项目介绍

2026年5月15日

Doctoral student in Earth Observation, Data Science, and AI for poverty estimation

Can satellites see poverty—and can AI help end it? We are looking for a Doctoral student to develop deep-learning methods that estimate living conditions across Africa from satellite imagery, and to compare different satellites for this purpose. Then, we use these estimates to evaluate how well villages and cities in Africa and beyond will achieve the Sustainable Development Goals. You will be mentored by an interdisciplinary team and join an internationally connected lab committed to your growth as a researcher.

About us

The Department of Computer Science and Engineering, a joint department of Chalmers and the University of Gothenburg, spans the breadth of computing disciplines. Our internationally visible research, strong industry links and diverse environment create a collaborative setting where ideas grow into real impact.

At the Division of Data Science and AI, we develop data-driven methods and AI solutions that support intelligent decisions across society, advancing machine-learning techniques from foundations to industrial and scientific applications.

About the Lab

The position is hosted by the AI and Global Development Lab based at the Division of Data Science and AI (DSAI), Department of Computer Science and Engineering, Chalmers University of Technology, and the Institute for Analytical Sociology, Linköping University. The Lab advances the use of AI for Social Good in pursuit of the Sustainable Development Goals.

The Lab brings together collaborators in Sweden, the United States, India, Chile, and the United Kingdom, and publishes in top interdisciplinary generalist journals, discipline-specific journals, and AI conferences. Because the work is highly interdisciplinary, we welcome candidates from a range of backgrounds and adapt our publication strategy to the doctoral student’s interests and trajectory.

Work environment

The Lab meets weekly, both in person and remotely, with collaborators across multiple time zones. The doctoral project is a collaboration mainly among the Department of Computer Science and Engineering at Chalmers, the Department of Earth Sciences at the University of Gothenburg, the Institute for Analytical Sociology at Linköping University (campus Norrköping), and the Department of Statistics at Harvard University. Occasional travel within Sweden and abroad is part of the role.

Leadership and mentorship

The Lab is headed by Adel Daoud, who will serve as the principal supervisor. Daoud is Professor of Computational Social Science at the Institute for Analytical Sociology (Linköping University) and Affiliated Associate Professor in Data Science and AI for the Social Sciences at Chalmers. He has previously held positions at Harvard University, the University of Cambridge, and the Alan Turing Institute.

The secondary supervisor is Ashkan Panahi, Associate Professor in the Division of Data Science and AI at Chalmers, who works at the interface of machine learning, signal processing, and statistical learning theory. Additional mentors include senior Lab members and collaborators such as Connor Jerzak (University of Texas at Austin), Mohammad Kakooei (Karlstad University), Devdatt Dubhashi (DSAI, Chalmers), Xiao-Li Meng (Harvard), and James Bailie (DSAI, Chalmers).

The Lab is committed to providing high-quality mentorship. The candidate is encouraged to explore the Journeys of Scholars podcast (created by Daoud), which features conversations about the trajectories, strategies, and advice of leading academics—available on YouTube and Spotify: https://www.youtube.com/@thejourneysofscholars8820

About the research project

About 900 million people—one third in Africa—still live in extreme poverty. Scholars and policymakers lack the fine-grained geo-temporal data needed to identify which communities are reaching the Sustainable Development Goals and which interventions are working.

The doctoral project, “Comparing Earth Observation and AI Methods for Sustainable Development,” is funded by the Swedish National Space Agency (SNSA / Rymdstyrelsen) and runs within the Lab’s Observatory of Poverty programme. The project pursues three objectives:

• Develop deep-learning methods that estimate multidimensional poverty from Sentinel-2 satellite imagery of African communities over time and space.
• Compare the quality and computational cost of poverty estimates produced from satellites with different resolutions—Pléiades (2 m), Sentinel-2 (10 m), and Landsat (30 m)—to identify the optimal trade-off between precision and cost.
• Apply AI explainability methods to understand what visual features drive the model’s poverty predictions, and to build trust in earth-observation-based estimates for policy use.

The doctoral student will lead all three work packages in close collaboration with the supervision team and contribute to the ObservatoryOfPoverty open-source statistical software. More information: www.aidevlab.org

Who we are looking for

The following requirements are mandatory:

• To qualify as a Doctoral student, you must have a Master’s degree (masterexamen) of 120 credits or a Master’s degree (magisterexamen) of 60 credits* in computer science, data science, statistics, applied mathematics, electrical engineering, signal processing, physics, computational social science, or a related field.
• Strong written and verbal communication skills in English.
• Solid programming skills in Python (or an equivalent scientific language such as R, Julia, or C++), with hands-on experience using modern deep-learning frameworks (e.g., PyTorch, TensorFlow, or JAX).
• Foundational knowledge of deep learning and computer vision, demonstrated through coursework, a Master’s thesis, an internship, or an independent project.
• Curiosity for interdisciplinary research—willingness to engage with questions in poverty research, sustainable development, and statistics alongside the technical work.
• Personal qualities in line with the requirements profile: self-propelled, intellectually curious, collaborative, and able to communicate clearly with researchers from different disciplines.

