Using artificial neural networks to predict monthly precipitation for the Cali river basin, Colombia

Abstract

Studying future precipitation behavior in river basins is essential for adequate land-use planning within them, as this will help to reduce vulnerability and mitigate disasters. This study analyzed climate change scenarios in the Cali river basin using a monthly rainfall database from 35 stations and General Circulation Models (GCMs) from the CMIP5 data set. Statistical downscaling was performed on the data at RCP 2.6, 4.5 and 8.5 using Artificial Neural Networks. Subsequently, the changes that would take place by the year 2100 were analyzed, establishing that the different scenarios show that over the coming years, rainfall will move from the upper areas to the middle and lower areas of the river basin.