Skip to main content

PhD Position in Deep Learning for Predicting Poverty from Satellite Images Chalmers University of Technology







PhD Position in Deep Learning for Predicting Poverty from Satellite Images Chalmers University of Technology


The data science and AI division at CSE is recruiting a PhD student for a project in Deep Learning for Predicting Poverty from Satellite Images.

The position is advertised within the research project Poverty traps in Africa, funded by FORMAS. FORMAS is a government research council for sustainable development. Its areas of activity include the environment, agricultural sciences, and spatial planning.

About 900 million people—one-third in Africa—live in extreme poverty. Operating on the assumption that life in impoverished communities is fundamentally so different that it can trap people in cycles of deprivation ('poverty traps'), major development agencies have deployed a stream of development projects to break these cycles ('poverty targeting'). However, scholars are currently unable to answer questions such as in what capacity do poverty traps exist; to what extent do these interventions release communities from such traps—as they are held back by a data challenges. There is a lack of geo-temporal poverty data; this project will develop new methods to produce such data. Consequently, the aim of this project is to identify to what extent African communities are trapped in poverty and explain how competing development interventions alter these communities' prospects to free themselves from deprivation. To achieve this aim, the project will (i) develop machine learning algorithms to identify poverty traps from satellite images (e.g. NASA's Landsat mission) between 1980s to 2020; (ii) use these remote sensing derived poverty data to examine how World Bank versus Chinese development programs target and communities; (iii) investigate the extent to which such analysis can be used to draw causal conclusions about the impact of development pograms (iv) using this foundational work, scale up the results from (i) – (iii) to validate them and develop a theory of the varieties of poverty traps and targeting. Lastly, (iv) To produce a statistical package—PovertyMachine—that enables us, and other scholars, to produce poverty estimates from new images (i).

The doctoral student is expected to produce a Ph.D. thesis contributing to primarly satisfying the project's first and third aims: "To develop machine learning and causal inference algorithms to identify poverty levels and poverty traps using satellite images, of African communities over time and space, on a quarterly basis, from the 1980s to 2020."

And secondarily contribututing to satisfying the project's fourth aim: "To produce a statistical package—PovertyMachine—that enables us, and other scholars, to produce poverty estimates from new images (i)."

The project is a collaboration between Chalmers University of Technology and the Department of Sociology, University of Gothenburg. Accordingly, although the student will pursue a PhD in machine learning within computer science and engineering at Chalmers, this person expected to have an interest in social-scientific issues and interdisciplinary research. 

Major responsibilities
Your major responsibilities as a PhD student is to pursue your doctoral studies within the framework of the outlined research project. You will be enrolled in a graduate program in the Department of Computer Science and Engineering. You are expected to develop your own ideas and communicate scientific results orally as well as in written form. In addition, the position will include 20% departmental work, mostly teaching duties in Chalmers' undergraduate and masters-level courses or performing other duties corresponding to 20% of working hours.

Position summary
Full-time temporary employment. The position is limited to a maximum of five years.

Qualifications
To qualify as a PhD student, you must have a master's-level degree, or a four-year bachelor's degree, corresponding to at least 240 higher education credits in a relevant field. The position requires sound verbal and written communication skills in Swedish and English. If Swedish is not your native language, you should be able to teach in Swedish after two years. Chalmers offers Swedish courses.

Chalmers continuously strives to be an attractive employer. Equality and diversity are substantial foundations in all activities at Chalmers.

Our offer to you
Chalmers offers a cultivating and inspiring working environment in the dynamic city of Gothenburg. 
Read more about working at Chalmers and our benefits for employees.

Application procedure
The application should be marked with Ref 20200430 and written in English. The application should be sent electronically and be attached as pdf-files, as below:

CV: (Please name the document: CV, Family name, Ref. number)
• CV
• Other, for example previous employments or leadership qualifications and positions of trust.
• Two references that we can contact.

Personal letter: (Please name the document as: Personal letter, Family name, Ref. number)
1-3 pages where you:
• Introduce yourself
• Describe your previous experience of relevance for the position (e.g. education, thesis work and, if applicable, any other research activities)
• Describe your future goals and future research focus

Other documents:
• Copies of bachelor and/or master's thesis.
• Attested copies and transcripts of completed education, grades and other certificates, e.g. TOEFL test results.

Please use the button at the foot of the page to reach the application form. The files may be compressed (zipped).

