ICTP-EAIFR cordially invites you to a special seminar in hybrid format:

Title: GIS and Geophysics driven Machine Learning Model for predicting floods in Sub-Sahara Countries Case Study: Rwanda

Speaker: Mr. Jean Pierre Hitimana, University of Rwanda

When: April 18, 2024

Time: 5-6 pm (Kigali time)

Physical Venue: UR CST Campus, Einstein Building, ICTP-EAIFR, Fifth Floor

Zoom Link: Click here and Register

Abstract:

By taking into consideration geophysical parameters like the presence of thin aeration zone, occurrence of low permeability rocks, shallow aquicludes etc...are the main causes of flooding
processes. Geophysics and machine learning (ML) techniques methods open up a new way of doing further research by expending the current approaches.
This approach has important implications and has not yet been directly observed in modeling to predict floods with high accuracy.
This talk will describe the underlying Geophysics and GIS applied to this research with focus on defining the problem statement, the objectives and algorithms proposed to predict floods with high accuracy using machine learning.

Biography:

Mr. Jean Pierre Hitimana is a PhD Student Candidate at the University of Rwanda and he is doing PhD studies by Research in the School of ICT at College of Science and Technology of the University of Rwanda. He did his undergraduate studies at former Kigali Institute of Science and Technology (KIST) and a Master Degree at University of Rwanda. He joined the Centre of Geographic Information Systems and Remote Sensing as GIS Officer of University of Rwanda in 2006 until now. He is a visiting lecturer at College of Arts and Social Science (CASS) of University of Rwanda where He teaches Graphic Design, ICT and Digital Publishing. He hold the Certificate in Research Data Science and Data Visualization, 6-17 August 2018 from ICTP-Trieste Italy, Certificate in Data Science Applied to Climate Data, 20-24 August 2018 from ICTP-Trieste Italy and a Certificate in Processing Raster Data Using ArcGIS, 1 August 2016.

His main research interests are GIS and Geophysics applied to Machine Learning for solutions.