Analysis of Environmental Data 2
Analysis of environmental data 2 builds on the course analysis of environmental data 1 and aims to equip you with the tools required to handle different types of data generated from different parts of society. National laser scans, satellites, and forest machines are some examples of modern data sources that are used both in research and business. In the course, you will learn to combine different data sources with field inventories to implement leading machine learning methods.
The course is structured into different modules where each module contains a lecture, an introductory example, and an individual task where you independently apply the method to new data. Through practical exercises, you get the best possible opportunities for increased learning.
Course evaluation
The course evaluation is now closed
SV0020-30257 - Course evaluation report
Once the evaluation is closed, the course coordinator and student representative have 1 month to draft their comments. The comments will be published in the evaluation report.
Syllabus and other information
Syllabus
SV0020 Analysis of Environmental Data 2, 7.5 Credits
Analys av miljödata 2Subjects
Forestry Science BiologyEducation cycle
Master’s levelModules
Title | Credits | Code |
---|---|---|
Single module | 7.5 | 0001 |
Advanced study in the main field
Second cycle, has only first-cycle course/s as entry requirementsMaster’s level (A1N)
Grading scale
The grade requirements within the course grading system are set out in specific criteria. These criteria must be available by the course start at the latest.
Language
EnglishPrior knowledge
Knowledge corresponding to 120 HP including- 60 HP in Forestry Science or
- 60 HP in Biology or
- 60 HP in Environmental Science or
- 60 HP in Natural Resource Management or
- 60 HP in Forest Management or
- 60 HP in Soil Science or
including 7.5 hp in data analysis methods and English 6.
Objectives
The course will teach the student to handle large data sets specifically for forestry and related fields such as ecology, biology, soil science, and genetics, using programming and programs commonly used by researchers in the research fields and in practice. They learn to combine various spatial data sources with typical field data from forestry and ecology to implement some common machine-learning algorithms. The course has a focus on practical exercises supported by reading literature and lectures.
After completing the course, the student should be able to:
- Collect and prepare forest data from authorities such as the Swedish Forestry Agency and the Swedish Environmental Protection Agency for analysis.
- Independently perform spatial modeling of forest land based on remote sensing data.
- Identify and classify differences and similarities between statistics and machine learning for ecological data.
- Compare some traditional machine learning models based on accuracy and calculation speed.
- Combine machine learning with geographic data to produce
maps of biological conditions for sustainable forestry.
Content
This course uses environmental data from different ecosystems, with a focus on forest land. Some examples of data analyzed in the course are: laser data from LiDAR scans, hydrological data such as watercourses and surface groundwater, state-of-the-art data from harvesters, and field data from forest inventories.
The course focuses on applying statistical models and machine learning methods to spatial data. The course is divided into several sections: 1) processing of spatial data with open software. 2) Programming in, for example, Python to analyze spatial data; 3) combining data from field studies with spatial data and statistical methods and machine learning; 4) implementing machine learning models on spatial data.
Implementation
The course uses multiple teaching methods to promote student learning and discussion through interactive lectures and exercises.
Each section begins with online introductions and exercises, reading material and recorded lectures. Each section ends with a submission task where the students have to solve a problem with a new data set. The students will have the opportunity for consultations with the teacher thought the course.
The course focuses on the following general competencies: problem-solving, scientific methods, digital competence, and technology use.
Cooperation with the surrounding society takes place through course assignments based on real and complex data that students may encounter in their future jobs, for example, data from the Forestry Agency or the Geological Survey of Sweden.
Grading form
The grade requirements within the course grading system are set out in specific criteria. These criteria must be available by the course start at the latest.Formats and requirements for examination
Approved assignments
If a student has failed an examination, the examiner has the right to issue supplementary assignments. This applies if it is possible and there are grounds to do so.
The examiner can provide an adapted assessment to students entitled to study support for students with disabilities following a decision by the university. Examiners may also issue an adapted examination or provide an alternative way for the students to take the exam.
If this syllabus is withdrawn, SLU may introduce transitional provisions for examining students admitted based on this syllabus and who have not yet passed the course.
For the assessment of an independent project (degree project), the examiner may also allow a student to add supplemental information after the deadline for submission. Read more in the Education Planning and Administration Handbook.
Other information
The right to participate in teaching and/or supervision only applies for the course instance the student was admitted to and registered on.
If there are special reasons, students are entitled to participate in components with compulsory attendance when the course is given again. Read more in the Education Planning and Administration Handbook.
Additional information
This course prepares students for their master's theses and equips them with the skills to design their study, and collect and analyze their data. They also gain general competencies in several areas listed for the Master's program at the Faculty of ForestryResponsible department
Department of Forest ecology and Management