1 Welcome!
Welcome to the Species Distribution Modeling (SDM) Course! 🎉 This course is designed to provide both theoretical insights and hands-on practical skills for understanding and predicting species distributions. Whether you’re new to SDMs or looking to deepen your expertise, you’re in the right place!
Goal: Equip participants with the knowledge and tools to build reliable species distribution models using R.
1.1 What to Expect
Throughout this course, you will engage in:
- Interactive lectures covering key SDM concepts.
- Hands-on practical sessions involving spatial data analysis in R.
- Collaborative learning through discussions and group activities.
1.1.1 Learning Path
| Module | Content |
|---|---|
| Module 1 | Introduction to Species Distribution Modeling |
| Module 2 | Preparing Spatial Data for Modeling |
| Module 3 | Applying SDM Algorithms (MaxEnt, GLM, RF, etc.) |
| Module 4 | Model Evaluation & Interpretation |
| Module 5 | Advanced Topics: Ensemble Modeling & Climate Projections |
1.2 How to Get Started 🚀
Follow these steps to set up your environment and begin your SDM journey:
-
Check the Resource Hub:
- Access essential files, including datasets, scripts, and reading materials, via the shared Google Drive.
-
Set Up Your Environment:
- Ensure R and RStudio are installed.
- Run the
installlibs.Rscript to install required packages.
-
Stay Engaged:
- Participate actively in lectures and practicals.
- Ask questions and share your insights during sessions.
Tip: Bookmark this guide for easy reference throughout the course. 📖
1.3 Course Overview 🌍
Species Distribution Models (SDMs) are powerful tools for understanding where species are likely to occur based on environmental variables. They play a crucial role in:
- Biodiversity conservation
- Ecological research
- Environmental management
1.3.1 Core Topics Covered
-
Theoretical Framework:
- Learn the fundamental principles of SDMs, including ecological niche theory and predictor variables.
-
Spatial Data Handling:
- Gain hands-on experience with spatial datasets in R (e.g., shapefiles, raster data).
-
Modeling Algorithms:
- Explore different SDM algorithms, such as:
- MaxEnt: For presence-only data.
- Generalized Linear Models (GLM) and Random Forests (RF) for presence-absence data.
- Explore different SDM algorithms, such as:
-
Model Evaluation:
- Use metrics like AUC, TSS, and Kappa to assess model performance.
-
Projection & Scenario Analysis:
- Predict species distributions under future climate scenarios using ensemble modeling.
1.4 Logistics and Structure 🗓️
The course spans two weeks, with each week comprising:
- Lectures (1-2 hours)
- Discussions (30 minutes)
- Practical Exercises (2-3 hours)
1.5 Instructor Background 👩🏫
The course instructor brings a unique blend of expertise in aerospace engineering and ecological modeling. Their research focuses on:
- Climate change impacts
- Invasive species management
- Habitat suitability modeling
This interdisciplinary approach ensures a well-rounded learning experience, combining technical rigor with ecological insight.
1.6 Course Objectives 🎯
By the end of this course, you will be able to:
- Understand the principles of SDMs and spatial data analysis.
- Prepare spatial datasets for modeling.
- Apply various SDM algorithms using R.
- Evaluate model performance using appropriate metrics.
- Interpret and project model results under different scenarios.
Advanced learners: Additional modules on ensemble modeling and climate downscaling will be available for those interested in more in-depth exploration.
1.7 Practical Exercises 💻
This course emphasizes hands-on learning. Key practical exercises include:
1.7.1 1. Handling Spatial Data
- Objective: Prepare spatial data for SDM by loading, manipulating, and visualizing datasets in R.
-
Skills Learned:
- Loading shapefiles and raster data.
- Performing spatial operations.
- Visualizing spatial data using
ggplot2andleaflet.
1.7.2 2. Fitting and Evaluating SDMs
- Objective: Apply SDM algorithms and evaluate model performance.
-
Skills Learned:
- Running MaxEnt and GLM models.
- Evaluating models using AUC, TSS, and Kappa metrics.
- Interpreting model outputs.
Note: Solutions will be shared after the course to allow self-assessment.
1.8 Communication and Support 🤝
Active participation is key to making the most of this course. Participants are encouraged to:
- Ask questions during sessions.
- Share insights and experiences.
- Collaborate with peers through group activities and discussions.
1.8.1 Support Channels
- Email Support: Reach out to the instructor for any queries.
- Discussion Forum: A dedicated forum will be set up for ongoing discussions.
- Office Hours: Weekly office hours for one-on-one support.
Reminder: Collaboration fosters better learning, so don’t hesitate to engage with your peers! 🤗
1.9 References and Readings 📚
The course references several recent publications on best practices in SDM (2019-2023). Key references include:
- Elith & Leathwick (2019) - A comprehensive review of SDM methods.
- Phillips et al. (2020) - Guidelines for using MaxEnt in ecological modeling.
All papers are available in the shared Google Drive under the “Best Practices” folder.