*For students with an education earned outside Sweden, a 4-year Bachelor’s degree is accepted.

The following experience will strengthen your application:

• Experience with image processing, preferably satellite imagery or other remote-sensing data.
• Experience with Google Earth Engine, geospatial libraries (e.g., GDAL, rasterio, geopandas), or earth-observation data pipelines—or a strong willingness to learn.
• Coursework or research exposure to remote sensing, geosciences, or spatial statistics.
• Familiarity with modeling geo-temporal data (e.g., spatio-temporal CNNs, LSTMs, transformers, or Gaussian processes).
• Interest in or exposure to causal inference (see, e.g., Imbens and Rubin, 2015, or Pearl, 2016).
• Awareness of statistical issues that arise when predictions are used as data for inference (e.g., prediction-powered inference, conformal prediction, multiple imputation).
• A Master’s thesis, peer-reviewed publication, conference paper, open-source contribution, or other written output that demonstrates independent research capacity.
• Experience working in or with international, interdisciplinary, or policy-relevant research teams.

The project welcomes spin-off ideas that build on the candidate’s own interests, especially those that open new angles on the objectives above. Please state clearly in your application which parts of the project attract you most and link this to your background.

What you will do

• Lead the three work packages of the project: train deep-learning models on Sentinel-2 imagery to estimate multidimensional poverty across Africa; benchmark them against Pléiades and Landsat-based models; and apply AI-explainability methods to interpret what the models see.
• Contribute to the ObservatoryOfPoverty open-source software, which lets the wider research community produce and use poverty estimates for policy evaluation.
• Take courses at an advanced level within the Chalmers Graduate School in Computer Science and Engineering, including a course in earth observation offered at the University of Gothenburg (https://www.chalmers.se/en/education/your-studies/doctoral-student-at-chalmers/graduate-schools/).
• Develop your own scientific ideas and communicate results orally and in writing—targeting top AI venues (e.g., NeurIPS, ICML, IJCAI), remote-sensing journals (e.g., IEEE TGRS, Remote Sensing of Environment), and interdisciplinary outlets (e.g., PNAS, Nature, Science).
• Engage in the life of the Lab: present at weekly meetings, co-author with international collaborators, and contribute to the lab’s research infrastructure.

Contract terms

• The doctoral student position is fully funded from the start.
• The position is a fixed-term appointment of four years, with the possibility to teach up to 20%, which extends the position to up to five years.
• A starting salary of 34,550 SEK per month (valid from May 25, 2025).
• Doctoral studies require physical presence throughout the entire study period. A valid residence permit must be presented by the study start date; otherwise the admission may be withdrawn.

What we offer

• As a Doctoral student at Chalmers, you are an employee and enjoy all employee benefits. Read more about working at Chalmers and our benefits for employees.
• A dynamic and inspiring working environment in the coastal city of Gothenburg.
• Read more about Sweden’s generous parental leave, subsidised day care, free schools, healthcare etc. at Move To Gothenburg.

Chalmers is dedicated to improving gender balance and actively works with equality projects, such as the GENIE Initiative for gender equality and excellence. We celebrate diversity and consider equality and inclusion as fundamental aspects of all our activities.

If Swedish is not your native language, Chalmers offers Swedish courses to help you settle in.

Find more general information about doctoral studies at Chalmers here.

Application procedure

The application should be written in English and attached as PDF files, as below. Maximum size for each file is 40 MB. Please note that the system does not support Zip files.

1. CV

• A comprehensive CV, including coursework relevant to data science, machine learning, and statistics; previous research projects; publications or technical reports (if any); software portfolio (GitHub or similar).

2. Personal letter

• A brief introduction about yourself.
• A motivation for why you are interested in this position—which of the three objectives attracts you most and why, and how your background prepares you for one or more of them.

3. Bachelor’s and, if available, Master’s thesis, or other publications, together with the transcripts.

The selection process will consist of several phases, in which the finalist will likely be invited for an in-person interview at Chalmers.

Use the button at the foot of the page to reach the application form.

A background check may be conducted as part of the application process.

Please note: The applicant is responsible for ensuring that the application is complete. Incomplete applications and applications sent by email will not be considered. Contact details for references will be requested after the interview.

We welcome your application no later than 13 June 2026.