Uncovering extreme climate events with machine learning
One of the most worrisome consequences of climate change for modern societies is the occurrence of extreme events, in particular heatwaves, wildfires and droughts. Extreme events impact not only our environment, but also our economy and health, so our society in general.
From a geophysical and economical point of view, extreme events have a significant impact in the sustainability of our social, economical and technological environment. From the point of view of statistics and data science, extreme events present theoretical and practical challenges where the aim of scientists is to predict the likelihood of their occurrence or to determine the main risk factors driven their amplitude and duration. In collaboration with the Institute Dom Luiz at the University of Lisbon (Portugal), the student will focus on one of the topics listed below, depending on his/her motivation. The supervision will be shared with University of Lisbon. Short visits to Lisbon (Portugal) may take place in the course of the thesis, to coordinate the ongoing work with the other partners of the DHEFEUS project.
Goal
Depending on the preferences of the student:
- Evaluate the link between droughts and heatwaves through the modelling of statistical dependencies
- Identification of the key moments (months, seasons) and timescales of dry and/or hot conditions involved in the reinforcement and triggering of fires and consequent smoke waves
- To explore the impact of single or composite climate extremes and fires on ozone exceedances.
- Explore possible connections between extreme events, such the ones above, with public health.
Learning outcome
- Climate data analysis, Machine Learning and AI methods to analyze data
- Scientific writing towards a publication
Qualifications
- Some knowledge on machine learning and programming
Supervisors
- Pedro Lind
Collaboration partners
- The Institute Dom Luiz at the University of Lisbon (Portugal)
