Public Seminar - Learning models through derivatives: a story in three acts

This talk covers some recent developments in the field of machine learning in which neural networks have been applied to solve differential equations. This talk covers the background and some of its potential applications to model environmental processes and time series.

 

About the speaker

Pablo Larraondo has an MSc in Distributed Systems (2011) from the University of Navarra and PhD in Computer Science (2019) from the University of the Basque Country, in Spain. His PhD research addressed the application of machine learning techniques to analyse weather forecasting data.

Pablo has more than 15 years experience as a scientific software developer. He started his career at the Spanish (AEMET) and European (ECMWF) weather forecasting centres, and subsequently worked at CSIRO and the National Computational Infrastructure (NCI). His focus was on developing large scale software systems to process massive remote sensing and weather data.

Pablo’s research interest are in developing and combining large scale data processing systems and machine learning methodologies to understand the relationship between dynamic processes in the atmosphere and at the Earth’s surface.