Research Information System
2th International Azerbaijan Congress on Life, Engineering, Mathematical, and Applied Sciences, Baku, Azerbaijan, 21 - 22 September 2025, pp.472-480, (Full Text)
Meteorological droughts, which occur due to deviations in the average precipitation amount, are the type of drought that living beings suffer from the most. Just as every part of the world is affected by this natural phenomenon, almost all regions of Türkiye are also impacted. Acıpayam is one of the regions located in western Türkiye that is affected by droughts. Therefore, monitoring and forecasting droughts in this region is paramount of important. In this study, the Acıpayam region was chosen as the study area, and monthly precipitation data from the meteorological station in the region covering the period 1967–2020 was used. Based on the obtained data, the Standardized Precipitation Index (SPI) values were first calculated and then analyzed using the Long Short-Term Memory Network (LSTM). Moreover, four different model input structures were created. In addition, to enrich the model performance results, Variational Mode Decomposition (VMD) was employed. To evaluate the model results, the correlation coefficient (r), the Nash–Sutcliffe efficiency (NSE), and the root mean square error (RMSE) were calculated for each model. According to the results, the best performance metrics were obtained in M04 (r=0.9271, NSE=0.9234, and RMSE=0.2762). For future drought forecasting studies, this model input structure should be preferred. This study will contribute to supporting decision-making authorities in determining drought-related policies in the region.