Exposure Modeling Boot Camp: Traditional and Machine Learning Methods in Environmental Epidemiology
August 8-9, 2024 | In-person training
The next Exposure Modeling Boot Camp is on August 8-9, 2024. Sign up below to hear about registration opening!
The Exposure Modeling Boot Camp is a two-day workshop focused on skills development in the application of both traditional and machine learning methods in predicting spatial/temporal variations in environmental exposures (e.g., air pollution, temperature, noise) using real data sets.
Subscribe for updates on registration and scholarship dates, deadlines, and announcements.
Exposure Modeling Boot Camp Overview
Summer 2024 dates: In-person training August 8-9, 2024; 9:00am - ~5:00pm EDT
This two-day workshop is focused on practical skills development in modeling environmental exposures using both traditional and machine learning methods. The workshop is led by Dr. Scott Weichenthal (Associate Professor, McGill University) who has extensive experience in the development and application of exposure models in environmental epidemiology. Morning sessions will include lectures discussing important concepts related to exposure science and exposure modeling in environmental epidemiology and afternoon sessions will focus on hands-on laboratory exercises applying both traditional (e.g., linear regression, generalized additive models) and machine learning methods (e.g., random forest, neural networks) in modeling environmental exposures using real data sets. Participants will learn practical skills in working with environmental exposure data and will gain knowledge in the application of multiple approaches to modeling environmental exposures known to impact human health.
By the end of the workshop, participants will be familiar with the following topics:
- Principles of exposure science as applied to environmental epidemiology
- The intuition behind how various modeling approaches work including linear regression models, generalized additive models, random forest models, dense neural networks, and convolutional neural networks
- Data handling and cleaning
- Developing and evaluating predictive models
- Data collection and management for exposure models based on non-traditional data streams including images and audio data
Investigators at all career stages are welcome to attend but we particularly encourage trainees and early-stage investigators to participate. There are four requirements to attend this training:
- Each participant should have an introductory background in statistics (i.e., linear and logistic regression).
- Each participant should be familiar with R/RStudio. All code examples used in the laboratory exercises will be annotated in detail but students will benefit from previous experience using R.
- Familiarity with Python is an asset but is not required. We will use Python code in training convolutional neural networks but examples will be annotated in detail so students will understand what is happening without having to reproduce code on their own.
- Each participant is required to have a personal laptop and a free, basic RStudio Cloud account. All lab sessions on the first day will be done using RStudio Cloud.
Scott Weichenthal, PhD, Department of Epidemiology, Biostatistics, and Occupational Health, McGill University. Dr. Weichenthal is an Associate Professor in the Department of Epidemiology, Biostatistics, and Occupational Health. His research program is dedicated to identifying and evaluating environmental risk factors for chronic diseases such as cancer and cardiovascular disease.
Training scholarships are available for the Exposure Modeling Boot Camp.
Summer 2024: The Exposure Modeling Boot Camp is a live, in-person training taking place at the Columbia University Irving Medical Campus in NYC. All training start and end times are in EDT.
"The teaching team is excellent and made traditional as well as novel exposure assessment techniques understandable and accessible. The workshop moved fairly quickly and covered a lot of ground, but it was well designed to accommodate questions, discussions and hands-on learning." - PhD student at UC Berkeley School of Public Health, 2023
"Excellent introduction to using machine learning for exposure assessment using spatiotemporal data!" - Faculty member at USF College of Public Health, 2023
Registration fee includes course material, breakfast, and lunch on training days. Course material will be available to all attendees during and after the workshop. Lodging and transportation are not included.
|Early-Bird Rate (through 6/10/24)||Regular Rate (6/11/24 - 8/1/24)||Columbia Discount*|
|Faculty/Academic Staff/Non-Profit Organizations/Government Agencies||$1,395||$1,595||10%|
*Columbia Discount: This discount is valid for any active student, postdoc, staff, or faculty at Columbia University. If paying by credit card, use your Columbia email address during the registration process to automatically have the discount applied. If paying by internal transfer within Columbia, submit this Columbia Internal Transfer Request form to receive further instructions. Please note: filling out this form is not the same as registering for a training and does not guarantee a training seat.
Invoice Payment: If you would prefer to pay by invoice/check, please submit this Invoice Request form to receive further instructions. Please note: filling out this form is not the same as registering for a training and does not guarantee a training seat.
Registration Fee: This fee includes course material, which will be made available to all participants both during and after the conclusion of the training.
Cancellations: Cancellation notices must be received via email at least 30 days prior to the training start date in order to receive a full refund, minus a $75 administrative fee. Cancellation notices received via email 14-29 days prior to the training will receive a 75% refund, minus a $75 administrative fee. Please email your cancellation notice to Columbia.ExposureModeling@gmail.com. Due to workshop capacity and preparation, we regret that we are unable to refund registration fees for cancellations <14days prior to the training.
If you are unable to attend the training, we encourage you to send a substitute within the same registration category. Please inform us of the substitute via email at least one week prior to the training to include them on attendee communications, updated registration forms, and materials. Should the substitute fall within a different registration category your credit card will be credited/charged respectively. Please email substitute inquiries to Columbia.ExposureModeling@gmail.com. In the event Columbia must cancel the event, your registration fee will be fully refunded.
- Subscribe for updates on new Boot Camp details and registration deadlines.
- Contact the Boot Camp team.
The Exposure Modeling Boot Camp is hosted by Columbia University's SHARP Program at the Mailman School of Public Health.