Computer Scientist to Develop Code to Implement Sampling Plan

GLD is Looking to Fill a 6 Month Full-time Position to Develop Code to Implement Sampling Plans 

Keywords: applied machine learning, satellite imagery, geographic data 


Project Motivation 

The Governance and Local Development Institute (GLD), located within the Department of Political Science at the University of Gothenburg, is a research program aiming to explain variation in governance and local development to promote human welfare globally.  

The program’s flagship project is the Local Governance Process Indicators (LGPI) which provides a new approach to measuring, analyzing, and improving local governance. The LGPI employs household surveys to gather micro-level data from communities, including data on experience, perception, and satisfaction regarding cross-cutting governance issues: specifically, batteries for health, education, security, voice and participation, and governance metrics. Thus, the LGPI collects, assesses, and benchmarks detailed information on local governance and service delivery issues. You can read more about the LGPI on our website and in the concept note. 

The method used to perform the sampling for the LGPI is critical. The observations need to be clustered at a very local level so that meaningful and reliable local-level indicators can be computed. To provide comprehensive governance measures, the sampling also needs to ensure that hard-to-reach populations (based on geography) are not left out; however, this needs to be balanced with survey implementation costs (you don’t want enumerators wandering around unpopulated areas). Furthermore, users of the LGPI may want to implement their surveys on a specific subset of a country(s). 

Thus, ensuring the quality of the LGPI data and resulting indicators, requires that the sampling is performed appropriately and consistently. Therefore, GLD is looking to recruit someone for 6 months, full-time, to work on the development of an R Package (or an equivalent) that can be used by scholars, governments, and other practitioners to implement various sampling plans that utilize satellite imagery and geographic data.  


Project Description 

In collaboration with the LGPI researchers and GLD statistician, you will:  

  • Develop/apply a model that can determine if a satellite image shows a populated or unpopulated area. 

  • Develop an R package (or an equivalent) that implements the LGPI sampling plan (and minor variants). This will include:  

  • Allowing the user to specify the country. 

  • Allowing the user to specify a subset/region of the country to sample (via a shapefile). 

  • Allowing the user to specify the Primary Sampling Unit (PSU). For example, the LGPI uses the square kilometer as the PSU, but others might want to use enumeration areas.  

  • Using satellite imagery data to filter out unpopulated areas in the specified sampling region. 

  • Implementing the multi-stage, probability proportional to size (population) sampling on the filtered areas.  

  • Returning sample materials such as reports, data files, and maps.   




Required Skillset 

To achieve the goals of the project, you must:  

  • Have prior experience working with satellite images 

  • Have previous experience developing and applying machine learning models 

  • Previous experience developing code packages for publication, that is, developing code to be used by someone other than yourself.   

While not necessary, the following skills are meritorious:  

  • Previous experience working in an interdisciplinary team 

  • Education or experience with statistical sampling 

  • Previous experience developing user interfaces for code 


Application Requirements 

Please include the following documents in your application: 

  • Cover Letter 

  • CV 

  • One past example of a project report 

  • A list of at least three references (with contact information)   

Apply for this position via the University of Gothenburg's recruitment system: 

Applications close at 23:59 CEST on May 27, 2024. For more information, please contact Erica Ann Metheney at 


Information for International Applicants

Choosing a career in a foreign country is a big step. Thus, to give you a general idea of what we and Gothenburg have to offer in terms of benefits and life in general for you and your family/spouse/partner, please visit:

The University works actively to achieve a working environment with equal conditions, and values the qualities that diversity brings to its operations.

Salaries are set individually at the University.

In accordance with the National Archives of Sweden’s regulations, the University must archive application documents for two years after the appointment is filled. If you request that your documents are returned, they will be returned to you once the two years have passed. Otherwise, they will be destroyed.

In connection to this recruitment, we have already decided which recruitment channels we should use. We therefore decline further contact with vendors, recruitment, and staffing companies.