Apply Machine Learning to Your Ecological Time Series Analysis with Machine Learning for Ecological Time Series (METR01) Take your ecological modelling to the next level by mastering modern machine learning techniques applied to time series data - one of the fastest-growing and most impactful areas in ecological research. This advanced, hands-on course is designed for ecologists, researchers, and practitioners who want to extract deeper insights, improve predictive performance, and handle complex temporal patterns in ecological datasets. What you'll learn Core machine learning approaches for ecological time series Handling temporal autocorrelation and non-stationarity Building and tuning predictive models in REvaluating model performance and avoiding overfitting Applying methods to real-world ecological datasets Expect a highly practical format combining theory, real datasets, and guided coding exercises - consistent with PR Stats' applied training approach. Who should attend? Ecologists and environmental scientists PhD students and academic researchers Data analysts working with temporal or monitoring data Anyone looking to apply machine learning to ecological problems Why take this course? Ecological time series are central to understanding biodiversity change, climate impacts, and ecosystem dynamics. Machine learning offers powerful tools - but only when applied correctly. This course will help you move beyond basic analysis to build robust, interpretable, and high-performing models you can confidently use in research and decision-making. Learn more & enrol Explore the full course details here: PR Statscourse page for Machine Learning for Ecological Time Series (METR01) Questions? Email:oliver@prstats.org Oliver Hooker PhD. PR stats Oliver Hooker (to subscribe/unsubscribe the EvolDir send mail to golding@mcmaster.ca)