2 PhD fellowship in One Crop Health Computer Vision for Monitoring of Pests, Weeds and Beneficials in Agricultural Fields and in simulation, mechanistic co-simulation of Insects, Weeds and Plant Infestation in Agricultural Fields
fuldtid
2 PhD fellowship in One Crop Health Computer Vision for Monitoring of Pests, Weeds and Beneficials in Agricultural Fields and in simulation, mechanistic co-simulation of Insects, Weeds and Plant Infestation in Agricultural Fields
The IMAGE section at Department of Computer Science is offering 2 PhD fellowship, One in Computer Vision and One in mechanistic co-simulation of Insects, Weeds and Plant Infestation in Agricultural Fields as a part of the One Crop Health project commencing 1 November 2025, or as soon as possible hereafter.
Our group and research
The IMAGE section hosts researchers in image analysis and processing, computer vision, computer simulation, numerical optimization, machine learning, computational modelling, geometry and geometric statistics. The work ranges from theoretical analyses, over algorithm development, to solving concrete problems for science, industry and society. We are part of the recently launched SCIENCE AI Centre at the University of Copenhagen.
Project description computer vision Phd
The One Crop Health project, funded by the Novo Nordisk Foundation, has the aim of producing accurate models of agricultural fields allowing the prediction of crop yield based on the interventions applied to the field with the goal of reducing the usage of pesticides. The modelling will be data-driven and based on continuous data collection from approximately 100 farmers in both Denmark and the United Kingdom.
The project therefore requires large scale automated monitoring of insects and plants as part of the data collection for modelling of the ecosystem of a field. The focus is on both problematic and beneficial species, i.e. for insects we include both pests, pollinators and natural enemies of pests. Similarly for plants we include competitive weeds and ‘beneficial’ plants that deliver ecosystem services. There will be a limited list of genus and species from both insects and plants that will be the focus of the monitoring activity. The collected monitoring data will consist mainly of images captured with color cameras but may include wavelengths outside the visible spectrum. We will collect monitoring data by a combination of handheld cameras, camera traps and cameras mounted on vehicles such as tractors, ATVs, and drones. The PhD student will take active part in the design and choice of procedure and technology for collecting monitoring data, as well as actively participating in the data collection. An initial dataset has been collected, and additional datasets will be collected and published throughout the project.
The PhD project requires interdisciplinary collaboration and to this end a close integration with domain experts is imperative and the student will be jointly supervised by faculty from computer science (DIKU), plant and environmental science (PLEN) and Rothamsted, UK.
Given monitoring data the PhD student will develop and implement efficient and reliable deep learning methods for recognition of species based on existing state-of-the-art computer vision algorithms for fine grained classification. The challenges are that we will have limited training datasets covering all species of interest and as well as the large variation in field data capturing condition (e.g. varying background, amount of clutter, and illumination). Initial phase will be on automating the process of establishing population distributions from data collected from a small set of monitoring lots spread out in fields from the test farms. The data consists of color photos of monitoring lots collected using mobile phone cameras as well as photos of larvae from harvested plants. The second phase of the project will be to develop novel approaches for biomonitoring at scale in collaboration with researchers within botany and entomology as well as technology for crop treatment and intervention. For this fine-grained classification problem, we will explore the possibility of using multi-modal input depending on the collected data, e.g. combining imaging with weather data and textual species descriptions. The problem to be solved is to learn and bootstrap from limited and potentially unsupervised data. We will investigate using weakly labelled data and zero- or few-shot learning methods.
Principal supervisor is Professor Kim Steenstrup Pedersen, Section for Image Analysis, Computational Modelling and Geometry (IMAGE) at Department of Computer Science, kimstp@di.ku.dk, Direct Phone: +45 61 37 45 29.
Start: 1 November 2025
Duration: 3 years as a PhD student
Required qualifications:
Preferable experience, knowledge and skills:
Other important criteria are:
Project description simulation PhD
The project will collect monitoring and farming data as well as field data as a combination of handheld cameras, camera traps and cameras mounted on vehicles such as tractors, ATVs, and drones.
The PhD will take an active part in the design and choice of model and integration of monitoring data, as well as actively participating in the data collection. A choice of base model has been made, and additional extensions to the model as well as simulation results and data integration will be published throughout the project.
The PhD students work will be to develop and implement and integrate interactions and co-simulation with additional other models for pest weed and diseases in close collaboration with the other partners in the project. The challenges are integrations and domain understanding. To this end a close integration with domain experts is imperative and the student will be jointly supervised by faculty from computer science (DIKU), plant and environmental science (PLEN) and Rothamsted. Furthermore, it is required that the student spend much of their time at PLEN in the group of the project leader Paul Neve. Furthermore, it is expected that the change of environment will be at Rothamsted research Centre in the UK at location of the UK co-supervisor.
