Mining Techniques to Improve Reservoir StreamflowPrediction Accuracy: A Case Study

This study illustrates the benefits of data pre-processing through supervised data-mining techniques and utilizing thoseprocessed data in an artificial neural networks (ANNs) for streamflow prediction. Two major categories of physicalparameters such as snowpack data and time-dependent trend indices were utilized as predictors of streamflow values.Correlation analysis of different models indicate that, for the period of January to June, using fewer predictors led tosimpler modeling with equivalent accuracy on daily prediction models. This did not hold in all periods. For monthlyprediction models, accuracy was improved compared to earlier works done to predict monthly streamflow for the samecase of Elephant Butte Reservoir (EB), NM. Overall, superior prediction performance was achieved by utilizing dataminingtechniques for pre-processing historical data, extracting the most effective predictors, correlation analysis,extracting and utilizing combined climate variability indices, physical indices, and employing several developed ANNs fordifferent prediction periods of the year.