Deep Learning based Multiple Regression to Predict Total Column Water Vapor (TCWV) from Physical Parameters in West Africa by using Keras Library

• DOI: 10.5121/ijdkp.2019.9602
• Publication Date: 2019-12-09T11:01:41Z
• Authors: Daouda DIOUF; Awa Niang; Sylvie Thiria
• Keywords: Dew point

Total column water vapor is an important factor for the weather and climate.This study apply deep learning based multiple regression to map TCWV with elements that can improve spatiotemporal prediction.In this study, we predict use of ERA5 fifth generation ECMWF atmospheric reanalysis global climate.We appropriate algorithm using Keras library nonlinear prediction between Column predictors as Mean sea level pressure, Surface Sea surface temperature, 100 metre U wind component, V 10 2 dew point temperature.The results obtained permit build a predictor which modelling mean abs error (MAE) equal 3.60 kg/m coefficient determination R 0.90.