Artificial neural network-based drought forecasting using a nonlinear aggregated drought index

[thumbnail of Manuscript.pdf]
Manuscript.pdf - Accepted Version (1MB)
Restricted to Repository staff only

Barua, Shishutosh, Ng, A. W. M and Perera, B. J. C (2012) Artificial neural network-based drought forecasting using a nonlinear aggregated drought index. Journal of Hydrologic Engineering, 17 (12). pp. 1408-1413. ISSN 1084-0699 (print) 1943-5584 (online)


Drought forecasting plays an important role in the planning and management of water resources systems, especially during dry climatic periods. In this study, a nonlinear aggregated drought index (NADI) was developed first to classify the drought condition of a catchment considering all significant hydrometeorological variables that have effects on droughts. An artificial neural network (ANN)—based drought forecasting approach was then developed by using the time series of the NADI to forecast NADI values. In forecasting future drought conditions, the NADI produces the overall dryness within the system as compared to the traditional forecasting of rainfall deficiency, which considers only the meteorological droughts. Two ANN forecasting models, namely a recursive multistep neural network (RMSNN) and a direct multistep neural network (DMSNN), were developed in this study. Overall, these models were capable of forecasting drought conditions well for up to 6 months of future forecasts, which were statistically significant at the 1% level. Moreover, it was found that both models showed the same performance for 1-month lead-time forecasts. The RMSNN model gave slightly better forecasts than the DMSNN model for lead times of 2–3 months, and the DMSNN model produced slightly better forecasts than the RMSNN model for forecast lead times of 4–6 months. Beyond the forecast lead time of 6 months, poor forecasts were observed. A comparative study was conducted to investigate the effectiveness of ANN-based drought forecasting models over an autoregressive integrated moving average (ARIMA) model (which is a traditional linear stochastic model), and the results showed that both RMSNN and DMSNN models performed better than the ARIMA model.

Dimensions Badge

Altmetric Badge

Item type Article
DOI 10.1061/(ASCE)HE.1943-5584.0000574
Official URL
Subjects Historical > FOR Classification > 0999 Other Engineering
Historical > SEO Classification > 9609 Land and Water Management
Current > Division/Research > College of Science and Engineering
Keywords ResPubID26628, neural networks, catchments, Australia, artificial neural network, drought, drought forecasting, hydrometeorological variables, nonlinear aggregated drought index, Yarra River catchment, water resources management
Citations in Scopus 61 - View on Scopus
Download/View statistics View download statistics for this item

Search Google Scholar

Repository staff login