Martí i Franquès StandCall for 1 PhD candidate within the project Phd in Graph Convolution Networks...
Universitat Rovira i Virgili
Tarragona, Spain
hace 9 horas
source : Euraxess

The Universitat Rovira i Virgili, in collaboration with the research institutions affiliated to the Campus of International Excellence Southern Catalonia (CEICS), is launching the Martí i Franquès research grants programme, a public-private cooperation designed to attract highly talented doctoral students and postdoctoral researchers to work on exciting research projects.

This programme honours the scientist Antoni Martí i Franquès (Altafulla, 1750 Tarragona, 1832), who made remarkable contributions not only to the fields of biology, physics and chemistry, but also to the economic development of Southern Catalonia.

He was the first scientist to accurately establish the composition of air.


In some applications, there are objects that their nature, class or type is unknown, and it is needed to predict or decide this class or the nature of the object.

Moreover, in some of these applications, it is useful to represent the objects as nodes of a graph and their relations as the edges that connect these nodes.

This happens due to the strong relation between objects that influences on their nature. Graph Convolutional Networks (GCN) are a form of graph neural network that perform parameterized message-passing operations in a graph, modelled as a first-order approximation to spectral graph convolutions.

GCNs achieved state-of-the-art performance in node-level classification tasks in a number of undirected graph datasets. The aim of the PhD thesis is to apply graph based techniques, and more specifically GCNs, in order to estimate chemical properties and predict their effects on the environment.

The diversity of chemical substances that are of environmental concern means that direct measurements, through time-consuming and expensive animal tests and in vitro experiments, will never be sufficient to meet the data needs of environmental scientists and regulators.

Computational modelling using machine learning techniques emerges here as a promising alternative to the analysis of very large datasets comprising thousands of diverse molecular structures.

Required Research Experiences

  • RESEARCH FIELD Computer science Modelling tools
  • RESEARCH FIELD Engineering Chemical engineering
  • Offer Requirements

  • REQUIRED EDUCATION LEVEL Mathematics : Master Degree or equivalent Computer science : Master Degree or equivalent Engineering : Master Degree or equivalent
  • Skills / Qualifications

    In general, be in possession of an official undergraduate degree, or equivalent, and of a master degree, and have passed a minimum of 300 ECTS credits during the course of their official university studies, of which at least 60 must be master s degree credits

    Reportar esta oferta

    Thank you for reporting this job!

    Your feedback will help us improve the quality of our services.

    Mi Correo Electrónico
    Al hacer clic en la opción "Continuar", doy mi consentimiento para que neuvoo procese mis datos de conformidad con lo establecido en su Política de privacidad . Puedo darme de baja o retirar mi autorización en cualquier momento.
    Formulario de postulación