Integrated Artificial Intelligent with RS and GIS for Long-Term Drought Prediction

Abstract

Abstract The accurate evaluation of drought plays an urgent role in the optimal solution for future development. The present research aimed to predict and assess drought in Nineveh governorate northwestern Iraq by integrated a fuzzy logic procedure with Geographical Information System (GIS) environment. Primary meteorological data for six stations were used in this study. Vegetation cover changes were detected using remote sensing analysis in which there was a decrease in the vegetation cover’s area by 17.7% from 592.3 km 2 in the year 1992 to 487.46 km 2 in the year 2016. Standardized Precipitation Index (SPI) as a proxy for drought conditions was simulated by developing the model of Adaptive Neuro-Fuzzy Inference System (ANFIS) as an artificial intelligent approach where its performance reached to 82% when evaluating the Nash-Sutcliffe coefficient and Root Mean Square Error (RMSE)as performance criteria. However, the long-term meteorological drought was an assessment where the results show that the drought level will intensify in a future by 10.1% with more successive droughts levels. Those results were clarified through developing spatial distribution map for long-term drought simulation by employing the (GIS) as a database to develop future plans for the study area.