Thesis Defence: Models for Forecasting and Clustering Wildfire Occurrence and Cause

Simon Snyman, supervised by Dr. W. John Braun and Dr. Lengyi Han, will defend their thesis titled “Models for Forecasting and Clustering Wildfire Occurrence and Cause” in partial fulfillment of the requirements for the degree of Master of Science in Mathematics.

An abstract for Simon Snyman’s thesis is included below.

Defences are open to all members of the campus community as well as the general public. Please email john.braun@ubc.ca to receive the Zoom link for this defence.

---

Abstract

Exponential smoothing methods offer several tools for forecasting and simulating varying time series patterns, including historical wildfire counts. The Box-Cox transform, ARMA errors, trend and seasonal components (BATS), and the trigonometric BATS model (TBATS) are exponential smoothing techniques capable of modelling complex seasonality, non-integer frequencies, and more. The BATS and TBATS frameworks support short- and intermediate-term forecasting and simulation, while also providing a foundation for time series clustering of wildfire counts. This application of the BATS and TBATS models aims to support fire agencies in forecasting and simulating wildfire occurrences across Canada on an increased scale that provides alternative methods for future use. Furthermore, we provide preliminary information on clustering wildfire counts using TBATS models that can be extended for future work and practical implementation.

Variable-length Markov chains (VLMCs) are an extension of traditional fixed-order Markov chains that can reduce model complexity and improve computational efficiency. To assess the practicality and effectiveness of VLMCs for modelling wildfire cause in Canada, they will be evaluated in terms of forecasting and simulation. Furthermore, VLMCs will be compared to a first-order Markov chain, serving as a baseline model for categorical wildfire outcomes in Canada.