Mélisande Teng: Species distribution modeling using remote sensing and citizen science data

Biodiversity is declining at an unprecedented rate, impacting ecosystem services and human wellbeing. A first step towards guiding biodiversity conservation policies is understanding the current state of biodiversity, and in particular, through mapping species to their habitat. 

However, there remain large knowledge gaps about species distribution, due to the amount of effort and expertise required for traditional field monitoring. Furthermore, traditional methods in ecology for species distribution modeling (SDM) are often unable to account for complex relationships between species and characteristics of the environment and generally focus either on narrow geographical areas or narrow sets of species, while species interact with each other. 

With the rise of citizen science, which offers rich and abundant data in comparison with field surveys, opening new possibilities to scientists, machine learning appears as a promising tool to model jointly species distributions.

In this talk, I will focus on approaches to tackle the challenge of joint species distribution modeling at scale with machine learning. I will present SatBird, a dataset and benchmark for bird species distribution modeling using remote sensing and citizen science data and introduce methods to leverage partial information about species present in a given location to predict occurrence patterns of other species. I will also share some personal learnings and reflections on applied research in ML for biodiversity conservation.

Mélisande Teng is a PhD candidate in Computer Science at Université de Montréal / Mila - Quebec AI Institute and her research focuses on applications of machine learning and remote sensing for biodiversity monitoring, in particular, bird and butterfly species distribution modeling and carbon storage quantification in tree plantations. She aims at building bridges between the machine learning and ecology communities and the general public. She holds a MSc in Mathematics, Vision and Learning (MVA) from ENS Paris-Saclay and a Msc in Management and Social Entrepreneurship from ESSEC Business School.