NPLK22002U Data Processing in Environmental Science and Agriculture

Volume 2022/2023
Education

MSc Programme in Agriculture

Content

The course will offer practical knowledge and hands-on experience in different aspects of data science with particular relevance for agronomy.

A large range of data challenges is met in both academia and industry. The purpose of this course is to introduce different tools within data science, to allow the participants to perform and assess different types of data analysis, and understand the methods at a level required to be able to talk to data science specialists.

An important part of the course is to learn the practical application of the methods in appropriate software, such as the open-source statistical programming language R. The main topics of the course include:

  • Experimental design
  • Statistics
  • Modelling
  • Machine learning

 

Within these main areas, the course will cover challenges like data handling, basic programming, and image analysis. Different data sources and types will be considered including both experimental and observational data. The student during the course enhance their general coding skills.

During the course, the participants will work in groups and hand in two reports.

As a final project, the students will in groups work on case studies provided by the course instructors. This work should be written together as a scientific paper that will be the basis for the exam.

Learning Outcome

Knowledge

The student will obtain knowledge of:

- Data quality and organization

- Commonly used experimental designs

- Appropriate statistical analyses associated with a given experimental design

- What is an image, and how to make visual objects into numbers and figures

- Basic concepts and techniques for prediction and regression

 

Skills

The student will be able to:

- Understand and evaluate data quality

- Formulate problems and testable hypotheses

- Choose a relevant design for a given hypothesis

- Carry out a statistical analysis suitable for a given experimental design

- Interpret and communicate the results from the analysis

- Do basic programming in the statistical programming language R

- Recognize possible applications of machine learning

- Evaluate results obtained with machine learning techniques

 

Competences

The successful student will be able to:

- Plan and communicate a research project.

- Select the relevant tool for investigating a scientific question

- Assess and reflect upon data processing strategies, results, and underlying data quality

 

Original literature, software manuals and tutorials, and teacher provided compendia.

Participants should have basic knowledge of statistics and of a programming-based data software program such as R or Python. Students lacking the required skills must expect to spend extra time familiarizing themselves with statistics and programming-based scientific data software such as R.

Academic qualifications equivalent to a BSc degree are recommended.
The teaching format will be a mixture of lectures and theoretical exercises with a focus on hands-on experience within all topic areas. During the course, the students will have to hand in reports based on group work, and to present their work for the class.
And the project in groups, will be based on case studies provided by the course instructors. This work should be written together as a scientific paper that will be the basis for the exam.
  • Category
  • Hours
  • Lectures
  • 30
  • Class Instruction
  • 20
  • Preparation
  • 80
  • Theory exercises
  • 30
  • Project work
  • 40
  • Guidance
  • 5
  • Exam
  • 1
  • Total
  • 206
Written
Oral
Collective
Continuous feedback during the course
Peer feedback (Students give each other feedback)

Written and oral feedback is given for reports on group level. All reports have to be re-submitted.

Peer feedback is given on the final presentation of the case study. All students are encouraged to ask questions during lectures and theoretical exercises and can expect to receive feedback on their questions and inquiries.

Credit
7,5 ECTS
Type of assessment
Oral examination, 20 min
Type of assessment details
20 min oral examination without preparation. Questions are asked in final case study report (50%) and curriculum (50%).
Exam registration requirements

50% of the exercise reports (1/2) are submitted and approved, and the final case study report is submitted.

Aid
Written aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
Several internal examiners
Re-exam

If the requirements are not met, the student one week before the re-exam has to hand in a report in a topic handed out by the teacher. The re-exam will be as the ordinary exam.

Criteria for exam assesment

See description of learning outcome