Application deadline: 21 October, 2020

For questions, please contact:
Fredrik Johansson, CSE DSAI, fredrik.johansson@chalmers.se






Vineesh V
Assistant Professor of Geography,
Directorate of Education,
Government of Kerala.
https://www.facebook.com/Applied.Geography
http://geogisgeo.blogspot.com

Comments

Post a Comment

Popular posts from this blog

GIS data continuous discrete ordinal interval ratio

In Geographic Information Systems (GIS) , data is categorized based on its nature (discrete or continuous) and its measurement scale (nominal, ordinal, interval, or ratio). These distinctions influence how the data is collected, analyzed, and visualized. Let's break down these categories with concepts, terminologies, and examples: 1. Discrete Data Discrete data is obtained by counting distinct items or entities. Values are finite and cannot be infinitely subdivided. Characteristics : Represent distinct objects or occurrences. Commonly represented as vector data (points, lines, polygons). Values within a range are whole numbers or categories. Examples : Number of People : Counting individuals on a train or in a hospital. Building Types : Categorizing buildings as residential, commercial, or industrial. Tree Count : Number of trees in a specific area. 2. Continuous Data Continuous data is obtained by measuring phenomena that can take any value within a range...
Post a Comment
Read more

History of GIS

The history of Geographic Information Systems (GIS) is rooted in early efforts to understand spatial relationships and patterns, long before the advent of digital computers. While modern GIS emerged in the mid-20th century with advances in computing, its conceptual foundations lie in cartography, spatial analysis, and thematic mapping. Early Roots of Spatial Analysis (Pre-1960s) One of the earliest documented applications of spatial analysis dates back to  1832 , when  Charles Picquet , a French geographer and cartographer, produced a cholera mortality map of Paris. In his report  Rapport sur la marche et les effets du choléra dans Paris et le département de la Seine , Picquet used graduated color shading to represent cholera deaths per 1,000 inhabitants across 48 districts. This work is widely regarded as an early example of choropleth mapping and thematic cartography applied to epidemiology. A landmark moment in the history of spatial analysis occurred in  1854 , when  John Snow  inv...
Post a Comment
Read more

Disaster Management

1. Disaster Risk Analysis → Disaster Risk Reduction → Disaster Management Cycle Disaster Risk Analysis is the first step in managing disasters. It involves assessing potential hazards, identifying vulnerable populations, and estimating possible impacts. Once risks are identified, Disaster Risk Reduction (DRR) strategies come into play. DRR aims to reduce risk and enhance resilience through planning, infrastructure development, and policy enforcement. The Disaster Management Cycle then ensures a structured approach by dividing actions into pre-disaster, during-disaster, and post-disaster phases . Example Connection: Imagine a coastal city prone to cyclones: Risk Analysis identifies low-lying areas and weak infrastructure. Risk Reduction includes building seawalls, enforcing strict building codes, and training residents for emergency situations. The Disaster Management Cycle ensures ongoing preparedness, immediate response during a cyclone, and long-term recovery afterw...
Post a Comment
Read more

Representation of Spatial and Temporal Relationships

Geographical Information System (GIS) is a powerful tool for analyzing and visualizing spatial data. One of the key features of GIS is its ability to represent spatial and temporal relationships between different geographic features. Spatial relationships refer to the physical location of an object or feature in relation to other objects or features, while temporal relationships refer to the sequence or timing of events. Together, these relationships are essential for understanding and analyzing complex spatial and temporal data. Representation of Spatial Relationships in GIS: Spatial relationships in GIS can be represented using a variety of techniques such as distance, proximity, and topology. For example, distance-based relationships can be used to measure the distance between two points, while proximity-based relationships can be used to determine which objects or features are closest to one another. Topology-based relationships can be used to represent the connectivity between dif...
Post a Comment
Read more

Data Generalization in GIS

Data generalization in GIS is the process of simplifying complex geographic data to make it suitable for visualization and analysis at specific map scales. It reduces unnecessary details while preserving the overall patterns and essential characteristics, ensuring that the map remains clear and interpretable at different zoom levels. Key Concepts and Terminologies Purpose of Data Generalization : To simplify spatial data for better visualization and usability at smaller scales. To prevent maps from becoming cluttered or unreadable due to excessive detail. To maintain the essence of geographic features while omitting minor details. Example : On a world map, a small island may be represented as a single point or omitted, while on a local map, it may appear with detailed boundaries. Key Data Generalization Techniques Simplification : Definition : Reduces the number of vertices or points in a line or polygon, removing minor details while retaining the general shap...
Post a Comment
Read more