Menu

Hi! I am Amirpasha
Geoscience ML / AI HPC Open data & FAIRness Workflow design
Data manager in Jülich Supercomputing Centre (JSC),
Research Center Jülich, Germany
Interests
- Data Science
- Geosciences
- Exascale machines / HPC
- Open science
- Data Management
- Environmental sciences
Professional
Experience
Jun 2019 - Present , Germany
- Data pipeline and workflow management in HPC
- Machine learning application in Geosciences
- FAIR and reproducible digital object in Earth System Sciences
Feb 2015 - Jun 2019 , Germany
- Numerical and statistical analysis of complex environmental data (Synthetic and Experimental data)
- Development and optimization of high-performance numerical modeling algorithms
- Developing analytical solutions for shortcomings in practical environmental problems
Jun 2014 - Jan 2015 , Germany
- Effect of borehole design on electrical impedance tomography measurements
Talks & Posters
RDA plenary 15 - 2020
Virtual poster session:
FAIRness in Air Quality and Weather forecast
Poster session FAIRness in Air Quality and Weather forecast
NIC symposium 2020
On the use of containers for machine learning and visualization workflows on JUWELS
Poster - Here PyStager in ESM forum 2020
Presentation about PyStager application for pre/post processing and staging on HPC
Presentation - Here CWFR workshop June 2021
CWFR Working Meeting on Jupyter Usage / Use case in Weather forecast by DeepRain project
Poster - Here
Previous
Next
Projects

DeepRain
Deep Rain is a project that aims to advance the possibility of using deep learning to improve small-scale rain forecast. I am responsible for staging more than 450 TB data weather data for further processing with the HPC system.

IntelliAQ
IntelliAQ is a European project (ERC grant) that aims to use deep learning to provide services for air quality forecasting. I am responsible for data preparation and staging.

Maelstrom
MAELSTROM is a large-scale R&D project, aiming to fundamentally improve weather and climate prediction. It will join the powers of HPC and ML to cope with the extreme complexity inherent in weather and climate forecasts.