Loïc Pellissier: Catalogue data in Autumn Semester 2021

Name Prof. Dr. Loïc Pellissier
FieldLandscape Ecology
Ökosysteme u. Landschaftsevolution
ETH Zürich, CHN F 29.2
Universitätstrasse 16
8092 Zürich
Telephone+41 44 632 32 03
DepartmentEnvironmental Systems Science
RelationshipAssociate Professor

701-0553-00LLandscape Ecology Information 3 credits2GF. Kienast, L. Pellissier
AbstractThe course is an introduction to Landscape Ecology and Landscape Modelling and provides various practical applications of Landscape Ecology in nature and landscape management.
ObjectiveThe students are able
- to explain and apply the concepts and methods of landscape analysis using examples,
-to explain causes and effects of changes in landscape using examples and simulations,
- to describe practical applications of Landscape Ecology in the management of nature and landscape.
ContentContents of the lecture:
- important terms and concepts of Landscape Ecology,
- analysis of landscape pattern (metrics),
- landscape modelling,
- perception of landscapes,
- landscape inventories used for nature and landscape protection.
Lecture notesThe course is offered via a MOOC (Edx)
LiteratureIn the MOOC
Prerequisites / NoticeThis lecture is coordinated with a MOOC.
It is advantageous but not required to have some GIS knowledge for this lecture and the practical 'Praktikum Wald und Landschaft' (spring semester) which is loosely linked with this lecture.
701-1679-00LLandscape Modelling of Biodiversity: From Global Changes to Conservation5 credits3GL. Pellissier, C. Graham, N. Zimmermann
AbstractThe course provides the student with the spatial tools to address societal challenges toward ensuring the sustainable use of terrestrial ecosystems and the conservation of biodiversity. Students learn theory, tools and models during a few introductory sessions and apply this knowledge to solve a practical problem in groups related to climate change, land use change and biodiversity conservation.
ObjectiveStudents learn:
- Theoretical foundations of the species ecological niche
- Biodiversity concepts and global change impacts
- Basic concepts of spatial (& macro-) ecology
- Environmental impact assessment and planning
- Advanced statistical methods (GLM, GAM, CART) and basic programming (loops, functions, advanced scripting) in the statistical environment R.
- The use of GIS functionality in R
Content1. The basics:
Introduction to the concept of the ecological niche, and biodiversity theories. Overview of the knowledge on expected biodiversity response to global changes and conservation planning methods.
Introduction to the statistical methods of Generalized Linear (GLM) and Generalized Additive models (GAM), and Classification and Regression Trees (CART). Introduction to basic GIS and programming elements in the statistical environment R.
2. The class project:
Students form groups of two, and each group solves a series of applied questions independently in R using the techniques taught in the introductory classes. The students then prepare a presentation and report of the obtained results that will be discussed during a mini-symposium. Each team choses one of the following topics for the class project:
a) Linking climate change velocities to species' migration capacities
b) Explaining and modelling land use change in Switzerland
c) Explaining and modelling biodiversity changes in Switzerland
d) Designing biodiversity conservation strategies under global changes.
Prerequisites / NoticeBasic knowledge in statistics (OLS regression, test statistics), and basic knowledge in geographic information science.
701-3001-00LEnvironmental Systems Data Science Restricted registration - show details 3 credits2GL. Pellissier, J. Payne, B. Stocker
AbstractStudents are introduced to a typical data science workflow using various examples from environmental systems. They learn common methods and key aspects for each step through practical application. The course enables students to plan their own data science project in their specialization and to acquire more domain-specific methods independently or in further courses.
ObjectiveThe students are able to
● frame a data science problem and build a hypothesis
● describe the steps of a typical data science project workflow
● conduct selected steps of a workflow on specifically prepared datasets, with a focus on choosing, fitting and evaluating appropriate algorithms and models
● critically think about the limits and implications of a method
● visualise data and results throughout the workflow
● access online resources to keep up with the latest data science methodology and deepen their understanding
Content● The data science workflow
● Access and handle (large) datasets
● Prepare and clean data
● Analysis: data exploratory steps
● Analysis: machine learning and computational methods
● Evaluate results and analyse uncertainty
● Visualisation and communication
Prerequisites / Notice252-0840-02L Anwendungsnahes Programmieren mit Python
401-0624-00L Mathematik IV: Statistik
401-6215-00L Using R for Data Analysis and Graphics (Part I)
401-6217-00L Using R for Data Analysis and Graphics (Part II)
701-0105-00L Mathematik VI: Angewandte Statistik für Umweltnaturwissenschaften