Course code BIN302

BIN302 High throughput phenotyping for precision farming

There may be changes to the course due to to corona restrictions. See Canvas and StudentWeb for info.

Norsk emneinformasjon

Search for other courses here

Showing course contents for the educational year 2021 - 2022 .

Course responsible: Gareth Frank Difford, Morten Lillemo
Teachers: Sahameh Shafiee
ECTS credits: 10
Faculty: Faculty of Biosciences
Teaching language: EN
(NO=norsk, EN=Engelsk)
Limits of class size:
25
Teaching exam periods:
This course starts in Autumn parallel. This course has teaching/evaluation in Autumn parallel.
Course frequency: Anually
First time: 2021H
Preferential right:
The course is intended for MSc students with basic knowledge in relevant fields of plant and animal science, biology or computational/data science. Masters students will have priority, but PhD students are welcome provided we have space.
Course contents:

This course aims to introduce the emerging field of high throughput precision phenotyping for use in animal and plant management, measurement and breeding. The course will focus on automation, digitalisation and rapid measurements in the fields of image analysis, vibrational spectroscopy and sensors and their data analysis.

Rapid technological developments are providing researchers and farmers alike with new instrumentation, methodologies, and sensors. Coupled with automation, this provides an opportunity to rapidly and cheaply acquire large numbers of phenotypes required for precision farming and breeding. This course will explain the theory and practical analysis of method comparison studies which will guide the decision to keep, further improve or discard potential new methods. Emerging technologies such as i) vibrational spectroscopy for prediction of chemical composition ii) image analysis for ii) sensor technologies with an emphasis of time series, all with practical tutorials for their analysis in R-statistical software. Lastly, guest lectures on integrating machine learning and phenotyping platforms like robots, conveyor belts or UAV, will provide students with a broad understanding of practical implementation. A special emphasis will be given on acquiring new understanding and answering biological questions using different datatypes. The objective of the course if to provide students with basic knowledge on emerging fields of precision phenotyping and developing phenotypes to best serve precision farming for sustainability, efficiency and animal welfare.

Learning outcome:
  • The student will acquire knowledge of developments of high throughput phenotyping and their uses in precision farming.
  • The students should gain a broad understanding of method comparison studies to evaluate the potential of emerging technologies. A practical analysis using the students own data or provided datasets to complete a mini report.
  • An understating of image analysis, vibrational spectroscopy, and sensors their advantages and disadvantages in precision phenotyping. Weekly tutorials with guidance through analysis of the different datatypes.
  • A broad understating of combining phenotyping technologies with phenotyping platforms and an introduction to how machine learning can be used to assist data acquisition and compression.
Learning activities:

Weekly lectures and weekly application/tutorials in R statistical software

Introduction to phenotyping and precision farming, method comparisons, practical example of method comparisons, image analysis, vibrational spectroscopy, sensors technologies and R statistical analysis. Guest lectures on phenotyping platforms, and machine learning.Minireport on method comparison analysis (students own data or given datasets)Final written report on students own data or provided data for defining and analysing a new phenotype.
Teaching support:
Teachers will be available during the webased teaching and application/tutorials active guidance of learning activities.
Syllabus:
Course handout material and accompanying digital literature within the topics.
Prerequisites:
Basic understanding and use of Python or R statistical software and programming
Recommended prerequisites:

Quantitative genetics courses in plant, animal and aquaculture (such as HFA200, BIO248, HFX315) are recommended but not required.

Basic understanding and use of Python or R statistical software and programming

Mandatory activity:
Pass/Fail based on active participation in assignments presentation, and submission of final report.
Assessment:
Combined Assessment with grades A - E/F: We will have a written report at the end of the course and an oral examination on the report and the course contents. These two assessments will make up 50% each.
Nominal workload:

32 hours of lectures,

28 hours analysing data sets in groups

190 hours independent work

Total: 250 hours

Entrance requirements:
The course is intended for masters and PhD students with basic knowledge in relevant fields of precision farming and plant or animal phenotyping.
Reduction of credits:
-
Type of course:
Discussion groups / lectures: 2 hours per week. Datalab / exercises: 2 hours per week.
Note:
-
Examiner:
External censor
Examination details: Combined assessment: A - E / F