Predicting Ecosystem Re-assembly using Machine Learning: Unveiling Ecosyste

How machine learning and network science can help predict ecosystem resilience and species interactions under global environmental change.

Climate change and extreme environmental events are accelerating biodiversity loss worldwide. Understanding how ecosystems respond to these pressures is essential for predicting future ecological dynamics and supporting effective conservation strategies.

In this seminar, Jorge Eduardo Castro Cruces, PhD researcher at Queen Mary University of London, will present his research on how machine learning and network science can be used to study ecological systems and predict how ecosystems reorganise under environmental stress.

By analysing ecological networks and food webs, this research explores how the loss or decline of species can trigger cascading effects across ecosystems. Using advanced data science techniques applied to graph structures, the study aims to identify structural patterns that allow researchers to predict new ecological interactions and ecosystem re-assembly processes under conditions of global environmental change.

The project contributes to the growing field of ecoinformatics, proposing predictive frameworks that may help scientists and decision-makers better understand and manage ecosystem resilience in a changing climate.

Speaker

Jorge Eduardo Castro Cruces
PhD Researcher
School of Electronic Engineering and Computer Science
Queen Mary University of London

Organised by

UNAM–UK Centre for Mexican Studies
in collaboration with MexSocUK – Mexican Society of Students in the United Kingdom