Post-Doc in Atmospheric Science and Machine Learning

You will contribute to the newly funded COGNITO project (carbon monoxide (CO) Global aNalysis, source Identification and emission quantification using TROPOMI Observations). COGNITO aims to develop the first global, satellite-based system for detecting and quantifying carbon monoxide emissions from major urban areas and industrial facilities, with a particular focus on the iron and steel sector. By using TROPOMI observations with advanced machine learning techniques, the project will provide independent information on emission patterns and support efforts to improve emission inventories and evaluate decarbonization strategies worldwide.

You will become part of the Earth Science Group (ESG) at SRON. The ESG consists of approximately 40 scientists, postdoctoral researchers, and PhD students working on the interpretation of satellite observations, atmospheric modelling, data science, and the development of future Earth observation missions. You will join a research team specializing in the detection and quantification of atmospheric emissions using satellite observations, atmospheric transport modeling, and machine learning. The team has pioneered the use of satellite observations for identifying methane super-emitters and quantifying emissions from industrial and urban sources worldwide.

Within the COGNITO project, you will apply novel machine learning approaches to detect CO plumes in global satellite observations from TROPOMI and possibly complemented by Sentinel-5. Building on successful methodologies previously developed for methane super-emitter detection, you will create a global database of CO emission events and investigate the emission source rates from hundreds of industrial facilities and urban regions worldwide.

Your work will include:

• Apply existing machine learning algorithms for automated detection of CO plumes in satellite observations
• Building a global catalogue of CO emission events from 2018 onwards
• Quantifying emissions from cities and iron and steel production facilities using inhouse quantification tools
• Evaluating temporal variability in emissions, including seasonal cycles, operational changes, and potential signatures of industrial decarbonization efforts
• Assessment of emission quantification tools using atmospheric transport modeling
• Comparing satellite derived emissions with bottom up inventories and reporting systems
• Publishing results in leading international scientific journals and presenting your work at conferences and stakeholder meetings

The project offers a unique opportunity to work at the intersection of atmospheric science, machine learning, satellite remote sensing, and climate policy.

We are looking for an ambitious, highly motivated, and result driven scientist with a PhD in atmospheric sciences or a similar degree, with experience in the interpretation of atmospheric (e.g. satellite, aircraft etc.) observations and machine learning applications. Strong programming and data analytics skills are also expected. Experience with research on atmospheric CO, transport modelling and/or flux inversions is considered an asset. A highly developed proficiency in written and oral English is essential, and the candidate should be capable of working both independently and in a team.

The position we offer at SRON is full-time for a period of two years with the possibility of a two-year extension in which you will be employed by NWO-I, The Netherlands Organization for Scientific Research Institutes. The salary will be in accordance with NWO salary scale 10, commensurate with your education and experience, be for a maximum of €5.758,- gross per month on a full-time basis. 

NWO-I has good secondary employment conditions such as: 

• An end-of-year bonus of 8,33% of the gross yearly salary;
• A holiday allowance of 8% of the gross yearly salary;
• 42 days of vacation leave per year on a full-time basis;
• Compensation for commuting expenses;
• An excellent pension scheme;
• Options for (additional) personal development;
• Excellent facilities for parental leave;
• Ample training opportunities;
• Possibility of flexible working hours;