Overview
Postdoc to develop physically consistent super-resolution downscaling deep learning models for atmospheric composition (R2) at Barcelona Supercomputing Center (BSC-CNS).
Responsibilities
* Develop and implement deep learning architectures (e.g., CNNs, GANs, diffusion models) for spatial super-resolution of atmospheric composition fields generated by atmospheric chemistry models
* Train and validate models using historical high-resolution observational datasets and CTM outputs
* Integrate physical constraints and uncertainty estimation within the machine learning workflow
* Collaborate closely with atmospheric scientists, and participate in the intellectual life of the group
* Present model developments and research findings, contribute to scientific publications, and other duties as assigned
Qualifications / Requirements
* Education
o PhD (or MSc with strong experience) in computer science, data sciences, Earth sciences, applied mathematics, physics, or related discipline
* Essential Knowledge and Professional Experience
o Strong background in deep learning, especially in image super-resolution or geospatial applications
o Experience with ML frameworks (e.g., PyTorch, TensorFlow) and high-performance computing environments
o Demonstrated expertise in designing and implementing machine learning models from scratch
o Excellent programming skills in Python
* Additional Knowledge and Professional Experience
o Experience working in HPC environment (including bash)
o Experience in Earth sciences will be valued
o Experience with graph neural networks will also be valued
o Experience with revision control systems (e.g., SVN or Git)
* Competences
o Very good interpersonal skills
o Fluency in English
o Excellent written and verbal communication skills
o Ability to take initiative, prioritize and work under set deadlines
o Ability to work both independently and within a team
Context and Mission
We are looking for software atmospheric modeler to join the Atmospheric Composition group within the Earth Sciences department at the BSC-CNS. The AC group aims at better understanding and predicting the spatiotemporal variations of atmospheric pollutants along with their effects upon air quality, weather and climate. The group develops and applies numerical models over multiple scales, from weather to climate and from global to urban scales. MONARCH, a cutting-edge atmospheric composition model, is part of the Copernicus CAMS system and is used in both research and operational activities. This activity is part of a large EU initiative on modernization and digitalization of observation networks.
Key Duties
* Develop and implement deep learning architectures (e.g., CNNs, GANs, diffusion models) for spatial super-resolution of atmospheric composition fields generated by atmospheric chemistry models
* Train and validate models using historical high-resolution observational datasets and CTM outputs
* Integrate physical constraints and uncertainty estimation within the machine learning workflow
* Collaborate closely with atmospheric scientists, and participate to the intellectual life of the group
* Present model developments and research findings, contribute to scientific publications, and other duties as assigned
Conditions
* The position will be located at BSC within the Earth Sciences Department
* Full-time contract (37.5h/week) with a stimulating environment, state-of-the-art infrastructure, flexible hours, training plan, and benefits
* Duration: Open-ended contract linked to project and budget duration
* Holidays: 23 paid vacation days plus 24th and 31st December per collective agreement
* Salary: competitive and commensurate with qualifications and Barcelona cost of living
* Starting date: Pending
Applications procedure
All applications must be submitted via the BSC website and contain:
* A full CV in English including contact details
* A cover/motivation letter with a statement of interest in English, clearly specifying the areas/topics of interest. Additionally, two references for further contacts must be included.
Equity, Diversity and Inclusion: We promote equity, diversity and inclusion and encourage applications from underrepresented groups. We are an equal opportunity employer.
Deadline: The vacancy will remain open until a suitable candidate has been hired. Applications will be regularly reviewed and potential candidates will be contacted.
OTM-R principles for selection processes are followed, and a gender-balanced recruitment panel is formed for each vacancy.
#J-18808-Ljbffr