PhD scholarship

PhD scholarship within the use of machine learning for CT-scanning of wood

Faculty of Environmental Sciences and Natural Resource Management at Norwegian University of Life Sciences (NMBU) has a vacant 3-year PhD–position related to the use of artificial intelligence for CT-scanning of wood.

Industrial computer tomography (CT) scanning of logs is becoming a more widespread tool in sawmills and has proven to considerably increase the volume of high-value sawn timber. CT-scanning of logs provides information on the interior structure of the logs before sawing, and this information can be used when optimising the yield of sawn timber.

Wood is a natural material, and the properties depend on growth and development of the trees in the forests. This applies in particular to knot properties, which are highly dependent on the crown development of the trees. Size of knots and whether knots are sound or dead are important factors for the quality of sawn timber products. These properties can be detected with CT-scanning, but the current technology provides only limited accuracy in cases with low contrast in the CT-images.

We seek a PhD candidate who will apply machine learning techniques to detect knots from CT-images of logs. Datasets containing information about knot properties, forestry data and CT-scanning images will be recorded. The candidate will investigate whether the algorithms for knot detection by CT-scanning can be improved by using machine learning, and by combining data from the forest with data obtained from CT-scanning. By following these goals the PhD candidate will help us develop an artificial intelligence framework to improve the sawmilling industry’s ability to utilise the forests’ natural resources more efficiently and more sustainably.

The position is part of the project «Wood Artifcial Intelligence —Knot Modelling by Computed Tomography», which is a cooperation between Sweden, Germany and Norway. Some of the work might be done at Luleå University of Technology in Skellefteå, Sweden.

The applicant is made aware that an application for a PhD position at NMBU is at the same time an application for admission to a PhD program at the institution. The documentation that is necessary to ensure that the admission requirements are met must be uploaded as an attachment.

Main tasks

• Procure data on knot properties to be used for statistical modelling and for training of machine learning models
• Develop models describing knot diameter and distribution of sound and dead knots in Norway spruce and Scots pine
• Develop machine learning models for the detection of knot properties from CT-scanning

The successful candidate is expected to enter a plan for the progress of the work towards a PhD degree during the first months of the appointment, with a view to completing a doctorate within the PhD scholarship period.

Competence

The successful applicant must meet the conditions defined for admission to a PhD programme at NMBU. The applicant must have an academically relevant education corresponding to a five-year master’s degree or a cand.med.vet. degree, with a learning outcome corresponding to the descriptions in the Norwegian Qualification Framework, second cycle. The applicant must have a documented strong academic background from previous studies and be able to document proficiency in both written and oral English. For more detailed information on the admission criteria please see the PhD Regulations and the relevant PhD programme description.

The applicant must document expertise and interest in the research subject.

Required Academic qualifications

• Master’s degree within a relevant scientific field, such as Data science, Computer science, Statistics or Wood science and technology
• Programming experience or education

The following experiences and skills will be emphasized:

• Experience with machine learning and deep learning
• Experience with statistical modelling
• Skills in a Scandinavian language (written and oral)

You need to:

• Have a high degree of motivation
• Have good analytical skills
• Have good communication skills
• Be able to work both independently and in an interdisciplinary group
• Be fluent in English (written and oral)

Remuneration and further information

The position is placed in government pay scale position code 1017 PhD. Fellow. PhD. Fellows are normally placed in pay grade 54 (NOK 532.200, -) on the Norwegian Government salary scale upon employment and follow ordinary meriting regulations.

Employment is conducted according to national guidelines for University and Technical College PhD scholars.

For further information, please contact Professor Geir I. Vestøl,
E-mail: geir.vestol@nmbu.no; phone +47 67231736

Information for PhD applicants and general information to applicants

Application

To apply online for this vacancy, please click on the 'Apply for this job' button above.

Application deadline: 01.10.2023

This will route you to the University's Web Recruitment System, where you will need to register an account (if you have not already) and log in before completing the online application form.

About The Faculty of Environmental Sciences and Natural Resource Management

The Faculty of Environmental Sciences and Natural Resource Management (MINA) works with nature and the environment, sustainable use of natural resources, biological and geological processes.

MINA’s employees undertake teaching, research and dissemination within the fields of geology, hydrology and limnology, soil science, environmental chemistry, forestry, ecology, natural resource management, renewable energy, and nature-based tourism.

Our vision is to be a key actor in knowledge production and dissemination, and our goal is to deliver research of high, international quality, and varied and excellent teaching. The faculty’s employees are significant participants within their respective fields of expertise, both nationally and internationally. The faculty is dominated by a vital research culture and high levels of scientific production.

The faculty has about 200 employees, 90 PhD students and 650 students.

Read more about MINA here.