Maedeh Behifar - Department of Remote Sensing and GIS, Faculty of Geography, University of Tehran, Tehran, Iran
Ata Abdollahi Kakroodi - Department of Remote Sensing and GIS, Faculty of Geography, University of Tehran, Tehran, Iran
Majid Kiavarz - Department of Remote Sensing and GIS, Faculty of Geography, University of Tehran, Tehran, Iran
Ghasem Azizi - Department of Geography, Faculty of Geography, University of Tehran, Tehran, Iran

Due to different influencing factors, drought is difficult to forecast. Hence, robust and accurate forecasting methods are needed. A method was presented to improve the accuracy of drought forecasts using the wavelet neural network and proximity information in satellite images. Satellite precipitation and evapotranspiration data were applied to calculate drought indices. And the drought intensity in different months of the following year was forecasted using the wavelet neural network method. To increase forecast accuracy and discriminate random changes from drought signals, proximity data in satellite images were used to forecast drought at the East Isfahan climate station. The results showed that the wavelet neural network method is able to forecast drought with reasonable accuracy. Also, using adjoining data may improve forecasting precision. The correlation between the target and predicted values was ۰.۶۷۵.

Drought, Forecasting, wavelet, Artificial Neural Network, Satellite image