The initial part will be to get the base model up and running capable of simulating the sites from the farmers as well as the long-term experiment established at PLEN. The first part will be to validate that the model is indeed well calibrated and does produce fair results. Secondly, start integrating different types of models for pest, weeds and diseases that is not available in the base model enabling the model to do predictions of the effect of different types of interactions and external circumstances
Principal supervisor is Professor Sune Darkner, Section for Image Analysis, Computational Modelling and Geometry (IMAGE) at Department of Computer Science, darkner@di.ku.dk Direct Phone: +45 21308584.
Start: 1 November 2025
Duration: 3 years as a PhD student
Required qualifications:
Preferable experience, knowledge and skills:
Job description
Your key tasks as a PhD student at Faculty of Science are:
Applicants must have qualifications corresponding to a master’s degree related to the subject area of the project as indicated below. To be eligible for the regular PhD programme, you must have completed a degree programme, equivalent to a Danish master’s degree (180 ECTS/3 FTE BSc + 120 ECTS/2 FTE MSc) related to the subject area of the project as indicated below
Place of employment
The place of employment is at the Department of Computer Science, Faculty of Science, University of Copenhagen. We offer creative and stimulating working conditions in dynamic and international research environment. Our research facilities include modern computing facilities and laboratories.
Terms of employment
The average weekly working hours are 37 hours per week.
Salary, pension and other conditions of employment are set in accordance with the Agreement between the Ministry of Taxation and AC (Danish Confederation of Professional Associations) or other relevant organisation. Currently, the monthly salary starts at 30,800 DKK/approx. 4,100 EUR (April 2025 level). Depending on qualifications, a supplement may be negotiated. The employer will pay an additional 18,07% to your pension fund
Questions
For specific information about the PhD fellowship, please contact the principal supervisor.
General information about PhD study at the Faculty of SCIENCE is available at the PhD School’s website: https://www.science.ku.dk/phd/
Application procedure
Your application must be submitted electronically by clicking ‘Apply now’ below. The application must include the following documents in PDF format:
1. Motivated letter of application (max. one page) and indicate which position you are applying for
2. CV incl. education, experience, language skills and other skills relevant for the position
3. Certified copy of original Master of Science diploma and transcript of records in the original language, including an authorized English translation if issued in other language than English or Danish. If not completed, a certified/signed copy of a recent transcript of records or a written statement from the institution or supervisor is accepted. As a prerequisite for a PhD fellowship employment, your master’s degree must be equivalent to a Danish master’s degree. We encourage you to read more in the assessment database: https://ufm.dk/en/education/recognition-and-transparency/find-assessments/assessment-database. Please note that we might ask you to obtain an assessment of your education performed by the Ministry of Higher Education and Science
4. Publication list (if possible)
Application deadline: 1 September, 23.59pm CET
We reserve the right not to consider material received after the deadline, and not to consider applications that do not live up to the abovementioned requirements.
The further process
After the expiry of the deadline for applications, the authorized recruitment manager selects applicants for assessment on the advice of the hiring committee. All applicants are then immediately notified whether their application has been passed for assessment by an unbiased assessor.
The assessor makes a non-prioritized assessment of the academic qualifications and experience with respect to the above-mentioned area of research, techniques, skills and other requirements listed in the advertisement.
Once the assessment work has been completed each applicant has the opportunity to comment on the part of the assessment that relates to the applicant him/herself.
You find information about the recruitment process at: http://employment.ku.dk/faculty/recruitment-process/
The applicants will be assessed according to the Ministerial Order no. 242 of 13 March 2012 on the Appointment of Academic Staff at Universities.
The University of Copenhagen wish to reflect the diversity of society and encourage all qualified candidates to apply regardless of personal background.
Our group and research
The IMAGE section hosts researchers in image analysis and processing, computer vision, computer simulation, numerical optimization, machine learning, computational modelling, geometry and geometric statistics. The work ranges from theoretical analyses, over algorithm development, to solving concrete problems for science, industry and society. We are part of the recently launched SCIENCE AI Centre at the University of Copenhagen.
Project description computer vision Phd
The One Crop Health project, funded by the Novo Nordisk Foundation, has the aim of producing accurate models of agricultural fields allowing the prediction of crop yield based on the interventions applied to the field with the goal of reducing the usage of pesticides. The modelling will be data-driven and based on continuous data collection from approximately 100 farmers in both Denmark and the United Kingdom.
