Amirpasha Mozaffari

Amirpasha Mozaffari
Forschungszentrum Jülich · Jülich Supercomputing Centre (JSC)

Master of Science
working on a reproducible workflow for ML application in the earth system, just defended my PhD :)

About

21
Publications
3,766
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
101
Citations
Introduction
My research focuses on applying data and workflow management in earth system sciences in HPC systems. I am mainly working on facilitating machine learning application in Geosciences utilizing the Big Data and HPC resources. I advocate for open science and open research data, and I am involved in multiple initiatives.
Additional affiliations
June 2019 - present
Forschungszentrum Jülich
Position
  • Manager
February 2015 - June 2019
Forschungszentrum Jülich
Position
  • PhD Student
June 2014 - November 2014
Forschungszentrum Jülich
Position
  • Master's Student
Education
February 2015 - January 2022
RWTH Aachen University
Field of study
  • Near surface Geophysics
September 2011 - December 2014
Universität Stuttgart
Field of study
  • Water resource engineering (WAREM)
September 2007 - September 2011
Amirkabir University of Technology
Field of study
  • Mining engineering

Publications

Publications (21)
Article
Full-text available
The recent hype about artificial intelligence has sparked renewed interest in applying the successful deep learning (DL) methods for image recognition, speech recognition, robotics, strategic games and other application areas to the field of meteorology. There is some evidence that better weather forecasts can be produced by introducing big data mi...
Article
Full-text available
Artificial intelligence for air quality IntelliAQ is an ERC Advanced Grant project to explore the application of cutting-edge machine learning techniques to global air quality data in combination with high resolution geospatial and weather data. It combines novel data management and data science approaches to build the foundation for innovative air...
Preprint
Full-text available
Numerical weather prediction (NWP) models solve a system of partial differential equations based on physical laws to forecast the future state of the atmosphere. These models are deployed operationally, but they are computationally very expensive. Recently, the potential of deep neural networks to generate bespoken weather forecasts has been explor...
Article
Full-text available
Machine learning (ML) applications in weather and climate are gaining momentum as big data and the immense increase in High-performance computing (HPC) power are paving the way. Ensuring FAIR data and reproducible ML practices are significant challenges for Earth system researchers. Even though the FAIR principle is well known to many scientists, r...
Article
Full-text available
The FAIR principles have been accepted globally as guidelines for improving data-driven science and data management practices, yet the incentives for researchers to change their practices are presently weak. In addition, data-driven science has been slow to embrace workflow technology despite clear evidence of recurring practices. To overcome these...
Poster
Full-text available
Designing the last mile of FAIRness in the multi-service data infrastructure of the Tropospheric Ozone Assessment Report (TOAR-II) and Artificial Intelligence for Air Quality (IntelliAQ)
Thesis
Full-text available
High-resolution imaging of the subsurface improves our understanding of thesubsurface flow and solute transportation that can directly help us protectgroundwater resources and remediate contaminated sites. The ground penetratingradar (GPR) is a useful non/minimal invasive method that consists of a transmitter(Tx) unit that emits electromagnetic (EM...
Article
Data harmonization and documentation of the data processing are essential prerequisites for enabling Canonical Analysis Workflows. The recently revised Terabyte-scale air quality database system, which the Tropospheric Ozone Assessment Report (TOAR) created, contains one of the world's largest collections of near-surface air quality measurements an...
Presentation
Full-text available
This presentation provides an overview of our efforts to link the DO3SE model to the TOAR database. Links: https://www.sei.org/projects-and-tools/tools/do3se-deposition-ozone-stomatal-exchange/ https://igacproject.org/activities/TOAR
Chapter
In this article, we present JUWELS Booster, a recently commissioned high-performance computing system at the Jülich Supercomputing Center. With its system architecture, most importantly its large number of powerful Graphics Processing Units (GPUs) and its fast interconnect via InfiniBand, it is an ideal machine for large-scale Artificial Intelligen...
Article
