AI + Machine Learning for predicting species responses to global change
Species’ distributions are shifting in response to global climate change and other human pressures. Accurate methods to monitor and predict distribution shifts are urgently needed to manage threatened species and ecosystems, and to control invasive species and diseases. This requires a step-change in the data and methods used to monitor and predict organism behaviours and ultimately shifts in species' distributions.
This project brings together advances in biological modelling, machine learning, and artificial intelligence to determine whether alternative low-cost data sources combined with new modelling techniques can transform our capacity to predict and manage biological responses to global change.
Areas of research
Ecology; Biodiversity conservation; Machine learning; Modelling
PhD student role description
The successful candidate will develop near-real-time integration between emerging environmental and ecological AI-driven data sources (e.g., automated acoustic and machine vision species classification, web scraping, environmental DNA, satellite imagery) and agent-based models and ecological simulations. Our recent work, funded by the Monash Data Futures Institute, has piloted the development of novel data sources and agent-based models for the Australian cane toad invasion. The successful candidate will use this case study as a foundation for integrating novel data sources into modelling approaches that are generalisable to a broad range of taxa and questions.
Required skills and experience
This position would suit a candidate who has an interest in ecology and biodiversity conservation with computational modelling experience (e.g., using R, Python, Matlab).