The project therefore requires large scale automated monitoring of insects and plants as part of the data collection for modelling of the ecosystem of a field. The focus is on both problematic and beneficial species, i.e. for insects we include both pests, pollinators and natural enemies of pests. Similarly for plants we include competitive weeds and ‘beneficial’ plants that deliver ecosystem services. There will be a limited list of genus and species from both insects and plants that will be the focus of the monitoring activity. The collected monitoring data will consist mainly of images captured with color cameras but may include wavelengths outside the visible spectrum. We will collect monitoring data by a combination of handheld cameras, camera traps and cameras mounted on vehicles such as tractors, ATVs, and drones. The PhD student will take active part in the design and choice of procedure and technology for collecting monitoring data, as well as actively participating in the data collection. An initial dataset has been collected, and additional datasets will be collected and published throughout the project.
The PhD project requires interdisciplinary collaboration and to this end a close integration with domain experts is imperative and the student will be jointly supervised by faculty from computer science (DIKU), plant and environmental science (PLEN) and Rothamsted, UK.
Given monitoring data the PhD student will develop and implement efficient and reliable deep learning methods for recognition of species based on existing state-of-the-art computer vision algorithms for fine grained classification. The challenges are that we will have limited training datasets covering all species of interest and as well as the large variation in field data capturing condition (e.g. varying background, amount of clutter, and illumination). Initial phase will be on automating the process of establishing population distributions from data collected from a small set of monitoring lots spread out in fields from the test farms. The data consists of color photos of monitoring lots collected using mobile phone cameras as well as photos of larvae from harvested plants. The second phase of the project will be to develop novel approaches for biomonitoring at scale in collaboration with researchers within botany and entomology as well as technology for crop treatment and intervention. For this fine-grained classification problem, we will explore the possibility of using multi-modal input depending on the collected data, e.g. combining imaging with weather data and textual species descriptions. The problem to be solved is to learn and bootstrap from limited and potentially unsupervised data. We will investigate using weakly labelled data and zero- or few-shot learning methods.
Principal supervisor is Professor Kim Steenstrup Pedersen, Section for Image Analysis, Computational Modelling and Geometry (IMAGE) at Department of Computer Science, kimstp@di.ku.dk, Direct Phone: +45 61 37 45 29.
Start: 1 November 2025
Duration: 3 years as a PhD student
Required qualifications:
- A master’s degree in computer science, bioinformatics, mathematics, software engineering or a related field.
- Educational training or previous experience in programming for image analysis and computer vision.
- Educational training covering image analysis and computer vision.
- Educational training covering machine learning and in particular deep learning for image analysis and computer vision.
- Demonstrate good academic writing skills as proven in the motivated letter of application and in any previous publications.
Preferable experience, knowledge and skills:
- Participation in writing scientific publications is a benefit.
- Experience in using common deep learning packages such as PyTorch or Tensorflow for both applying existing models as well as writing models from scratch.
- Proficiency in Python programming at an advanced level.
- Experience in software development for larger software projects, including knowledge of version control systems such as Git and test-driven development (CI/CD).
- Experience with software development for mobile or web apps is a benefit.
- Interest in agriculture and biology is a benefit.
- Good collaborative skills and a keen interest in working in a multi-disciplinary research project.
- Fluent in both spoken and written English.
Other important criteria are:
- The grade point average achieved
- Professional qualifications relevant to the PhD project
- Previous publications
- Relevant work experience
- Other professional activities
Project description simulation PhD
The project will collect monitoring and farming data as well as field data as a combination of handheld cameras, camera traps and cameras mounted on vehicles such as tractors, ATVs, and drones.
The PhD will take an active part in the design and choice of model and integration of monitoring data, as well as actively participating in the data collection. A choice of base model has been made, and additional extensions to the model as well as simulation results and data integration will be published throughout the project.
The PhD students work will be to develop and implement and integrate interactions and co-simulation with additional other models for pest weed and diseases in close collaboration with the other partners in the project. The challenges are integrations and domain understanding. To this end a close integration with domain experts is imperative and the student will be jointly supervised by faculty from computer science (DIKU), plant and environmental science (PLEN) and Rothamsted. Furthermore, it is required that the student spend much of their time at PLEN in the group of the project leader Paul Neve. Furthermore, it is expected that the change of environment will be at Rothamsted research Centre in the UK at location of the UK co-supervisor.
The initial part will be to get the base model up and running capable of simulating the sites from the farmers as well as the long-term experiment established at PLEN. The first part will be to validate that the model is indeed well calibrated and does produce fair results. Secondly, start integrating different types of models for pest, weeds and diseases that is not available in the base model enabling the model to do predictions of the effect of different types of interactions and external circumstances
Principal supervisor is Professor Sune Darkner, Section for Image Analysis, Computational Modelling and Geometry (IMAGE) at Department of Computer Science, darkner@di.ku.dk Direct Phone: +45 21308584.
