About me:
I am a Visiting Scientist at the Natural History Museum of Crete, Greece. Since March 2019 I am also a Data Analytics consultant.
Before that I was a Senior Assistant Professor in Data Analytics, at the Institute for Applied Data Analytics, Universiti Brunei Darussalam in Brunei, Borneo (South East Asia). Before Borneo, I was a lecturer in Predictive Modelling at the School of Biological and Chemical Sciences, Queen Mary University of London, UK.
I am coming from an engineering background with a PhD in Mathematical Ecology. I have been affiliated at several different Schools including Mathematics, Biology, and Engineering. I am interested in timely biological, environmental, and behavioural questions and I approach them from a statistical, mathematical and computational perspective. While the challenge is to employ state-of-the-art quantitative methods, I also enjoy explaining complex stats to non-numerically trained audience through talks or teaching
You can find more information at my webpage.
About the paper:
Minimal effect of prescribed burning on fire spread rate and intensity in savanna ecosystems
Prescribed or controlled burning treatments are debated as a potential measure for ameliorating the spread and intensity of wildfires.
Machine learning analysis using random forests was performed in a spatio-temporal data set comprising a large number of savanna fires across 22 years.
Results indicate that fire return interval was not an important predictor of fire spread rate or fire intensity, having a feature importance of 3.5%, among eight other predictor variables. Manipulating burn seasonality showed a feature importance of 6% or less regarding fire spread rate or fire intensity. Overall prescribed burning effects were low in comparison with meteorological (hydrological and climatic) variables.
Predicting fire spread rate and intensity has been a poor endeavour thus far and we show that more data of the variables already monitored would not result in higher predictive accuracy.
The full text is published at Stochastic Environmental Research and Risk Assessment.
