Workshops

WEST specializes in the design, conduct, and analysis of ecological studies. We have offered workshops and trainings internationally on topics ranging from ecological sampling and study design, fundamental and sophisticated statistical analyses, and data management and computer programming for practitioners. WEST is flexible in adapting the format and content of training to your specific interests and needs.

See our list of upcoming workshops, or reach out to marketing@west-inc.com to arrange a workshop not currently on the calendar.

Upcoming Workshops

Statistical Methods for Estimating Abundance in Ecology

November 29th, December 1st, 3rd, 6th | 3:00 PM – 4:30 PM Mountain Time

Estimating the number of individuals within a population across time and space is a fundamental task in ecological research and natural resource management. Simply counting individual organisms is often insufficient because some individuals often evade detection by observers; therefore, methods that correct for imperfect detection have become particularly popular. This purpose of this workshop is to familiarize participants with three methods commonly used to estimate wildlife abundance while accounting for detection probability: capture-mark-recapture, N-mixture models, and distance sampling. One session will be devoted to each method, and the final session will be unstructured work time for participants to tackle analysis of their own data with instructors on hand to troubleshoot and answer questions. Hands-on exercises will be run using free software (Program R, RStudio, Program MARK [run via R], and the R packages RMark and unmarked). We expect that participants will gain a breadth of exposure to popular methods and enough understanding to pursue further independent study if interested in applying these methods of their own research. 

Instructors

Dr. Gabe Barrile, Colorado State University
Dr. Jason Carlisle, WEST

Audience

Students and practicing ecologists. Basic familiarity with Program R is recommended. Because this workshop is sponsored by the Wyoming EPSCoR Program, registration is only open to current students, faculty, or staff of the University of Wyoming or a Wyoming community college or other residents of Wyoming. Attendance capped at 15 participants.

Maximum Participants

15 total

Format

Live workshop conducted over zoom. 6 hours total (4 sessions, 1.5 hours each)

Cost

Free for Wyoming students, faculty, staff and other residents

Additional Available Workshops

A Gentle Introduction to Program R for Ecological Data Science

Program R is a free software environment for statistical computing and graphics (https://www.r-project.org/), and R is increasingly popular among scientists across many disciplines including environmental and ecological sciences. R is notorious for having a steep learning curve, so we offer this 4-hour workshop to provide a very basic introduction to Program R and its uses, and to guide beginner R users through what may be their first encounter with R via RStudio, a program that makes the power of R more approachable (http://www.rstudio.com/). Each participant must provide his/her own computer (with software-installation privileges), and instructions will be sent to participants in advance to download the free software used in the workshop. Example datasets and materials will be distributed ahead of the workshop. Multiple assistant instructors will be on hand to assist with troubleshooting any issues that arise.

Audience

Designed for pre-beginner R users (those who may have never seen Program R) and beginner R users (those who may have dabbled lightly and would like to learn more fundamentals)

An Applied Introduction to Bayesian Statistics

Bayesian methods are increasingly used to analyze data in ecology and related disciplines and have some advantages over classical (frequentist) methods many scientists are familiar with. The aim of this workshop is to introduce participants to Bayesian statistics, with the expectation that participants will become better-equipped consumers and producers of scientific inference based on Bayesian methods of data analysis. The workshop will focus on applied tutorials built around simple and familiar statistical models. Discussions of the underlying philosophy, computational methods, and mathematical theory will be brief. Participants will use Bayesian methods to calculate basic summary statistics (mean, proportion), then advance to fitting Bayes regression models (linear regression, generalized linear models [GLM], and mixed models [GLMM]. Hands-on exercises will be run in Program R using its interface to JAGS. We expect that participants will leave with an increased fluency to evaluate research based on Bayesian statistics and with an increased capacity to learn and apply Bayesian methods in their own research.

Audience

Students and practicing data scientists, especially those familiar with basic statistical concepts but with little to no experience with Bayesian statistics. Participants that already know how to fit and interpret non-Bayesian linear regression models in Program R will benefit the most.

Introduction to Deep Learning in Python for Ecologists

Artificial neural networks (ANNs) present powerful tools for analyzing data, but their use in ecology is limited. This workshop will provide participants with the background and skills necessary to program ANNs and train and evaluate them. Then we will introduce deep neural networks (“Deep Learning”) and computer vision. Theoretical instruction will provide and introduction to the mechanisms behind neural networks and the steps to training and evaluation. Hands-on instruction will allow participants to program their own ANNs and understand how network architectures can be represented in python code. Participants will learn to program using a Pytorch (pytorch.org) framework, a common library for ANNs and deep learning. The skills provided in this workshop will lay the groundwork for participants to begin using deep learning in their own research.

Audience

Designed for those who have completed the “Introduction to Machine Learning with Python for Ecologists” workshop, or comfort with python and experience with machine learning.

Introduction to Machine Learning for Ecologists in Python

Machine learning is a useful tool for ecologists to manage and analyze data. This introductory workshop will provide the skills needed to begin working with data, and training and evaluating machine learning algorithms in python. We will include a brief introduction to python and anaconda, data management, regression, classification, random forests, model selection, and more. While theoretical introductions to each topic will be provided, the main focus will be on practical applications, as workshop participants will be programming along with instructors. Following this workshop, participants will be ready for our next workshop in artificial neural networks.

Audience

Designed for those with at least some programming experience (in any language) and some familiarity with basic statistics (like linear regression).

On-Demand Workshops

Population Modeling in Ecology

This online course introduces key software packages and fundamental models used in fish and wildlife population analysis. Course content includes the parameterization of models used to estimate ecological state variables such as occupancy and abundance as well as population vital rates such as survival, recruitment, and dispersal. The course is comprised of instructional videos with associated datasets and R code.

Audience

This course is for anyone looking for an applied introduction to key software packages and fundamental models used in fish and wildlife population analysis. Further, anyone who has or will be collecting count, detection/nondetection, or capture-mark-recapture data and is interested in estimating occupancy, abundance, survival, recruitment, or dispersal should find this course especially useful. Some prior experience with Program R would be helpful for the user, but not required in order to move through the course. 

Ready to connect with us? Let's work together.