Cities on the Aegean and Mediterranean coasts of Turkey usually receive heavy rainfall during autumn and winter as a result of cyclogenesis during this period. The most recent flash flood to have occurred in this region was in the city of Bodrum, located in the Mugla Province, on September 23, 2015. The flood event affected thousands of houses and caused destructive road and other infrastructural damages. The aim of this research is to analyse the extreme precipitation events building up to flash floods in the Bodrum Region of Turkey and to design a flash flood forecasting system issuing timely and accurate flood warnings in order for operational measures to be put in action. For this purpose, spatiotemporal kriging was first applied to reconstruct the extreme precipitation event leading to the flood using precipitation data from 19 meteorological stations located in the Mugla Province. A simple Artificial Neural Network was then developed to predict floods in the Bodrum Region, using the reconstructed data from the kriging analysis.