For high-resolution crosshole ground-penetrating radar (GPR) tomography, a wide-range of ray path angles are required, including transmitter-receiver pairs with high-angles. However, artefacts have been observed in the inverted GPR tomograms when high-angle data were incorporated in ray-based inversion (RBI) tomography, due to not well-understood i...
Preprint
Full-text available
In this article, we present JUWELS Booster, a recently commissioned high-performance computing system at the J\"ulich Supercomputing Center. With its system architecture, most importantly its large number of powerful Graphics Processing Units (GPUs) and its fast interconnect via InfiniBand, it is an ideal machine for large-scale Artificial Intellig...
Article
Full-waveform inversion (FWI) of cross-borehole Ground Penetrating Radar (GPR) data is a technique with the potential to investigate subsurface structures. Typical FWI applications transform the 3D measurements into a 2D domain via an asymptotic 3D to 2D data transformation, widely known as a Bleistein filter. Despite the broad use of such a transf...
Poster
Full-text available
Containers stock a single code along with its dependencies so it can run reliably and efficiently in different computing environments. They promise the same level of isolation and security as a virtual machine and a higher degree of integration with the host operating system (OS). The main benefits of containers are, from a user perspective: greate...
Poster
Full-text available
IntelliAQ is a European project aiming to develop novel approaches for the analysis and synthesis of global air quality data based on deep neural networks. A core element of the project’s strategy is the linkage of several different types of data, including time-series of air quality observations, high-resolution geospatial data, high-resolution we...
Poster
Full-text available
GPR full-waveform inversion (FWI) is a challenging high-resolution inversion approach for GPR data that can return simultaneously the electromagnetic wave velocity and attenuation. In recent years, crosshole GPR FWI has been applied to a wide range of applications, where it has been mostly implemented in the computationally attractive 2D domain. Th...
Conference Paper
2D crosshole ground penetrating (GPR) full-waveform inversion (FWI) has shown superior resolution compared to ray-based inversion tomograms for synthetic and experimental data. To invert measured 3D data with a 2D model that has a reduced geometrical spreading and assumes infinite source and receiver dimensions perpendicular to the 2D inversion pla...
Conference Paper
Full-text available
Over the last years, crosshole GPR full-waveform inversion has proved to be a powerful tool to map and characterize aquifers with a decimeter-scale resolution. Especially the detection of small-scale high contrast layers that can be related to zones of high porosity and zones of preferential flow improved our understanding of the propagation of the...
Poster
Full-text available
Electrical Impedance Tomography (EIT) is a sophisticated non-invasive tool to investigate the subsurface in engineering and environmental studies. To increase the depth of investigation, EIT measurements can be made in boreholes. However, the presence of the borehole may affect EIT measurements. Here, we aim to investigate the effect of different b...
Thesis
Full-text available
Electrical Impedance Tomography (EIT) is a sophisticated non-invasive tool to investigate the subsurface in engineering and environmental studies. To increase the depth of investigation, EIT measurements can be made in boreholes. However, the presence of the borehole may affect EIT measurements. Here, we aim to investigate the effect of different b...

Network

Cited By

Projects

Projects (3)
Project
The DeepRain project is a collaboration among the Jülich Supercomputing Centre (JSC) at Forschungszentrum Jülich, the German Weather Service (DWD), the Universities of Osnabrück and Bonn and the Jacobs University in Bremen. During the three years of funding from BMBF, the partners investigate how modern methods of machine learning can be applied to improve precipitation forecasts in Germany. Precise predictions of rain and snow with a reliable indication of the expected amount of precipitation are still an extreme challenge for weather modelling, especially at the local scales where they are most relevant.
Project
The IntelliAQ project develops a novel approach to make concurrent use of global air quality data together with different earth system data types and applies cutting edge machine learning techniques to improve the analysis of air quality data globally. https://www.intelliaq.eu/
Project
Increase the reliability of the crosshole GPR Full-waveform inversion by utilizing detailed 3D modeling