Start: 1 November 2025
Duration: 3 years as a PhD student
Required qualifications:
- A master’s degree in computer science, bioinformatics, mathematics, software engineering or a related field.
- Educational training or previous experience in programming for image analysis and computer vision.
- Educational training and strong skills in programming preferably c++.
- Educational training covering machine learning and in particular deep learning for image analysis and computer vision.
- Demonstrate good academic writing skills as proven in the motivated letter of application and in any previous publications.
- Educational training covering optimization, simulation and numerical analysis.
Preferable experience, knowledge and skills:
- Participation in writing scientific publications is a benefit.
- Experience in using and modifying 3rd party c++ software
- Software development skills
- Experience with mechanistic models of agricultural systems
- Experience in software development for larger software projects, including knowledge of version control systems such as Git and test-driven development (CI/CD).
- Experience with software development for mobile or web apps is a benefit.
- Interest in agriculture and biology is a benefit.
- Good collaborative skills and a keen interest in working in a multi-disciplinary research project.
- Fluent in both spoken and written English.
- The grade point average achieved
- Professional qualifications relevant to the PhD project
- Previous publications
- Relevant work experience
- Other professional activities
Job description
Your key tasks as a PhD student at Faculty of Science are:
- Carrying through an independent research project under supervision.
- Completing PhD courses or other equivalent education corresponding to approximately 30 ECTS points.
- Participating in active research environments including a stay at another research team.
- Obtaining experience with teaching or other types of dissemination related to your PhD project
- Teaching and disseminating your knowledge.
- Writing a PhD thesis on the grounds of your project
Applicants must have qualifications corresponding to a master’s degree related to the subject area of the project as indicated below. To be eligible for the regular PhD programme, you must have completed a degree programme, equivalent to a Danish master’s degree (180 ECTS/3 FTE BSc + 120 ECTS/2 FTE MSc) related to the subject area of the project as indicated below
Place of employment
The place of employment is at the Department of Computer Science, Faculty of Science, University of Copenhagen. We offer creative and stimulating working conditions in dynamic and international research environment. Our research facilities include modern computing facilities and laboratories.
Terms of employment
The average weekly working hours are 37 hours per week.
Salary, pension and other conditions of employment are set in accordance with the Agreement between the Ministry of Taxation and AC (Danish Confederation of Professional Associations) or other relevant organisation. Currently, the monthly salary starts at 30,800 DKK/approx. 4,100 EUR (April 2025 level). Depending on qualifications, a supplement may be negotiated. The employer will pay an additional 18,07% to your pension fund
Questions
For specific information about the PhD fellowship, please contact the principal supervisor.
General information about PhD study at the Faculty of SCIENCE is available at the PhD School’s website: https://www.science.ku.dk/phd/
Application procedure
Your application must be submitted electronically by clicking ‘Apply now’ below. The application must include the following documents in PDF format:
1. Motivated letter of application (max. one page) and indicate which position you are applying for
2. CV incl. education, experience, language skills and other skills relevant for the position
3. Certified copy of original Master of Science diploma and transcript of records in the original language, including an authorized English translation if issued in other language than English or Danish. If not completed, a certified/signed copy of a recent transcript of records or a written statement from the institution or supervisor is accepted. As a prerequisite for a PhD fellowship employment, your master’s degree must be equivalent to a Danish master’s degree. We encourage you to read more in the assessment database: https://ufm.dk/en/education/recognition-and-transparency/find-assessments/assessment-database. Please note that we might ask you to obtain an assessment of your education performed by the Ministry of Higher Education and Science
4. Publication list (if possible)
Application deadline: 1 September, 23.59pm CET
We reserve the right not to consider material received after the deadline, and not to consider applications that do not live up to the abovementioned requirements.
The further process
After the expiry of the deadline for applications, the authorized recruitment manager selects applicants for assessment on the advice of the hiring committee. All applicants are then immediately notified whether their application has been passed for assessment by an unbiased assessor.
The assessor makes a non-prioritized assessment of the academic qualifications and experience with respect to the above-mentioned area of research, techniques, skills and other requirements listed in the advertisement.
Once the assessment work has been completed each applicant has the opportunity to comment on the part of the assessment that relates to the applicant him/herself.
You find information about the recruitment process at: http://employment.ku.dk/faculty/recruitment-process/
The applicants will be assessed according to the Ministerial Order no. 242 of 13 March 2012 on the Appointment of Academic Staff at Universities.
The University of Copenhagen wish to reflect the diversity of society and encourage all qualified candidates to apply regardless of personal background.