Doctoral Research Fellow - Multimodal AI for Mapping Biodiversity in Forests

Nøkkelinformasnon

The country forest initiative seeks a PhD candidate who will develop groundbreaking multimodal methods in artificial intelligence for mapping and monitoring biodiversity in forests. The project will investigate how heterogeneous information sources, including remote sensing data, forest innovation data, existing forest maps, environmental and climate data as well as new large-scale AI representations, can be utilized to characterize forest ecosystems and their BI

The research will focus on developing multimodal learning methods that combine complementary information about forests across data sources, spatial scales and time dimensions. A central scientific challenge will be to learn integrated representations of forest ecosystems from datasets with very different properties, solutions, geographical coverage and degree of guidance (SuperVision). These representations should then be used to seal important knowledge holes related to biodiversity, with particular emphasis on mapping natural forests and important habitats for biodiversity at regional and national level.

The position is three-year-old with workplace at Nibio's headquarters on Ås, about 30 km south of Oslo.

The candidate will be admitted by a doctoral program at the Norwegian University of Life Sciences (NMBU) and will be part of the emerging research environment AI for Nature, which is developed in collaboration between NIBIO and NMBU.

A little about the frames for the position

The candidate will have access to supervisors both from NIBIO and from NMBU.

The position gives a unique opportunity to conduct basic research in artificial intelligence while working on issues of great social and environmental importance. The candidate will access comprehensive national forest data set and geographic information, work in an interdisciplinary research environment and contribute to the development of the next generation of AI methods for large-scale monitoring of forests and biodiversity.

In order to be qualified applicant, you can not have previously had a fellow position at NIBIO, nor may you have a doctorate from before or earlier have had a fellow position financed by the Research Council of Norway.

If you do not master Norwegian, Swedish or Danish at Level A2 when hiring, NIBIO will offer free Norwegian education with the goal of achieving at least this level.

Position's main tasks

The doctoral project will explore new methods of learning from several complementary sources of forest and environmental information. The research will move beyond models based on individual data sets, and examine how multimodal artificial intelligence can integrate information from multiple data sources to describe forestry properties that cannot be observed or measuring satisfactory through a single source alone.

The most important tasks will be to:

• Develop multimodal methods for deep learning and representation learning that integrates heterogeneous forest and environmental data set, including remote sensing data, observations from forest inventations, existing forest maps, climate and environment variables and large-scale Geos
• Examine methods to combine information across various spatial resolutions, time scales and data modes, including situations where some data sources are incomplete or inaccessible
• Exploring the use of Foundation Models and self-guided learning (self-super-learning) to extract transmitted representations from large-scale data set in forest and earth observation
• Develop AI models for prediction and mapping of natural forests, important habitats for biodiversity and other ecologically relevant forest properties
• Integrate organic knowledge and biodiversity observations in model development and evaluation
• Evaluate the models' generalization ability and transferability between different forest types, environmental gradients and geographical regions
• Produce regional and national maps related to biodiversity in forests and assess their accuracy and ecological relevance
• Publish results in leading international scientific journals and conferences, as well as contribute to cooperation between NIBIO, NMBU and national and international research partners

Kvalifikasjonskrav

• Masters Degree in Machine Learning, Artificial Intelligence, Informatics, Remote Measurement, Geomatics, Computer Science or Forest and Environmental Studies with a Strong Quantitative or AI-Related Component
• Solid knowledge of machine learning and deep learning
• Good programming skills, preferably in Python and modern framework for deep learning, such as Pytorch
• Experience with work on large or complex datasets
• Good English skills, both oral and written
• You must meet the terms defined for admission to the appropriate doctoral program at NMBU

It is an advantage if you have

• Experience with multimodal learning, representation learning, self-guided learning (self-supervised learning) or foundation Models
• Experience with geospatial data, remote sensing data and data set based on folk research (Citizen Science)
• Experience with work on heterogeneous datasets from various sensors or data sources
• Knowledge of forest ecology, biodiversity or applications in natural resource management
• Experience with the development of reproducible research software and work in high performance or GPU-based calculation environments
• Experience with publication or contribution to scientific articles or conference contributions.

Personal characteristics

• Good cooperative and communication skills
• Strong analytical abilities and good problem solving skills
• Ability to work under pressure and handle demanding users and stakeholders
• Commitment to and motivation to contribute in an ambitious research environment
• Ability to cooperate effectively with internal and external experts with different academic backgrounds and expertise

We offer

• Ability to work with an important social mission focusing on sustainability and forward-looking projects
• Challenging, exciting and varied tasks in interdisciplinary teams
• A flexible everyday with the opportunity to influence their own work tasks
• A strong professional environment with good colleagues
• A generous personal policy with welfare schemes and focus on the employees' different life phases

The position is placed in government regulations as a fellow, job code 1017, annual salary NOK 555.000 - 635.000. Remuneration is considered after education and experience.

Membership in the Government Pension Fund, which entails a good occupational pension scheme, occupational injury and group life insurance, and offers for mortgages to favorable interest rates.

More about NIBIO as an employer can be found here:Jobs in NIBIO

How to apply for the position

Application with CV is filled in electronically and sent via link on this page, " search position ".
Diplomas and testimonials are included in any interview, or are electronically placed.

NIBIO conducts background checks on current candidates.

Other information

We emphasize diversity in the workplace and encourage qualified candidates to apply - regardless of age, gender, functional ability, holes in CV, national or ethnic background.
As state business, we have the opportunity to provide a positive special treatment for applicants who have impairment, holes in the CV or immigrant background. Positive special treatment involves, among other things, that you will more easily come to interview.
Read more about thishere.

We note that information about the applicant can be made public, cf. Act on the right to access documents in public activities (Public Glegova), § 25. An applicant may request to be exempt from entry on public search list. If the request is not included, the applicant is notified of this.