Postdoc in biology, focus on applied machine learning and eel behavior - Hiring in process/Finished, not possible to apply

Description                                             

The Faculty of Health Science and Technology has an opening for one full-time post-doctoral research fellow in Biology at the Department of Environmental and Life Sciences in the field of quantitative aquatic ecology, with a focus on fish movement behavior and machine learning techniques to predict how an eel will move in a river as a function of the surroundings.

The River Ecology and Management Research Group (RivEM), a research environment within the Department of Environmental and Life Sciences at Karlstad University, conducts both basic and applied research in and along rivers and lakes and their surrounding landscapes. The research group is interested in the sustainable use of natural resources in watersheds, working for solutions to environmental problems that benefit both society and nature. Areas of research addressed by RivEM include river connectivity and the effects of hydropower, aquatic- terrestrial interactions and habitats, winter ecology under global climate change, endangered species such as unionid mussels, conservation biology and social-ecological research relating to river regulation and recreational fishing (www.kau.se/biology, http://www.nrrv.se). Within many of these topics, research is conducted in collaboration with stakeholders from industry, administrative agencies, interest organizations and landowners. You will be employed as a post-doc in Biology and the employment is a temporary full-time position for two years, with a possible one-year-extension, and may include teaching or other academic duties in the Department.

Duties

Hydropower dams impact riverine connectivity, deteriorating life-cycle performance of many species as they obstruct the migration routes for organisms between areas used for feeding, reproduction and survival. To prevent further global declines in fish biodiversity, identifying and understanding key fish-environment interactions is crucial for successful conservation strategies. This is especially so for the European eel (Anguilla anguilla) whose population has declined 95% in the last 25 years and is currently categorized as critically threatened. The exact reasons for the decline in the eel population are not known, but a combination of effects from over-exploitation, new pathogens, climatic changes, and habitat degradation including fragmentation are believed to be the most probable causes. Adult seaward-migrating eels are more vulnerable to passage through hydropower installations than many other fish species due to their elongated body length. The need for mitigation and effective strategies for increasing survival of out-migrating eels in regulated rivers is thus obvious.

Concurrently, inferences of cost-effectiveness and relevance of mitigation and restoration efforts demand detailed knowledge of the specific processes that result in elevated migrating fish mortalities. In the case of eels and power plant-induced mortality, there is a very simple solution: prevent the eels from entering the turbines and restore river connectivity. This solution demands knowledge-based development of optimized solutions that should be rooted in in-depth knowledge about eel behavior and ecology. However, at present there is a lack of detailed knowledge on how to create sustainable solutions to do this and at the same time prevent loss of hydropower electricity production. The reason being a lack of a fundamental understanding on how the eel behaves as a function of the hydrological environment.

Our project aims at developing a statistical framework that provides an understanding of how different key hydrological variables affect eel swimming behavior, and machine learning techniques to predict how an eel will move in a river as a function of the surroundings. The statistical model framework will be developed based on existing models for smolt behavior, developed by members of the proposed project. This will provide a generic and general understanding of the correlation between hydrological variables and the swimming behavior of eels during downstream migration. This result will then be used in a machine learning model to predict eel downstream migratory routes. The results of this project are expected to help in the development of mitigation solutions for eels to strengthen the European eel population and consequently contribute to the restoration of the ecological dynamics of freshwater aquatic systems.

The successful candidate will work within RivEM, in close collaboration with experts from the Norwegian Institute for Nature Research (NINA) and Vattenfall R&D, with end-to-end data science projects which require leveraging state-of-the-art machine learning techniques, statistical methods, and other advanced analytics tools so as to deliver solutions for fish conservation. Through this role, you will have the opportunity to collaborate and develop your career together with experts within biology and other experienced data scientists in the project. In addition, silver eel telemetry studies in the field to study eel swimming behavior and hydrodynamics can come into question. The applicant is expected to be active at the university and participate in the research environment.

Requirements

To be eligible for the position, applicants are required to hold a PhD (or to be completed before the decision about the employment is taken) in quantitative ecology, statistics, computational ecology , or related fields. The candidate must have completed the degree no more than three years before the last date for applications unless special grounds exist. Older PhD degrees can be taken into account when there are special reasons, such as leave due to sick leave, parental leave, clinical service, positions of trust within unions or other similar circumstances. Excellent oral and written communication skills in English are required.

Assessment grounds

We are searching for a highly motivated candidate with experience in computer science and/or quantitative aquatic ecology.

In the selection process, special weight will be given to the applicant's research skills, as demonstrated by the quality of the applicant’s PhD thesis, published scientific articles and other scientific merits. Special weight will also be given to the applicant’s knowledge in advanced statistics & machine learning (random forest, artificial neural networks etc.), time series analysis and programming (Python and/or R).

Considerable weight will be given to the applicant's scientific experience in fish ecology, conservation and/or freshwater/marine ecology. Considerable weight will also be given to the ability to cooperate and establish good relations with colleagues, as well as the ability to work independently and to take initiatives.

Weight will be given to the applicant's interest and knowledge of European eel conservation, telemetry and experience of collaborating with society and communicating research. Completed higher education pedagogy courses is a merit, as well as a driver’s license.

Terms

The position is a fixed-term full-time employment for 24 months, with a possible extension of 12 months, starting no later than May 1, 2024, or by agreement between the applicant and the employer.

Other

Karlstad University values the qualities that even gender distribution and diversity bring to the business. We are therefore happy to see applicants of all genders and with different birth backgrounds, functionality and life experience.

Application

Submit the application via the university’s web-based recruitment tool, Varbi. For advice on how to draft your application, refer to “What should be included with my application?”

Applicants are responsible for submitting a complete application in accordance with the advertisement, for providing translations of any documents written in a language other than Swedish or English, and for ensuring that the documentation allows for objective and qualitative assessments. A complete application should be submitted by the application deadline. An incomplete application may jeopardize a fair assessment of qualifications.

The application should include:

• CV
• cover letter describing the applicant’s qualifications and research interests in relation to the duties of the position,
• a list of publications (in multi-authored publications, the role of the applicant must be specified)
• copies of relevant transcripts, degree certificates, certificates to corroborate previous employment, and letters of recommendation
• copy of doctoral thesis and other relevant publications
• language proficiency certificates
• two references, at least one of which is a current or former supervisor
• example a project on an online code repository such as GitHub or Gitlab

Attach all the documents and publications you wish to be considered to the electronic application (do not just provide links). Name each uploaded document to clearly indicate its content.

Documents that cannot be submitted electronically, such as books or publications, should be sent to: Karlstads universitet, Hanna Ljungdahl, 651 88 Karlstad, Sweden

Application deadline: 31st of January 2024

State the reference no: REK2023/244

We look forward to your application!

Karlstad University has chosen advertising channels for this recruitment and firmly declines any contact with advertising or recruitment agencies.