PhD position in bioacoustics, statistics, and AI for forest biodiversity

Department of Wildlife, Fish, and Environmental Studies

WIFORCE Research School

Do you want to contribute to the future sustainable use of forests? Apply to join WIFORCE Research School!

Biodiversity and the role of forests in climate change are now key social issues that require more knowledge. In order to both sustainably use and safeguard forest biodiversity, a coherent basic science research program is needed that addresses large and complex issues and develops new analytical tools. That’s why the WIFORCE Research School, part of the Wallenberg Initiatives in Forest Research (www.slu.se/en/wiforce), was created.

Department of Wildlife, Fish, and Environmental Studies

We are looking for a PhD student with strong interests in wildlife conservation technology, specifically the use of passive acoustic monitoring (PAM) and AI. The position is hosted at the department of Wildlife, Fish, and Environmental Studies at SLU in Umeå and is part of a cohort of PhD students funded through the Wallenberg Initiatives in Forest Research (WIFORCE) program. The successful applicant will work on the development of bioacoustic monitoring methods using automated recording units (ARUs), deep learning methods, and applied statistical models, and will be part of a growing conservation technology hub at the department.

The Department of Wildlife, Fish, and Environmental Studies offers a creative, stimulating, and highly international environment and performs globally recognised research, education, and environmental monitoring in the research areas of animal ecology, aquatic ecology, molecular ecology, and restoration ecology (see https://www.slu.se/en/about-slu/organisation/departments/department-of-wildlife-fish-and-environmental-studies/). The department has many international employees and well-established national and international collaborations, which give opportunities for fruitful knowledge exchange.

Read more about our benefits and what it is like to work at SLU at https://www.slu.se/en/about-slu/work-at-slu/

Developing bioacoustics methods using AI for monitoring and quantifying Swedish forest biodiversity

Research subject Biology

Description:

Rapid and quantitative biodiversity monitoring is becoming increasingly important as climate and land-use change impact the planet, and biodiversity credit systems start to be implemented. For vocally active species, PAM holds large promise as a standardized and quantitative methodology for monitoring the presence and abundance of vocal species. However, the manual annotation of sound files is labour intensive. Therefore, deep learning models have been developed to automate the process of species classification. However, there are still several methodologies that need to be developed to integrate these models into a functioning workflow for ecologists.

In this 4-year PhD project, the successful candidate will develop an open-source workflow using deep learning and hierarchical statistical models to streamline the data flow from acoustic recorders to ecological insights that inform biodiversity management. The project includes:

·       Apply of deep learning models to annotate bird and bat species from sound recordings.

·       Develop a Bayesian statistical framework to incorporate annotation probabilities in hierarchical models.

·       Use long-term passive-acoustic datasets from at least two projects investigating the role of forest structure and composition on the community composition of birds and bats in Swedish forests.

·       Produce an open-source workflow for ecologists and other non-technical users to improve the application of PAM.

The successful candidate is expected to work with (inter)national collaborators to make sure that their work is embedded in the PAM community, to help ensure uptake and maintenance of the developed methodologies.

What we offer:

·       A vibrant and collaborative research environment, supported by experienced supervisors with expertise in wildlife ecology, conservation technology, applied statistics, and deep learning

·       Access to state-of-the-art research facilities and infrastructure.

·       Opportunities for professional development through interdisciplinary collaboration and training in advanced analytical techniques, including two work visits to collaborators.

Engagement with international research networks.

Qualifications:

We are looking for a highly motivated and team-oriented individual with:

·       An MSc degree (or equivalent) in Computer Science, Statistics, Ecology, Biology or Forestry.

·       Documented experience with application of deep learning and advanced statistical analysis and programming (e.g., R or Python).

·       A strong interest in biodiversity, conservation, and forest ecology.

·       Experience with passive acoustic monitoring, Bayesian statistics, and creating open-source software or code will count as strong merits.

·       Affinity with bird or bat ecology counts as merit.

Place of work:      

Umeå

Forms for funding or employment:

Employment as PhD student (4 years education)

Starting date:

According to agreement. 

Application:

Click the “Apply” button to submit your application. The deadline is 2026-02-10.

A CV (max 3 pages, font type Arial or Times New Roman, min size 11) should include the following headings: education, work experience, research interests, awards, publications, presentations and conferences, software and computing skills, languages, and contact details for minimally two reference persons.

A motivation letter (max 2 pages, font type Arial or Times New Roman, min size 11) should motivate the candidate´s qualifications and interest in conducting this PhD project.

To qualify for third-cycle (Doctoral) courses and study programmes, you must have a second-cycle (Master’s) qualification. Alternatively, you must have conducted a minimum of four years of full-time study, of which a minimum of one year at second-cycle level.

Applicants will be selected based on their written application and CV, degree project, copies of their degree certificate and transcript of records from previous first and second-cycle studies at a university or higher education institution, two personal references, and knowledge of English. More information about the English language requirements can be found here: https://www.slu.se/en/education/programmes-courses/doctoral-studies/application-admission-doctoral-studies/

Please note that applicants invited to interview must submit attested copies of their degree certificate, or equivalent, a transcript of records from previous first and second-cycle studies at a university or higher education institution. Applicants who are not Swedish citizens need to submit an attested copy of their passport’s information page containing their photograph and personal details.

Read about the PhD education at SLU at https://www.slu.se/en/study/programmes-courses/doctoral-education/

Academic union representatives:

https://internt.slu.se/en/my-employment/employee-associations/kontaktpersoner-vid-rekrytering/

The Swedish University of Agricultural Sciences (SLU) has a key role in the development for sustainable life, based on science and education. Through our focus on the interaction between humans, animals and ecosystems and the responsible use of natural resources, we contribute to sustainable societal development and good living conditions on our planet. Our main campuses are located in Alnarp, Umeå and Uppsala, however, the university also operates at research stations, experimental forests and teaching sites throughout Sweden. SLU has around 4,000 employees, 6,000 students and doctoral students and a turnover of over SEK 4,5 billion. We are investing in attractive environments on all of our campuses. We strive to provide a work environment characterised by inclusivity and gender equality, where different experiences generate conversations between people and pave the way for science, creativity and development. Therefore, we welcome applications from people with diverse backgrounds and perspectives.