Ammar Kheder

Doctoral Researcher in Computational Engineering

LUT University — Atmospheric Modelling Centre (AMC-Lahti)

I develop neural network architectures that explicitly encode atmospheric physics — terrain-atmosphere interactions, advective transport — to push spatial resolution and forecast accuracy for air quality and Earth system prediction. Supervised by Prof. Michael Boy and Assoc. Prof. Zhi-Song Liu.

I have hands-on experience running large-scale distributed training on the LUMI supercomputer, scaling experiments up to 1,024 AMD MI250X GPUs for training vision transformer models on high-resolution atmospheric reanalysis data.

MSc in Engineering (Big Data & AI) from EiCnam Paris, with a one-year apprenticeship at INRIA Bordeaux within the Mnemosyne team, co-led by Frédéric Alexandre and Nicolas Rougier.

GitHub Scholar LinkedIn

News

Publications

2026

TopoFlow: Physics-guided Neural Networks for High-Resolution Air Quality Prediction

A. Kheder et al.

2025

Deep Spatio-Temporal Neural Network for Air Quality Reanalysis

A. Kheder et al. — SCIA 2025

Experience

2024 – now

Junior Researcher & Teaching Assistant

LUT University, Lahti, Finland

2023 – 2026

CEO — Wabel Group

AI services & web development

2021 – 2022

Research Engineer (Apprenticeship)

INRIA Bordeaux — Mnemosyne team (F. Alexandre & N. Rougier)

2021 – 2023

Volunteer Firefighter

Sapeurs-pompiers des Deux-Sèvres

Education

2024 – now

Ph.D. Computational Engineering

LUT University, Finland

2021 – 2024

MSc Engineering — Big Data & AI

EiCnam Paris — Apprenticeship at INRIA Bordeaux (Mnemosyne team)

2019 – 2021

Bachelor — Data Science

BUT Niort — Statistics, Big Data, Business Intelligence & Data Science