Academic Positions

PhD student position: Developing AI architectures for extreme weather events forecasting.

Department of Earth and Planetary Science, Weizmann Institute of Science, Israel

Responsibilities:

Develop and explore AI architectures for extreme weather events forecasting, driven by remote sensing and in-situ data, to replace theory-driven climate models.

Explore explainable AI approaches to gain a scientific understanding of the weather events' precursor processes and their physical patterns.

Identify and define unique challenges for AI in the field of remote sensing-driven extreme weather forecast models, and study novel solutions.

Explore the integration of fundamental physical and atmospherical theory (e.g., Navier–Stokes equations) within deep learning architectures.

Study unsupervised approaches for learning concise representations of large-scale spatio-temporal meteorological data sequences for various tasks, including memory compression, clustering, augmentation, and generative purposes.

The candidate is expected to advance the group's current AI capabilities and to be a source of knowledge for various machine learning and data science tasks carried out by other group members, including R&D projects of a drone-based system. Candidates should be passionate about Earth and planetary sciences, working in a small research team, and collaborating with researchers from other disciplines.

Minimum Qualifications:

• MSc in computer sciences/ physics/ environmental science/ engineering /statistics/ related fields
• Proven experience (theory and hands-on) in Statistical modeling/ machine learning / deep learning.
• Experience in developing research projects, from data acquisition through analysis to prediction.
• Proven independence, self-management, and self-learning skills
• Proven teamwork skills

Preferred Background in:

• Experience with Python packages such as Scikit-learn, Pytorch, Tensorflow, etc. 
• Experience in the analysis of spatio-temporal data/ remote-sensing/ 
• monitoring networks.
• In-depth understanding of deep learning theory

The atmospheric transport of microorganisms can affect the biodiversity and health of global ecosystems. However, the processes influencing airborne bacterial communities' abundance, composition, and dispersal are still not well understood. We study the aerial microbiome to better understand the structure, function, and ecological drivers of airborne communities transported by dust-plumes in the Eastern Mediterranean. We use state-of-the-art aerosol sampling techniques, Next-generation sequencing (NGS), molecular biology and bioinformatics tools.

We are looking for highly motivated and curious PhD students and PostDocs to join our team.

Required qualifications:

• MSc. or PhD. degree in microbial ecology, environmental genomics or related fields.
• Experience in DNA/RNA extraction techniques.
• Experience in bioinformatic/biostatistical pipelines using R or Python.
• Knowledge on the analysis and interpretation of microbial community genomics data.

The following additional qualifications will be advantageous:

• Background in bioaerosol research or related fields.
• Knowledge on molecular biology and microbiology techniques (i.e., genomic sequencing, qPCR, flow cytometry, cell culturing).
• The generation of NGS sequencing libraries.

Please contact:

Prof. Yinon Rudich

yinon.rudich@weizmann.ac.il

Department of Earth and Planetary Sciences

Weizmann Institute of Science

Develop and explore AI architectures for extreme weather events forecasting, driven by remote sensing and in-situ data, to replace theory-driven climate models.

Explore explainable AI approaches to gain a scientific understanding of the weather events' precursor processes and their physical patterns.

Identify and define unique challenges for AI in the field of remote sensing-driven extreme weather forecast models, and study novel solutions.

Explore the integration of fundamental physical and atmospherical theory (e.g., Navier–Stokes equations) within deep learning architectures.

Study unsupervised approaches for learning concise representations of large-scale spatio-temporal meteorological data sequences for various tasks, including memory compression, clustering, augmentation, and generative purposes.

The candidate is expected to advance the group's current AI capabilities and to be a source of knowledge for various machine learning and data science tasks carried out by other group members, including R&D projects of a drone-based system. Candidates should be passionate about Earth and planetary sciences, working in a small research team, and collaborating with researchers from other disciplines.

Minimum Qualifications:

• MSc in computer sciences/ physics/ environmental science/ engineering /statistics/ related fields
• Proven experience (theory and hands-on) in Statistical modeling/ machine learning / deep learning.
• Experience in developing research projects, from data acquisition through analysis to prediction.
• Proven independence, self-management, and self-learning skills
• Proven teamwork skills

Preferred Background in:

• Experience with Python packages such as Scikit-learn, Pytorch, Tensorflow, etc. 
• Experience in the analysis of spatiotemporal data/remote sensing/ 
• monitoring networks.
• In-depth understanding of deep learning theory

The atmospheric transport of microorganisms can affect the biodiversity and health of global ecosystems. However, the processes influencing airborne bacterial communities' abundance, composition, and dispersal are still not well understood. We study the aerial microbiome to better understand the structure, function, and ecological drivers of airborne communities transported by dust-plumes in the Eastern Mediterranean. We use state-of-the-art aerosol sampling techniques, Next-generation sequencing (NGS), molecular biology and bioinformatics tools.

We are looking for highly motivated and curious PhD students and PostDocs to join our team.

Required qualifications:

• MSc. or PhD. degree in microbial ecology, environmental genomics or related fields.
• Experience in DNA/RNA extraction techniques.
• Experience in bioinformatic/biostatistical pipelines using R or Python.
• Knowledge on the analysis and interpretation of microbial community genomics data.

The following additional qualifications will be advantageous:

• Background in bioaerosol research or related fields.
• Knowledge on molecular biology and microbiology techniques (i.e., genomic sequencing, qPCR, flow cytometry, cell culturing).
• The generation of NGS sequencing libraries.

Please contact:

Prof. Yinon Rudich

yinon.rudich@weizmann.ac.il

Department of Earth and Planetary Sciences

Weizmann Institute of Science

Our group studies clouds and their role in the climate system. We are interested in the dynamic and microphysical processes within clouds and cloud fields, cloud organization, atmospheric radiation transfer, and clouds' climatic trends. We are exploring the emergence of pattern formation within cloud fields using mathematical models and AI.

We develop analytical models, use numerical models, and analyze surface and satellite observations. Additionally, we are developing new AI approaches to study the emergence of patterns in self-organizing systems.

If you are interested in these topics and have a solid background in physics, geophysics, atmospheric sciences, and/or mathematics, you are welcome to contact us.